{"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":"2026-10-13T14:31:25Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:d42a4c4c0f7d3cdf","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677191999999998},"medium":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063079999999998},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063079999999998},"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":17.677192}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292},"codegen_output_tokens":{"attempt_count":30,"output_max":149830,"output_mean":37334.40740740741,"output_min":2400,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":149830,"output_mean":94967.22222222222,"output_min":65515,"run_count":9},"medium":{"attempt_count":10,"output_max":31033,"output_mean":13777.666666666666,"output_min":6104,"run_count":9},"none":{"attempt_count":9,"output_max":3890,"output_mean":3258.3333333333335,"output_min":2400,"run_count":9}},"display_name":"Claude Opus 5.5","economics":{"all":78.05527439288385,"highest":91.8036584576873,"medium":83.44297922948483,"none":58.91918549147943},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:14:22Z","match_totals_all":{"draws":869,"losses":967,"wins":9997},"match_totals_tracks":{"highest":{"draws":75,"losses":127,"wins":3444},"medium":{"draws":114,"losses":216,"wins":3764},"none":{"draws":680,"losses":624,"wins":2789}},"model_slug":"claude-opus-5-5","overall":{"max":100.0,"mean":78.05527439288386,"min":27.514151803230728},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.42997014112734,"GB2-02":99.99999999999999,"GB2-03":93.26764898568224,"GB2-04":95.10558941046477,"GB2-05":94.85227188248896,"GB2-06":100.0,"GB2-07":99.12225787350019,"GB2-08":83.65152936823499},"per_game_all":{"GB2-01":76.21761181372258,"GB2-02":82.18958052366769,"GB2-03":64.8207935947226,"GB2-04":70.65062866755396,"GB2-05":84.51152345032529,"GB2-06":83.21204069012511,"GB2-07":89.75636594502659,"GB2-08":73.08365045792702},"per_game_match_totals_all":{"GB2-01":{"draws":57,"losses":118,"wins":1222},"GB2-02":{"draws":125,"losses":57,"wins":1096},"GB2-03":{"draws":321,"losses":110,"wins":889},"GB2-04":{"draws":282,"losses":80,"wins":982},"GB2-05":{"draws":0,"losses":91,"wins":1361},"GB2-06":{"draws":61,"losses":114,"wins":1193},"GB2-07":{"draws":0,"losses":73,"wins":1337},"GB2-08":{"draws":23,"losses":324,"wins":1917}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":69,"wins":389},"GB2-02":{"draws":23,"losses":4,"wins":399},"GB2-03":{"draws":3,"losses":10,"wins":427},"GB2-04":{"draws":40,"losses":7,"wins":401},"GB2-05":{"draws":0,"losses":7,"wins":477},"GB2-06":{"draws":1,"losses":0,"wins":455},"GB2-07":{"draws":0,"losses":7,"wins":463},"GB2-08":{"draws":0,"losses":23,"wins":433}},"medium":{"GB2-01":{"draws":28,"losses":16,"wins":422},"GB2-02":{"draws":9,"losses":14,"wins":403},"GB2-03":{"draws":21,"losses":26,"wins":393},"GB2-04":{"draws":34,"losses":34,"wins":380},"GB2-05":{"draws":0,"losses":47,"wins":437},"GB2-06":{"draws":22,"losses":27,"wins":407},"GB2-07":{"draws":0,"losses":27,"wins":443},"GB2-08":{"draws":0,"losses":25,"wins":879}},"none":{"GB2-01":{"draws":21,"losses":33,"wins":411},"GB2-02":{"draws":93,"losses":39,"wins":294},"GB2-03":{"draws":297,"losses":74,"wins":69},"GB2-04":{"draws":208,"losses":39,"wins":201},"GB2-05":{"draws":0,"losses":37,"wins":447},"GB2-06":{"draws":38,"losses":87,"wins":331},"GB2-07":{"draws":0,"losses":39,"wins":431},"GB2-08":{"draws":23,"losses":276,"wins":605}}},"per_game_raw_elo_all":{"GB2-01":2012.0260247337328,"GB2-02":2016.9492454173605,"GB2-03":1954.4806337391321,"GB2-04":1866.4633677076965,"GB2-05":2366.7842422162307,"GB2-06":2243.6554377250864,"GB2-07":2353.105284783452,"GB2-08":2123.154004364935},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1894.066415336434,"GB2-02":2158.7005735170424,"GB2-03":2329.7943560859057,"GB2-04":2048.7299045419304,"GB2-05":2598.520165099116,"GB2-06":2617.4062268682983,"GB2-07":2544.120122862298,"GB2-08":2287.7198315557116},"medium":{"GB2-01":2114.3957433977785,"GB2-02":2124.5274993472235,"GB2-03":2071.372267892755,"GB2-04":1910.3451432945867,"GB2-05":2214.0637041637833,"GB2-06":2212.5360382844683,"GB2-07":2308.843616430512,"GB2-08":2410.6483332588123},"none":{"GB2-01":2027.6159154669858,"GB2-02":1767.6196633878162,"GB2-03":1462.2752772387355,"GB2-04":1640.3150552865727,"GB2-05":2287.7688573857927,"GB2-06":1901.0240480224923,"GB2-07":2206.3521150575457,"GB2-08":1671.0938482802817}},"per_game_tracks":{"highest":{"GB2-01":68.42997014112734,"GB2-02":99.99999999999999,"GB2-03":93.26764898568224,"GB2-04":95.10558941046477,"GB2-05":94.85227188248896,"GB2-06":100.0,"GB2-07":99.12225787350019,"GB2-08":83.65152936823499},"medium":{"GB2-01":82.9760157381953,"GB2-02":95.70630629060287,"GB2-03":73.68057999525483,"GB2-04":76.53830897325153,"GB2-05":77.69667728932177,"GB2-06":81.81423437979072,"GB2-07":87.58611568312568,"GB2-08":91.54559548633588},"none":{"GB2-01":77.2468495618451,"GB2-02":50.86243528040017,"GB2-03":27.514151803230728,"GB2-04":40.30798761894558,"GB2-05":80.98562117916514,"GB2-06":67.82188769058459,"GB2-07":82.56072427845389,"GB2-08":44.05382651921021}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":91.8036584576873,"medium":83.44297922948483,"none":58.91918549147944},"reasoning_agg":{"highest":{"max":100.0,"mean":91.8036584576873,"min":68.42997014112734},"medium":{"max":95.70630629060287,"mean":83.44297922948483,"min":73.68057999525483},"none":{"max":82.56072427845389,"mean":58.91918549147944,"min":27.514151803230728}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":84.26964801008066,"reasoning_variance":32.884472966207866,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.214373617196799},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":91.68101276294446,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.12264569474284315},"medium":{"ceiling_score":95.70630629060287,"expected_score":90.09954867234919,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.6565694428643525},"none":{"ceiling_score":82.56072427845389,"expected_score":71.02838259494831,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":12.109197103468873}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:42003ea533b21c57","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.2723400000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349},"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":15.613270000000005},"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":77.85671002621308,"highest":90.73282294160947,"medium":75.67059260999093,"none":67.1667145270388},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:04:32Z","match_totals_all":{"draws":1169,"losses":1063,"wins":12304},"match_totals_tracks":{"highest":{"draws":128,"losses":212,"wins":4490},"medium":{"draws":390,"losses":376,"wins":4084},"none":{"draws":651,"losses":475,"wins":3730}},"model_slug":"gpt-6-astra","overall":{"max":100.0,"mean":77.85671002621307,"min":37.97836538155213},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.03472238859375,"GB2-02":98.39906794308499,"GB2-03":97.27835430870856,"GB2-04":89.77905111462037,"GB2-05":99.64850879716332,"GB2-06":78.43108126729338,"GB2-07":100.0,"GB2-08":67.29179771341136},"per_game_all":{"GB2-01":78.81038334339483,"GB2-02":62.31238062172994,"GB2-03":70.96008030030275,"GB2-04":78.95995095180761,"GB2-05":89.65954553497266,"GB2-06":77.0792829251629,"GB2-07":95.53426723192875,"GB2-08":69.53778930040511},"per_game_match_totals_all":{"GB2-01":{"draws":72,"losses":201,"wins":1577},"GB2-02":{"draws":490,"losses":65,"wins":1137},"GB2-03":{"draws":296,"losses":102,"wins":1408},"GB2-04":{"draws":190,"losses":114,"wins":1474},"GB2-05":{"draws":0,"losses":77,"wins":1831},"GB2-06":{"draws":121,"losses":200,"wins":1501},"GB2-07":{"draws":0,"losses":57,"wins":1809},"GB2-08":{"draws":0,"losses":247,"wins":1567}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":19,"wins":597},"GB2-02":{"draws":26,"losses":9,"wins":521},"GB2-03":{"draws":12,"losses":6,"wins":582},"GB2-04":{"draws":46,"losses":22,"wins":524},"GB2-05":{"draws":0,"losses":3,"wins":633},"GB2-06":{"draws":44,"losses":55,"wins":503},"GB2-07":{"draws":0,"losses":10,"wins":612},"GB2-08":{"draws":0,"losses":88,"wins":518}},"medium":{"GB2-01":{"draws":44,"losses":146,"wins":428},"GB2-02":{"draws":189,"losses":21,"wins":346},"GB2-03":{"draws":69,"losses":29,"wins":506},"GB2-04":{"draws":55,"losses":26,"wins":511},"GB2-05":{"draws":0,"losses":43,"wins":593},"GB2-06":{"draws":33,"losses":56,"wins":529},"GB2-07":{"draws":0,"losses":17,"wins":605},"GB2-08":{"draws":0,"losses":38,"wins":566}},"none":{"GB2-01":{"draws":28,"losses":36,"wins":552},"GB2-02":{"draws":275,"losses":35,"wins":270},"GB2-03":{"draws":215,"losses":67,"wins":320},"GB2-04":{"draws":89,"losses":66,"wins":439},"GB2-05":{"draws":0,"losses":31,"wins":605},"GB2-06":{"draws":44,"losses":89,"wins":469},"GB2-07":{"draws":0,"losses":30,"wins":592},"GB2-08":{"draws":0,"losses":121,"wins":483}}},"per_game_raw_elo_all":{"GB2-01":2051.298802007607,"GB2-02":1858.7486208477496,"GB2-03":2035.4793421853954,"GB2-04":1928.3940087793442,"GB2-05":2482.151292931497,"GB2-06":2107.121686840276,"GB2-07":2470.944022106256,"GB2-08":2067.936909293751},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2297.049284240982,"GB2-02":2145.958917119414,"GB2-03":2382.7096159040225,"GB2-04":2009.030405585265,"GB2-05":2706.00371864249,"GB2-06":2137.216809648715,"GB2-07":2562.0214366345217,"GB2-08":2032.9617296466192},"medium":{"GB2-01":1764.0037193715546,"GB2-02":1765.2102918689877,"GB2-03":2025.4326360216992,"GB2-04":1972.0633518705865,"GB2-05":2329.1440612596944,"GB2-06":2154.512234858813,"GB2-07":2483.130617319016,"GB2-08":2258.4569844311554},"none":{"GB2-01":2092.843402410285,"GB2-02":1665.0766535548476,"GB2-03":1698.2957746304644,"GB2-04":1804.0882688821805,"GB2-05":2411.3060988923057,"GB2-06":2029.636016013301,"GB2-07":2367.6800123652306,"GB2-08":1912.392013803478}},"per_game_tracks":{"highest":{"GB2-01":95.03472238859375,"GB2-02":98.39906794308499,"GB2-03":97.27835430870856,"GB2-04":89.77905111462037,"GB2-05":99.64850879716332,"GB2-06":78.43108126729338,"GB2-07":100.0,"GB2-08":67.29179771341136},"medium":{"GB2-01":59.843288002034264,"GB2-02":50.55970854055272,"GB2-03":70.19859149673042,"GB2-04":84.81912888712051,"GB2-05":82.83190624911403,"GB2-06":79.20794891040852,"GB2-07":96.13180371070035,"GB2-08":81.77236508326675},"none":{"GB2-01":81.55313963955648,"GB2-02":37.97836538155213,"GB2-03":45.40329509546931,"GB2-04":62.28167285368195,"GB2-05":86.49822155864064,"GB2-06":73.59881859778679,"GB2-07":90.47099798508589,"GB2-08":59.54920510453725}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":90.73282294160947,"medium":75.67059260999093,"none":67.1667145270388},"reasoning_agg":{"highest":{"max":100.0,"mean":90.73282294160947,"min":67.29179771341136},"medium":{"max":96.13180371070035,"mean":75.67059260999093,"min":50.55970854055272},"none":{"max":90.47099798508589,"mean":67.1667145270388,"min":37.97836538155213}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":84.45052821559791,"reasoning_variance":23.566108414570664,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.593818189384848},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":89.90575191735047,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.8270710242589985},"medium":{"ceiling_score":96.13180371070035,"expected_score":81.67042772492216,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.99983511493123},"none":{"ceiling_score":90.47099798508589,"expected_score":81.7754050045211,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":14.608690477482298}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:bbc1e2b29dda8249","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609},"historical-provider-setting-intensive":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781584},"codegen_output_tokens":{"attempt_count":35,"output_max":231035,"output_mean":46647.59375,"output_min":5610,"run_count":32},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":231035,"output_mean":80471.125,"output_min":38285,"run_count":16},"medium":{"attempt_count":9,"output_max":25949,"output_mean":17238.625,"output_min":9715,"run_count":8},"none":{"attempt_count":8,"output_max":10198,"output_mean":8409.5,"output_min":5610,"run_count":8}},"display_name":"Claude Fable 5.1","economics":{"all":74.54702605125493,"highest":86.20841048951151,"medium":69.12602866421003,"none":68.30663900004325},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:19:09Z","match_totals_all":{"draws":994,"losses":1449,"wins":13871},"match_totals_tracks":{"highest":{"draws":165,"losses":356,"wins":6118},"medium":{"draws":371,"losses":595,"wins":3868},"none":{"draws":458,"losses":498,"wins":3885}},"model_slug":"claude-fable-5-1","overall":{"max":95.77544296238115,"mean":74.54702605125492,"min":35.839263610654065},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.4012239184376,"GB2-02":90.12822927490443,"GB2-03":83.92265064315916,"GB2-04":72.25561082691297,"GB2-05":83.40352256312052,"GB2-06":95.77544296238115,"GB2-07":88.80615243941408,"GB2-08":93.97445128776208},"per_game_all":{"GB2-01":71.17540217239555,"GB2-02":73.74030195948858,"GB2-03":74.39421180275858,"GB2-04":50.8210827331555,"GB2-05":80.50827224397544,"GB2-06":82.15198067002088,"GB2-07":84.86881948737751,"GB2-08":78.71613734086732},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":49,"wins":564},"GB2-02":{"draws":27,"losses":17,"wins":512},"GB2-03":{"draws":6,"losses":24,"wins":565},"GB2-04":{"draws":56,"losses":41,"wins":495},"GB2-05":{"draws":0,"losses":41,"wins":595},"GB2-06":{"draws":9,"losses":6,"wins":587},"GB2-07":{"draws":0,"losses":34,"wins":588},"GB2-08":{"draws":0,"losses":14,"wins":596}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":49,"wins":564},"GB2-02":{"draws":27,"losses":17,"wins":512},"GB2-03":{"draws":6,"losses":24,"wins":565},"GB2-04":{"draws":56,"losses":41,"wins":495},"GB2-05":{"draws":0,"losses":41,"wins":595},"GB2-06":{"draws":9,"losses":6,"wins":587},"GB2-07":{"draws":0,"losses":34,"wins":588},"GB2-08":{"draws":0,"losses":14,"wins":596}}},"per_game_raw_elo_all":{"GB2-01":1935.6515451678258,"GB2-02":1949.7022914897377,"GB2-03":2080.7875725504505,"GB2-04":1718.670749986734,"GB2-05":2277.071479264758,"GB2-06":2220.055293017798,"GB2-07":2253.425093901426,"GB2-08":2210.8645914088643},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2090.542331061875,"GB2-02":2080.1321482849817,"GB2-03":2206.5010758602334,"GB2-04":1878.4255435190767,"GB2-05":2341.953969065709,"GB2-06":2523.354800042299,"GB2-07":2333.7259367938486,"GB2-08":2448.471123194354},"medium":{"GB2-01":1732.270218665832,"GB2-02":1978.5247462245675,"GB2-03":2021.304080627593,"GB2-04":1607.0089765068142,"GB2-05":2170.6931542966922,"GB2-06":2108.374220058872,"GB2-07":2322.918153744594,"GB2-08":2090.710071070006},"none":{"GB2-01":1984.1420857757705,"GB2-02":1790.449979959664,"GB2-03":2014.5575611635252,"GB2-04":1670.5777299343108,"GB2-05":2318.567314431874,"GB2-06":2028.4368589522219,"GB2-07":2103.6311911658354,"GB2-08":2093.4125799622325}},"per_game_tracks":{"highest":{"GB2-01":81.4012239184376,"GB2-02":90.12822927490443,"GB2-03":83.92265064315916,"GB2-04":72.25561082691297,"GB2-05":83.40352256312052,"GB2-06":95.77544296238115,"GB2-07":88.80615243941408,"GB2-08":93.97445128776208},"medium":{"GB2-01":57.74825620449023,"GB2-02":77.36171430212237,"GB2-03":69.88566817078501,"GB2-04":35.839263610654065,"GB2-05":75.7613539265868,"GB2-06":77.1355436136186,"GB2-07":88.27622225679691,"GB2-08":71.00020722862615},"none":{"GB2-01":74.37672639425882,"GB2-02":53.73096230143895,"GB2-03":69.37431659433156,"GB2-04":44.36837376189947,"GB2-05":82.35994024221897,"GB2-06":73.54495543406291,"GB2-07":77.52408376592156,"GB2-08":71.17375350621373}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":86.20841048951151,"medium":69.12602866421003,"none":68.30663900004325},"reasoning_agg":{"highest":{"max":95.77544296238115,"mean":86.20841048951151,"min":72.25561082691297},"medium":{"max":88.27622225679691,"mean":69.12602866421003,"min":35.839263610654065},"none":{"max":82.35994024221897,"mean":68.30663900004325,"min":44.36837376189947}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":95.77544296238115,"expected_score":80.72569856657671,"reasoning_variance":17.90177148946826,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.178672515321793},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":95.77544296238115,"expected_score":85.28810816281532,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9203023266961878},"medium":{"ceiling_score":88.27622225679691,"expected_score":74.00128777019692,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.875259105986899},"none":{"ceiling_score":82.35994024221897,"expected_score":82.88769976671786,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":14.58106076667461}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:4769998e8ac60f55","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":73.09601802211813,"highest":87.30859425337505,"medium":73.10720413547,"none":58.872255677509344},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:00:58Z","match_totals_all":{"draws":831,"losses":1147,"wins":8952},"match_totals_tracks":{"highest":{"draws":101,"losses":211,"wins":3334},"medium":{"draws":205,"losses":363,"wins":3074},"none":{"draws":525,"losses":573,"wins":2544}},"model_slug":"gpt-6-1-sol","overall":{"max":100.0,"mean":73.09601802211813,"min":28.976020357385288},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.345911920664896,"GB2-02":90.68272636600271,"GB2-03":99.99999999999999,"GB2-04":100.0,"GB2-05":94.85227188248896,"GB2-06":79.08258821813236,"GB2-07":92.66060584281914,"GB2-08":80.84464979689227},"per_game_all":{"GB2-01":53.796309037685766,"GB2-02":55.89787153771826,"GB2-03":83.44746465741116,"GB2-04":72.40099029961947,"GB2-05":87.47632136702157,"GB2-06":76.5132149688145,"GB2-07":91.60596062147026,"GB2-08":63.63001168720407},"per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":428,"wins":903},"GB2-02":{"draws":404,"losses":70,"wins":804},"GB2-03":{"draws":32,"losses":74,"wins":1214},"GB2-04":{"draws":216,"losses":99,"wins":1029},"GB2-05":{"draws":0,"losses":67,"wins":1385},"GB2-06":{"draws":110,"losses":130,"wins":1128},"GB2-07":{"draws":0,"losses":57,"wins":1353},"GB2-08":{"draws":2,"losses":222,"wins":1136}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":111,"wins":355},"GB2-02":{"draws":27,"losses":9,"wins":390},"GB2-03":{"draws":2,"losses":5,"wins":433},"GB2-04":{"draws":31,"losses":7,"wins":410},"GB2-05":{"draws":0,"losses":7,"wins":477},"GB2-06":{"draws":41,"losses":28,"wins":387},"GB2-07":{"draws":0,"losses":17,"wins":453},"GB2-08":{"draws":0,"losses":27,"wins":429}},"medium":{"GB2-01":{"draws":11,"losses":111,"wins":344},"GB2-02":{"draws":124,"losses":31,"wins":271},"GB2-03":{"draws":4,"losses":11,"wins":425},"GB2-04":{"draws":34,"losses":43,"wins":371},"GB2-05":{"draws":0,"losses":21,"wins":463},"GB2-06":{"draws":32,"losses":27,"wins":397},"GB2-07":{"draws":0,"losses":17,"wins":453},"GB2-08":{"draws":0,"losses":102,"wins":350}},"none":{"GB2-01":{"draws":56,"losses":206,"wins":204},"GB2-02":{"draws":253,"losses":30,"wins":143},"GB2-03":{"draws":26,"losses":58,"wins":356},"GB2-04":{"draws":151,"losses":49,"wins":248},"GB2-05":{"draws":0,"losses":39,"wins":445},"GB2-06":{"draws":37,"losses":75,"wins":344},"GB2-07":{"draws":0,"losses":23,"wins":447},"GB2-08":{"draws":2,"losses":93,"wins":357}}},"per_game_raw_elo_all":{"GB2-01":1672.4099729388781,"GB2-02":1807.696191511404,"GB2-03":2200.231707289717,"GB2-04":1879.5090788105688,"GB2-05":2433.2252920003907,"GB2-06":2094.5193007200373,"GB2-07":2390.8272690141584,"GB2-08":1975.9394216212459},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1771.616976838709,"GB2-02":2084.545334577143,"GB2-03":2418.6176613195544,"GB2-04":2085.2086900684208,"GB2-05":2598.520165099116,"GB2-06":2151.7213263987123,"GB2-07":2412.336473660663,"GB2-08":2244.0103547152503},"medium":{"GB2-01":1756.3516512660212,"GB2-02":1745.1153403736243,"GB2-03":2308.557879933344,"GB2-04":1872.0627159328037,"GB2-05":2428.8064958695804,"GB2-06":2182.449786796272,"GB2-07":2412.336473660663,"GB2-08":1826.3231968320138},"none":{"GB2-01":1489.2612907119046,"GB2-02":1593.427899583445,"GB2-03":1873.5195806162528,"GB2-04":1681.255830430482,"GB2-05":2272.349215032477,"GB2-06":1949.3867889651285,"GB2-07":2347.8088597211495,"GB2-08":1857.4847133164737}},"per_game_tracks":{"highest":{"GB2-01":60.345911920664896,"GB2-02":90.68272636600271,"GB2-03":99.99999999999999,"GB2-04":100.0,"GB2-05":94.85227188248896,"GB2-06":79.08258821813236,"GB2-07":92.66060584281914,"GB2-08":80.84464979689227},"medium":{"GB2-01":59.33810182208111,"GB2-02":48.034867889766765,"GB2-03":91.6580330026905,"GB2-04":71.4019011908006,"GB2-05":87.27914149696393,"GB2-06":80.46283451538275,"GB2-07":92.66060584281914,"GB2-08":54.02214732325523},"none":{"GB2-01":41.70491337031128,"GB2-02":28.976020357385288,"GB2-03":58.68436096954297,"GB2-04":45.8010697080578,"GB2-05":80.29755072161178,"GB2-06":69.99422217292837,"GB2-07":89.49667017877252,"GB2-08":56.02323794146467}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":87.30859425337505,"medium":73.10720413547,"none":58.872255677509344},"reasoning_agg":{"highest":{"max":100.0,"mean":87.30859425337505,"min":60.345911920664896},"medium":{"max":92.66060584281914,"mean":73.10720413547,"min":48.034867889766765},"none":{"max":89.49667017877252,"mean":58.872255677509344,"min":28.976020357385288}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":78.41537006379474,"reasoning_variance":28.436338575865705,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.319352041676609},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":86.23863587064491,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0699583827301353},"medium":{"ceiling_score":92.66060584281914,"expected_score":79.03515350481685,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.927949369346848},"none":{"ceiling_score":89.49667017877252,"expected_score":69.97232081592243,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":11.100065138413086}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:092cc29c5fe928e5","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":7.1388750000000005},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.138875},"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":58.472324734322555,"highest":71.90458789600687,"medium":55.77248331223557,"none":51.759490448451956},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":2},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":2},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"first_pass_admitted":13,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":3}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-13T14:01:56Z","match_totals_all":{"draws":3114,"losses":3930,"wins":16362},"match_totals_tracks":{"highest":{"draws":410,"losses":904,"wins":5839},"medium":{"draws":1095,"losses":1377,"wins":5572},"none":{"draws":1609,"losses":1649,"wins":4951}},"model_slug":"claude-opus-5","overall":{"max":93.30423979477159,"mean":59.812187218898124,"min":12.514634169877416},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.09031168831543,"GB2-02":54.658305150666834,"GB2-03":84.14680916385734,"GB2-04":62.39427072449399,"GB2-05":86.83777962792956,"GB2-07":93.30423979477159,"GB2-08":63.900399122013326},"per_game_all":{"GB2-01":58.924355709773614,"GB2-02":43.28075461756212,"GB2-03":57.7602312573091,"GB2-04":30.83687194636987,"GB2-05":79.91742003177751,"GB2-07":77.16780011358469,"GB2-08":61.41883946388101},"per_game_match_totals_all":{"GB2-01":{"draws":565,"losses":713,"wins":2125},"GB2-02":{"draws":1103,"losses":277,"wins":1813},"GB2-03":{"draws":191,"losses":646,"wins":2296},"GB2-04":{"draws":1137,"losses":874,"wins":1434},"GB2-05":{"draws":0,"losses":350,"wins":3172},"GB2-06":{"draws":30,"losses":40,"wins":512},"GB2-07":{"draws":0,"losses":346,"wins":2036},"GB2-08":{"draws":88,"losses":684,"wins":2974}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":16,"losses":338,"wins":732},"GB2-02":{"draws":220,"losses":84,"wins":730},"GB2-03":{"draws":10,"losses":50,"wins":948},"GB2-04":{"draws":164,"losses":127,"wins":843},"GB2-05":{"draws":0,"losses":82,"wins":1056},"GB2-07":{"draws":0,"losses":19,"wins":561},"GB2-08":{"draws":0,"losses":204,"wins":969}},"medium":{"GB2-01":{"draws":115,"losses":287,"wins":748},"GB2-02":{"draws":440,"losses":97,"wins":524},"GB2-03":{"draws":19,"losses":146,"wins":892},"GB2-04":{"draws":519,"losses":390,"wins":257},"GB2-05":{"draws":0,"losses":138,"wins":1054},"GB2-07":{"draws":0,"losses":184,"wins":1018},"GB2-08":{"draws":2,"losses":135,"wins":1079}},"none":{"GB2-01":{"draws":434,"losses":88,"wins":645},"GB2-02":{"draws":443,"losses":96,"wins":559},"GB2-03":{"draws":162,"losses":450,"wins":456},"GB2-04":{"draws":454,"losses":357,"wins":334},"GB2-05":{"draws":0,"losses":130,"wins":1062},"GB2-06":{"draws":30,"losses":40,"wins":512},"GB2-07":{"draws":0,"losses":143,"wins":457},"GB2-08":{"draws":86,"losses":345,"wins":926}}},"per_game_raw_elo_all":{"GB2-01":1750.0846282249906,"GB2-02":1707.2778334487111,"GB2-03":1861.3270708480213,"GB2-04":1569.7253916291804,"GB2-05":2263.830495444361,"GB2-07":2096.3648822354103,"GB2-08":1941.50645838607},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1737.4513419070581,"GB2-02":1797.830607948605,"GB2-03":2209.4585123727315,"GB2-04":1804.9274779156185,"GB2-05":2418.9155870328595,"GB2-07":2425.4632143974936,"GB2-08":1980.14996682611},"medium":{"GB2-01":1721.9432050787411,"GB2-02":1658.6035872258599,"GB2-03":1908.2235164249378,"GB2-04":1433.1669705512509,"GB2-05":2183.540643204158,"GB2-07":2032.5828417570774,"GB2-08":2105.833961275224},"none":{"GB2-01":1790.8593376891736,"GB2-02":1665.3993051716689,"GB2-03":1466.2991837463944,"GB2-04":1471.0817264206719,"GB2-05":2189.0352560960655,"GB2-06":2169.8437509979585,"GB2-07":1831.048590551659,"GB2-08":1738.535447056876}},"per_game_tracks":{"highest":{"GB2-01":58.09031168831543,"GB2-02":54.658305150666834,"GB2-03":84.14680916385734,"GB2-04":62.39427072449399,"GB2-05":86.83777962792956,"GB2-07":93.30423979477159,"GB2-08":63.900399122013326},"medium":{"GB2-01":57.066471297137625,"GB2-02":37.16505358995944,"GB2-03":61.31474132780406,"GB2-04":12.514634169877416,"GB2-05":76.33464722149067,"GB2-07":74.04042161196793,"GB2-08":71.9714139674119},"none":{"GB2-01":61.616284143867794,"GB2-02":38.01890511206009,"GB2-03":27.819143280265912,"GB2-04":17.601710944738215,"GB2-05":76.57983324591233,"GB2-06":79.89660262453899,"GB2-07":64.15873893401455,"GB2-08":48.38470530221778}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":71.90458789600687,"medium":55.77248331223557,"none":51.759490448451956},"reasoning_agg":{"highest":{"max":93.30423979477159,"mean":71.90458789600687,"min":54.658305150666834},"medium":{"max":76.33464722149067,"mean":55.77248331223557,"min":12.514634169877416},"none":{"max":79.89660262453899,"mean":51.759490448451956,"min":17.601710944738215}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":93.30423979477159,"expected_score":61.72977871314595,"reasoning_variance":20.145097447554917,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.917591494247823},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":93.30423979477159,"expected_score":70.27917017459644,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6254177214104288},"medium":{"ceiling_score":76.33464722149067,"expected_score":58.555617556847594,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.7831342446120217},"none":{"ceiling_score":79.89660262453899,"expected_score":61.81022985699457,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":10.050739408542611}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:bcc368392551468c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.34556800000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.34556800000000004},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425000000005},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":57.61096975393522,"highest":68.45057867991243,"medium":58.00768710126683,"none":46.374643480626375},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:14:58Z","match_totals_all":{"draws":1465,"losses":2117,"wins":7343},"match_totals_tracks":{"highest":{"draws":222,"losses":600,"wins":2820},"medium":{"draws":596,"losses":593,"wins":2454},"none":{"draws":647,"losses":924,"wins":2069}},"model_slug":"gpt-6-sol","overall":{"max":89.99707539642073,"mean":57.610969753935215,"min":8.542593071746985},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":8.542593071746985,"GB2-02":56.94501266663782,"GB2-03":79.70780005877654,"GB2-04":73.88743343226373,"GB2-05":84.72229219103296,"GB2-06":80.20432037616327,"GB2-07":89.99707539642073,"GB2-08":73.5981022462574},"per_game_all":{"GB2-01":30.80759240396687,"GB2-02":35.77386507866684,"GB2-03":59.328058660280256,"GB2-04":43.89896459974002,"GB2-05":76.0198620752172,"GB2-06":72.25706905295849,"GB2-07":76.41959358158827,"GB2-08":66.38275257906375},"per_game_match_totals_all":{"GB2-01":{"draws":196,"losses":790,"wins":412},"GB2-02":{"draws":569,"losses":133,"wins":576},"GB2-03":{"draws":72,"losses":202,"wins":1044},"GB2-04":{"draws":474,"losses":200,"wins":669},"GB2-05":{"draws":0,"losses":173,"wins":1279},"GB2-06":{"draws":131,"losses":186,"wins":1051},"GB2-07":{"draws":0,"losses":255,"wins":1155},"GB2-08":{"draws":23,"losses":178,"wins":1157}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":408,"wins":29},"GB2-02":{"draws":110,"losses":16,"wins":300},"GB2-03":{"draws":4,"losses":25,"wins":411},"GB2-04":{"draws":49,"losses":31,"wins":368},"GB2-05":{"draws":0,"losses":27,"wins":457},"GB2-06":{"draws":28,"losses":30,"wins":398},"GB2-07":{"draws":0,"losses":22,"wins":448},"GB2-08":{"draws":2,"losses":41,"wins":409}},"medium":{"GB2-01":{"draws":154,"losses":210,"wins":102},"GB2-02":{"draws":196,"losses":39,"wins":191},"GB2-03":{"draws":37,"losses":104,"wins":299},"GB2-04":{"draws":145,"losses":52,"wins":250},"GB2-05":{"draws":0,"losses":39,"wins":445},"GB2-06":{"draws":53,"losses":60,"wins":343},"GB2-07":{"draws":0,"losses":24,"wins":446},"GB2-08":{"draws":11,"losses":65,"wins":378}},"none":{"GB2-01":{"draws":13,"losses":172,"wins":281},"GB2-02":{"draws":263,"losses":78,"wins":85},"GB2-03":{"draws":31,"losses":73,"wins":334},"GB2-04":{"draws":280,"losses":117,"wins":51},"GB2-05":{"draws":0,"losses":107,"wins":377},"GB2-06":{"draws":50,"losses":96,"wins":310},"GB2-07":{"draws":0,"losses":209,"wins":261},"GB2-08":{"draws":10,"losses":72,"wins":370}}},"per_game_raw_elo_all":{"GB2-01":1324.1992887979666,"GB2-02":1647.531258504192,"GB2-03":1882.0122091706698,"GB2-04":1667.0791521510746,"GB2-05":2176.486315670707,"GB2-06":1999.7646098491734,"GB2-07":2081.1054119521436,"GB2-08":2018.8058365144843},"per_game_raw_elo_tracks":{"highest":{"GB2-01":986.9507693004671,"GB2-02":1816.0302818976186,"GB2-03":2150.892424562247,"GB2-04":1890.5877652511774,"GB2-05":2371.5075646104624,"GB2-06":2176.6944795695545,"GB2-07":2358.0144890784873,"GB2-08":2131.1651847365974},"medium":{"GB2-01":1379.2271787200839,"GB2-02":1634.832145799745,"GB2-03":1693.1212217248308,"GB2-04":1680.851295898175,"GB2-05":2272.349215032477,"GB2-06":1977.4224311464884,"GB2-07":2337.797511671929,"GB2-08":1983.693762156185},"none":{"GB2-01":1606.4199183733483,"GB2-02":1491.7313478152125,"GB2-03":1802.0229812249315,"GB2-04":1429.7983953038713,"GB2-05":1885.602167369181,"GB2-06":1845.1769188314775,"GB2-07":1547.5042351060142,"GB2-08":1941.5585626506706}},"per_game_tracks":{"highest":{"GB2-01":8.542593071746985,"GB2-02":56.94501266663782,"GB2-03":79.70780005877654,"GB2-04":73.88743343226373,"GB2-05":84.72229219103296,"GB2-06":80.20432037616327,"GB2-07":89.99707539642073,"GB2-08":73.5981022462574},"medium":{"GB2-01":34.44050956011913,"GB2-02":34.17827844624832,"GB2-03":45.011090522455,"GB2-04":45.74679273391571,"GB2-05":80.29755072161178,"GB2-06":71.25351374859521,"GB2-07":89.00579101550755,"GB2-08":64.12797006168195},"none":{"GB2-01":49.4396745800345,"GB2-02":16.19830412311438,"GB2-03":53.26528539960925,"GB2-04":12.062667633040617,"GB2-05":63.03974331300685,"GB2-06":65.31337303411698,"GB2-07":50.25591433283656,"GB2-08":61.4221854292519}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":68.45057867991243,"medium":58.00768710126683,"none":46.374643480626375},"reasoning_agg":{"highest":{"max":89.99707539642073,"mean":68.45057867991243,"min":8.542593071746985},"medium":{"max":89.00579101550755,"mean":58.00768710126683,"min":34.17827844624832},"none":{"max":65.31337303411698,"mean":46.374643480626375,"min":12.062667633040617}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":89.99707539642073,"expected_score":60.50603609682416,"reasoning_variance":22.07593519928605,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.8950663428889456},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.99707539642073,"expected_score":65.84602084692365,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.6045578329887746},"medium":{"ceiling_score":89.00579101550755,"expected_score":61.486557170356505,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4788700690896732},"none":{"ceiling_score":65.31337303411698,"expected_score":54.185530273192335,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.8108867925659595}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:e41547632cf0ace6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"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":0.663736},"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":6.235559999999999}},"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":10.08905},"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":57.449252361355875,"highest":68.44486402449147,"medium":67.17099042103665,"none":39.26548307222124},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:36:35Z","match_totals_all":{"draws":932,"losses":2060,"wins":6592},"match_totals_tracks":{"highest":{"draws":137,"losses":460,"wins":2597},"medium":{"draws":184,"losses":436,"wins":2568},"none":{"draws":611,"losses":1164,"wins":1427}},"model_slug":"x-ai-grok-4-7","overall":{"max":89.49809492680822,"mean":56.37989006428423,"min":10.999663869241507},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":47.434600860018534,"GB2-02":67.91062290037567,"GB2-03":65.51688062045237,"GB2-05":82.41583244948515,"GB2-06":80.46283451538275,"GB2-07":65.82587414942766,"GB2-08":69.54740267629805},"per_game_all":{"GB2-01":45.74106121805232,"GB2-02":45.32975099816415,"GB2-05":68.83123442779953,"GB2-07":59.570005493583984,"GB2-08":67.7742096691794},"per_game_match_totals_all":{"GB2-01":{"draws":188,"losses":535,"wins":675},"GB2-02":{"draws":438,"losses":123,"wins":717},"GB2-03":{"draws":92,"losses":139,"wins":649},"GB2-04":{"draws":151,"losses":219,"wins":526},"GB2-05":{"draws":0,"losses":340,"wins":1112},"GB2-06":{"draws":63,"losses":89,"wins":760},"GB2-07":{"draws":0,"losses":435,"wins":975},"GB2-08":{"draws":0,"losses":180,"wins":1178}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":186,"wins":267},"GB2-02":{"draws":46,"losses":27,"wins":353},"GB2-03":{"draws":66,"losses":20,"wins":354},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":12,"losses":37,"wins":407},"GB2-07":{"draws":0,"losses":103,"wins":367},"GB2-08":{"draws":0,"losses":54,"wins":398}},"medium":{"GB2-01":{"draws":29,"losses":80,"wins":357},"GB2-02":{"draws":95,"losses":36,"wins":295},"GB2-03":{"draws":26,"losses":119,"wins":295},"GB2-04":{"draws":34,"losses":16,"wins":398},"GB2-05":{"draws":0,"losses":30,"wins":454},"GB2-07":{"draws":0,"losses":116,"wins":354},"GB2-08":{"draws":0,"losses":39,"wins":415}},"none":{"GB2-01":{"draws":146,"losses":269,"wins":51},"GB2-02":{"draws":297,"losses":60,"wins":69},"GB2-04":{"draws":117,"losses":203,"wins":128},"GB2-05":{"draws":0,"losses":277,"wins":207},"GB2-06":{"draws":51,"losses":52,"wins":353},"GB2-07":{"draws":0,"losses":216,"wins":254},"GB2-08":{"draws":0,"losses":87,"wins":365}}},"per_game_raw_elo_all":{"GB2-01":1550.3969263260453,"GB2-02":1723.5855885023047,"GB2-05":2015.3893435256066,"GB2-07":1737.4626105078253,"GB2-08":2040.4739772056118},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1576.0490149895704,"GB2-02":1903.304465199218,"GB2-03":1963.6644612347702,"GB2-05":2319.819857448248,"GB2-06":2182.449786796272,"GB2-07":1865.0493633194455,"GB2-08":2068.0866113455386},"medium":{"GB2-01":1820.554281111196,"GB2-02":1773.8828530084422,"GB2-03":1666.8761836995036,"GB2-04":2006.9363964436018,"GB2-05":2345.0628790926244,"GB2-07":1817.9623864297955,"GB2-08":2159.09298992787},"none":{"GB2-01":1254.58748287737,"GB2-02":1493.569447299254,"GB2-04":1421.8756667946634,"GB2-05":1381.2852940359473,"GB2-06":2014.7739637256057,"GB2-07":1529.376081774235,"GB2-08":1894.2423303434268}},"per_game_tracks":{"highest":{"GB2-01":47.434600860018534,"GB2-02":67.91062290037567,"GB2-03":65.51688062045237,"GB2-05":82.41583244948515,"GB2-06":80.46283451538275,"GB2-07":65.82587414942766,"GB2-08":69.54740267629805},"medium":{"GB2-01":63.576731283700354,"GB2-02":51.649377003617865,"GB2-03":43.021851235470166,"GB2-04":89.49809492680822,"GB2-05":83.54225140622185,"GB2-07":63.51709258448475,"GB2-08":75.39153450695326},"none":{"GB2-01":26.211851510438073,"GB2-02":16.42925309049893,"GB2-04":10.999663869241507,"GB2-05":40.53561942769158,"GB2-06":72.93125203655215,"GB2-07":49.36704974683954,"GB2-08":58.38369182428687}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.19769663142111,"medium":64.96564657843098,"none":37.9763269830006},"reasoning_agg":{"highest":{"max":82.41583244948515,"mean":66.19769663142111,"min":47.434600860018534},"medium":{"max":89.49809492680822,"mean":64.96564657843098,"min":43.021851235470166},"none":{"max":72.93125203655215,"mean":37.9763269830006,"min":10.999663869241507}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":89.49809492680822,"expected_score":58.69634529063499,"reasoning_variance":28.221369648420513,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3164552263507545},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.41583244948515,"expected_score":64.87188340166475,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.3258132297563634},"medium":{"ceiling_score":89.49809492680822,"expected_score":71.11597863546196,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.15033205703098},"none":{"ceiling_score":72.93125203655215,"expected_score":44.47740453399904,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.5010775509984455}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:21b3ef9c75b3fd07","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.0229249999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.372553750000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983750000002},"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":49.43235850289583,"highest":62.15494917704579,"medium":47.56308792815524,"none":38.57903840348645},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:27:49Z","match_totals_all":{"draws":2542,"losses":4386,"wins":9954},"match_totals_tracks":{"highest":{"draws":399,"losses":884,"wins":4149},"medium":{"draws":816,"losses":1538,"wins":3148},"none":{"draws":1327,"losses":1964,"wins":2657}},"model_slug":"gpt-5-6-sol","overall":{"max":78.51237794270706,"mean":49.43235850289583,"min":9.626089642902215},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.28280891967357,"GB2-02":44.194097869665114,"GB2-03":55.46231810900392,"GB2-04":66.15673865224207,"GB2-05":60.313052233583,"GB2-06":75.77394805923406,"GB2-07":78.51237794270706,"GB2-08":57.54425163025755},"per_game_all":{"GB2-01":58.47414632489881,"GB2-02":28.350977698525355,"GB2-03":39.74778221971797,"GB2-04":43.50952206627168,"GB2-05":56.382370522258384,"GB2-06":57.480462086461976,"GB2-07":61.33820176182471,"GB2-08":50.17540534320771},"per_game_match_totals_all":{"GB2-01":{"draws":171,"losses":527,"wins":1376},"GB2-02":{"draws":1047,"losses":218,"wins":657},"GB2-03":{"draws":334,"losses":604,"wins":1169},"GB2-04":{"draws":741,"losses":322,"wins":998},"GB2-05":{"draws":0,"losses":718,"wins":1524},"GB2-06":{"draws":67,"losses":788,"wins":1318},"GB2-07":{"draws":0,"losses":701,"wins":1504},"GB2-08":{"draws":182,"losses":508,"wins":1408}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":184,"wins":483},"GB2-02":{"draws":220,"losses":41,"wins":361},"GB2-03":{"draws":12,"losses":118,"wins":542},"GB2-04":{"draws":103,"losses":54,"wins":503},"GB2-05":{"draws":0,"losses":186,"wins":534},"GB2-06":{"draws":43,"losses":81,"wins":562},"GB2-07":{"draws":0,"losses":73,"wins":623},"GB2-08":{"draws":0,"losses":147,"wins":541}},"medium":{"GB2-01":{"draws":148,"losses":179,"wins":367},"GB2-02":{"draws":306,"losses":72,"wins":248},"GB2-03":{"draws":75,"losses":235,"wins":365},"GB2-04":{"draws":162,"losses":66,"wins":431},"GB2-05":{"draws":0,"losses":170,"wins":552},"GB2-06":{"draws":11,"losses":403,"wins":286},"GB2-07":{"draws":0,"losses":210,"wins":516},"GB2-08":{"draws":114,"losses":203,"wins":383}},"none":{"GB2-01":{"draws":2,"losses":164,"wins":526},"GB2-02":{"draws":521,"losses":105,"wins":48},"GB2-03":{"draws":247,"losses":251,"wins":262},"GB2-04":{"draws":476,"losses":202,"wins":64},"GB2-05":{"draws":0,"losses":362,"wins":438},"GB2-06":{"draws":13,"losses":304,"wins":470},"GB2-07":{"draws":0,"losses":418,"wins":365},"GB2-08":{"draws":68,"losses":158,"wins":484}}},"per_game_raw_elo_all":{"GB2-01":1743.2652950533438,"GB2-02":1588.4532482491468,"GB2-03":1623.6797385165783,"GB2-04":1664.1765777974517,"GB2-05":1736.4106037449312,"GB2-06":1670.7926119638444,"GB2-07":1773.5244961722128,"GB2-08":1766.4207053946327},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1755.5141282462619,"GB2-02":1714.5470400593993,"GB2-03":1831.0095427603967,"GB2-04":1832.9697228551984,"GB2-05":1824.4970860637063,"GB2-06":2078.0609816508086,"GB2-07":2123.7871841662495,"GB2-08":1881.1703438946727},"medium":{"GB2-01":1666.2015489161936,"GB2-02":1603.5554554912196,"GB2-03":1574.268220925764,"GB2-04":1747.9218010809684,"GB2-05":1864.8453233124276,"GB2-06":1302.33560762913,"GB2-07":1763.2599741028394,"GB2-08":1642.8902319327533},"none":{"GB2-01":1808.080207997576,"GB2-02":1447.2572491968208,"GB2-03":1465.761451863574,"GB2-04":1411.6382094561886,"GB2-05":1519.88940185866,"GB2-06":1631.981246611594,"GB2-07":1433.5263302475494,"GB2-08":1775.2015403564715}},"per_game_tracks":{"highest":{"GB2-01":59.28280891967357,"GB2-02":44.194097869665114,"GB2-03":55.46231810900392,"GB2-04":66.15673865224207,"GB2-05":60.313052233583,"GB2-06":75.77394805923406,"GB2-07":78.51237794270706,"GB2-08":57.54425163025755},"medium":{"GB2-01":53.386431606866566,"GB2-02":30.24850239621762,"GB2-03":36.0026425888919,"GB2-04":54.74573790367075,"GB2-05":62.11351098801245,"GB2-06":40.93028647241292,"GB2-07":60.83490890056804,"GB2-08":42.242682568601694},"none":{"GB2-01":62.753198448156304,"GB2-02":10.610332829693341,"GB2-03":27.778385961258085,"GB2-04":9.626089642902215,"GB2-05":46.72054834517972,"GB2-06":55.73715172773896,"GB2-07":44.66731844219906,"GB2-08":50.7392818307639}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":62.15494917704579,"medium":47.56308792815524,"none":38.57903840348645},"reasoning_agg":{"highest":{"max":78.51237794270706,"mean":62.15494917704579,"min":44.194097869665114},"medium":{"max":62.11351098801245,"mean":47.56308792815524,"min":30.24850239621762},"none":{"max":62.753198448156304,"mean":38.57903840348645,"min":9.626089642902215}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":78.51237794270706,"expected_score":50.0565572132432,"reasoning_variance":23.575910773559343,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6241987103473718},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.51237794270706,"expected_score":57.99262604306404,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.162323133981751},"medium":{"ceiling_score":62.11351098801245,"expected_score":47.68133296230303,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.1182450341477903},"none":{"ceiling_score":62.753198448156304,"expected_score":44.49571263436251,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.916674230876062}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:6c8ebe2f37004c96","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.397416199999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181687999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.397416199999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.2535328433333333,"median":0.1720692,"min":0.0217974,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":28,"run_count":24,"total":6.084788240000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":4051923,"mean_ms":1012660.4583333334,"min_ms":28293,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":4051923,"mean_ms":2278758.375,"min_ms":1011583,"run_count":8},"medium":{"attempt_count":10,"max_ms":1900345,"mean_ms":621701.25,"min_ms":106081,"run_count":8},"none":{"attempt_count":8,"max_ms":420991,"mean_ms":137521.75,"min_ms":28293,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":206676,"output_mean":54914.25,"output_min":2671,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":206676,"output_mean":121740.75,"output_min":61533,"run_count":8},"medium":{"attempt_count":10,"output_max":49662,"output_mean":33008.75,"output_min":15862,"run_count":8},"none":{"attempt_count":8,"output_max":33431,"output_mean":9993.25,"output_min":2671,"run_count":8}},"display_name":"GLM-5.3","economics":{"all":49.61064011668037,"highest":64.21033223530152,"medium":52.693618707056885,"none":33.42264320778039},"first_seen_at":"2026-10-13T14:22:27Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":29,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":84,"requested_max_output_token_observations":10,"requested_max_output_tokens":[131072],"total_output_tokens":1317942,"total_reasoning_output_tokens":1189870,"total_visible_output_tokens":128072,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":8,"failed_game_aliases":["GB2-01"],"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":"z-ai/glm-5.3","is_recent_addition":true,"last_measured_at":"2026-10-13T14:22:27Z","match_totals_all":{"draws":2710,"losses":3260,"wins":7039},"match_totals_tracks":{"highest":{"draws":334,"losses":340,"wins":2254},"medium":{"draws":834,"losses":1108,"wins":3018},"none":{"draws":1542,"losses":1812,"wins":1767}},"model_slug":"z-ai-glm-5-3","overall":{"max":84.70673291786173,"mean":49.40615133831758,"min":8.31831074909881},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-02":40.01573878375013,"GB2-03":56.72958409727195,"GB2-04":50.73922315014517,"GB2-05":77.0795980138722,"GB2-06":80.72503598285799,"GB2-07":66.19997337389759,"GB2-08":77.98317224531561},"per_game_all":{"GB2-02":22.431252412375756,"GB2-03":42.60251432148029,"GB2-04":43.57752038005779,"GB2-05":60.299619682685126,"GB2-06":71.24785021993928,"GB2-07":63.29546133763497,"GB2-08":43.82026246258945},"per_game_match_totals_all":{"GB2-01":{"draws":232,"losses":441,"wins":641},"GB2-02":{"draws":1092,"losses":192,"wins":330},"GB2-03":{"draws":247,"losses":495,"wins":956},"GB2-04":{"draws":623,"losses":215,"wins":815},"GB2-05":{"draws":0,"losses":566,"wins":1244},"GB2-06":{"draws":74,"losses":407,"wins":1283},"GB2-07":{"draws":0,"losses":470,"wins":1250},"GB2-08":{"draws":442,"losses":474,"wins":520}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":188,"losses":23,"wins":215},"GB2-03":{"draws":4,"losses":75,"wins":361},"GB2-04":{"draws":122,"losses":48,"wins":276},"GB2-05":{"draws":0,"losses":49,"wins":435},"GB2-06":{"draws":20,"losses":32,"wins":404},"GB2-07":{"draws":0,"losses":101,"wins":369},"GB2-08":{"draws":0,"losses":12,"wins":194}},"medium":{"GB2-01":{"draws":122,"losses":273,"wins":293},"GB2-02":{"draws":397,"losses":68,"wins":101},"GB2-03":{"draws":43,"losses":128,"wins":426},"GB2-04":{"draws":102,"losses":52,"wins":449},"GB2-05":{"draws":0,"losses":231,"wins":409},"GB2-06":{"draws":33,"losses":27,"wins":558},"GB2-07":{"draws":0,"losses":164,"wins":460},"GB2-08":{"draws":137,"losses":165,"wins":322}},"none":{"GB2-01":{"draws":110,"losses":168,"wins":348},"GB2-02":{"draws":507,"losses":101,"wins":14},"GB2-03":{"draws":200,"losses":292,"wins":169},"GB2-04":{"draws":399,"losses":115,"wins":90},"GB2-05":{"draws":0,"losses":286,"wins":400},"GB2-06":{"draws":21,"losses":348,"wins":321},"GB2-07":{"draws":0,"losses":205,"wins":421},"GB2-08":{"draws":305,"losses":297,"wins":4}}},"per_game_raw_elo_all":{"GB2-02":1541.3387531407036,"GB2-03":1661.3436601237354,"GB2-04":1664.683379558234,"GB2-05":1824.19606292216,"GB2-06":1977.2963438558645,"GB2-07":1813.4422769673408,"GB2-08":1667.456726535601},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1681.2919024983275,"GB2-03":1847.7292226239042,"GB2-04":1718.060638081062,"GB2-05":2200.234972488673,"GB2-06":2188.2871851110112,"GB2-07":1872.6790160352002,"GB2-08":2199.450663573849},"medium":{"GB2-01":1514.3245006569782,"GB2-02":1513.7090797585488,"GB2-03":1752.557320452602,"GB2-04":1821.1700952007577,"GB2-05":1689.7864800908637,"GB2-06":2276.93181094778,"GB2-07":1827.2115531965828,"GB2-08":1641.6161076905328},"none":{"GB2-01":1663.6715625690645,"GB2-02":1429.0152771652347,"GB2-03":1383.7444372947002,"GB2-04":1454.819405392882,"GB2-05":1582.5667361869434,"GB2-06":1466.6700355088021,"GB2-07":1740.4362616702388,"GB2-08":1161.3034083424222}},"per_game_tracks":{"highest":{"GB2-02":40.01573878375013,"GB2-03":56.72958409727195,"GB2-04":50.73922315014517,"GB2-05":77.0795980138722,"GB2-06":80.72503598285799,"GB2-07":66.19997337389759,"GB2-08":77.98317224531561},"medium":{"GB2-01":43.35957549758117,"GB2-02":18.95970770427833,"GB2-03":49.5160419932928,"GB2-04":64.5735658105221,"GB2-05":54.30186298773833,"GB2-06":84.70673291786173,"GB2-07":63.970600266073355,"GB2-08":42.160862479107266},"none":{"GB2-01":53.21940301793966,"GB2-02":8.31831074909881,"GB2-03":21.561916873876108,"GB2-04":15.419772179506124,"GB2-05":49.51739804644484,"GB2-06":48.311781759098146,"GB2-07":59.71581037293397,"GB2-08":11.316752663345468}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":62.10219210011544,"medium":52.693618707056885,"none":33.42264320778039},"reasoning_agg":{"highest":{"max":80.72503598285799,"mean":62.10219210011544,"min":40.01573878375013},"medium":{"max":84.70673291786173,"mean":52.693618707056885,"min":18.95970770427833},"none":{"max":59.71581037293397,"mean":33.42264320778039,"min":8.31831074909881}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":84.70673291786173,"expected_score":51.05633990257966,"reasoning_variance":28.67954889233505,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.6501885642620806},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.72503598285799,"expected_score":59.73053950107141,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.371652599044026},"medium":{"ceiling_score":84.70673291786173,"expected_score":56.33953202569042,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.645913318633532},"none":{"ceiling_score":59.71581037293397,"expected_score":37.710513141826006,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.287869934045617}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:a3e3cdfd27bf0fcd","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":0.48637800000000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.32749799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.48637800000000003},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.32749799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199237999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":48.79011962289338,"highest":83.52002316726487,"medium":35.75418583891918,"none":27.096149862496077},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:24:39Z","match_totals_all":{"draws":1929,"losses":3335,"wins":5672},"match_totals_tracks":{"highest":{"draws":283,"losses":163,"wins":3196},"medium":{"draws":851,"losses":1358,"wins":1437},"none":{"draws":795,"losses":1814,"wins":1039}},"model_slug":"claude-sonnet-5-5","overall":{"max":100.0,"mean":48.79011962289337,"min":6.770777225919291},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":62.761283410167195,"GB2-02":99.24815400679277,"GB2-03":84.67754718079702,"GB2-04":64.05348388137868,"GB2-05":91.8046959845615,"GB2-06":78.48569415368743,"GB2-07":87.12932672073447,"GB2-08":100.0},"per_game_all":{"GB2-01":48.271103556765844,"GB2-02":38.749259984477895,"GB2-03":41.053969873741174,"GB2-04":29.074695701299948,"GB2-05":45.852891961428156,"GB2-06":57.73075911082238,"GB2-07":63.915282347937215,"GB2-08":65.67299444667442},"per_game_match_totals_all":{"GB2-01":{"draws":195,"losses":479,"wins":724},"GB2-02":{"draws":678,"losses":163,"wins":437},"GB2-03":{"draws":300,"losses":422,"wins":598},"GB2-04":{"draws":622,"losses":282,"wins":440},"GB2-05":{"draws":0,"losses":820,"wins":632},"GB2-06":{"draws":62,"losses":505,"wins":801},"GB2-07":{"draws":0,"losses":421,"wins":989},"GB2-08":{"draws":72,"losses":243,"wins":1051}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":141,"losses":28,"wins":297},"GB2-02":{"draws":18,"losses":7,"wins":401},"GB2-03":{"draws":1,"losses":20,"wins":419},"GB2-04":{"draws":76,"losses":37,"wins":335},"GB2-05":{"draws":0,"losses":12,"wins":472},"GB2-06":{"draws":40,"losses":31,"wins":385},"GB2-07":{"draws":0,"losses":28,"wins":442},"GB2-08":{"draws":7,"losses":0,"wins":445}},"medium":{"GB2-01":{"draws":11,"losses":243,"wins":212},"GB2-02":{"draws":333,"losses":84,"wins":9},"GB2-03":{"draws":194,"losses":217,"wins":29},"GB2-04":{"draws":289,"losses":122,"wins":37},"GB2-05":{"draws":0,"losses":391,"wins":93},"GB2-06":{"draws":16,"losses":95,"wins":345},"GB2-07":{"draws":0,"losses":133,"wins":337},"GB2-08":{"draws":8,"losses":73,"wins":375}},"none":{"GB2-01":{"draws":43,"losses":208,"wins":215},"GB2-02":{"draws":327,"losses":72,"wins":27},"GB2-03":{"draws":105,"losses":185,"wins":150},"GB2-04":{"draws":257,"losses":123,"wins":68},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":6,"losses":379,"wins":71},"GB2-07":{"draws":0,"losses":260,"wins":210},"GB2-08":{"draws":57,"losses":170,"wins":231}}},"per_game_raw_elo_all":{"GB2-01":1588.7195429255607,"GB2-02":1671.212125767325,"GB2-03":1640.9129315629577,"GB2-04":1556.5916244210869,"GB2-05":1500.4452432319495,"GB2-06":1676.3649813416916,"GB2-07":1826.0833591861958,"GB2-08":2007.7532936954995},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1808.2026711258106,"GB2-02":2152.71670726363,"GB2-03":2216.460806931865,"GB2-04":1817.2938455886,"GB2-05":2530.2240627526744,"GB2-06":2138.4326578057426,"GB2-07":2299.527528827355,"GB2-08":2542.3025738121823},"medium":{"GB2-01":1459.4172570625483,"GB2-02":1416.6986142993778,"GB2-03":1274.1453337328558,"GB2-04":1413.0337158807615,"GB2-05":1037.4465494113902,"GB2-06":1912.4590374884876,"GB2-07":1761.6093219121476,"GB2-08":1953.3266144354293},"none":{"GB2-01":1498.5387005883233,"GB2-02":1444.2210557389674,"GB2-03":1432.1326540241523,"GB2-04":1439.4473117938996,"GB2-05":933.6651175317841,"GB2-06":978.2032487308452,"GB2-07":1417.1132268190852,"GB2-08":1527.6306928388863}},"per_game_tracks":{"highest":{"GB2-01":62.761283410167195,"GB2-02":99.24815400679277,"GB2-03":84.67754718079702,"GB2-04":64.05348388137868,"GB2-05":91.8046959845615,"GB2-06":78.48569415368743,"GB2-07":87.12932672073447,"GB2-08":100.0},"medium":{"GB2-01":39.734623359064564,"GB2-02":6.770777225919291,"GB2-03":13.25486689310846,"GB2-04":9.813326726692573,"GB2-05":25.192508548890032,"GB2-06":68.33551908198326,"GB2-07":60.75397366964564,"GB2-08":62.1778912060496},"none":{"GB2-01":42.31740390106578,"GB2-02":10.228848720721619,"GB2-03":25.22949554731805,"GB2-04":13.35727649582858,"GB2-05":20.561471350832917,"GB2-06":26.37106409679643,"GB2-07":43.86254665343152,"GB2-08":34.8410921339737}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.52002316726487,"medium":35.75418583891918,"none":27.096149862496077},"reasoning_agg":{"highest":{"max":100.0,"mean":83.52002316726487,"min":62.761283410167195},"medium":{"max":68.33551908198326,"mean":35.75418583891918,"min":6.770777225919291},"none":{"max":43.86254665343152,"mean":27.096149862496077,"min":10.228848720721619}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":49.031715186353956,"reasoning_variance":56.42387330476879,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.24159556346058508},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":82.05189319264014,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4681299746247305},"medium":{"ceiling_score":68.33551908198326,"expected_score":36.1156514811766,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.3614656422574214},"none":{"ceiling_score":43.86254665343152,"expected_score":28.927600885245123,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8314510227490466}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:cd329d16ad5e23ab","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.3088499999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.260500000000004},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":48.49105403709949,"highest":56.79255116465113,"medium":47.35878851533555,"none":41.32182243131179},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:58:46Z","match_totals_all":{"draws":2811,"losses":3807,"wins":8181},"match_totals_tracks":{"highest":{"draws":680,"losses":1032,"wins":3181},"medium":{"draws":917,"losses":1315,"wins":2668},"none":{"draws":1214,"losses":1460,"wins":2332}},"model_slug":"claude-fable-5","overall":{"max":78.36217050861919,"mean":48.49105403709948,"min":5.262820504477954},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":71.75887510342196,"GB2-02":46.66116480305427,"GB2-03":56.73059372537796,"GB2-04":66.84875993461759,"GB2-05":47.47231447754674,"GB2-06":76.9171053737359,"GB2-07":56.785074243118295,"GB2-08":31.16652165633641},"per_game_all":{"GB2-01":62.41957066836821,"GB2-02":25.90766721935582,"GB2-03":26.0966601029632,"GB2-04":32.815900578620194,"GB2-05":52.95561995419157,"GB2-06":72.55131206388846,"GB2-07":56.91194976696278,"GB2-08":58.26975194244569},"per_game_match_totals_all":{"GB2-01":{"draws":133,"losses":394,"wins":1321},"GB2-02":{"draws":943,"losses":217,"wins":524},"GB2-03":{"draws":503,"losses":736,"wins":572},"GB2-04":{"draws":841,"losses":374,"wins":663},"GB2-05":{"draws":0,"losses":762,"wins":1220},"GB2-06":{"draws":95,"losses":314,"wins":1397},"GB2-07":{"draws":0,"losses":702,"wins":1240},"GB2-08":{"draws":296,"losses":308,"wins":1244}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":90,"wins":524},"GB2-02":{"draws":170,"losses":47,"wins":343},"GB2-03":{"draws":105,"losses":57,"wins":434},"GB2-04":{"draws":85,"losses":55,"wins":465},"GB2-05":{"draws":0,"losses":314,"wins":372},"GB2-06":{"draws":26,"losses":74,"wins":502},"GB2-07":{"draws":0,"losses":230,"wins":390},"GB2-08":{"draws":294,"losses":165,"wins":151}},"medium":{"GB2-01":{"draws":52,"losses":143,"wins":419},"GB2-02":{"draws":336,"losses":78,"wins":148},"GB2-03":{"draws":142,"losses":411,"wins":52},"GB2-04":{"draws":341,"losses":119,"wins":149},"GB2-05":{"draws":0,"losses":225,"wins":425},"GB2-06":{"draws":46,"losses":99,"wins":457},"GB2-07":{"draws":0,"losses":191,"wins":435},"GB2-08":{"draws":0,"losses":49,"wins":583}},"none":{"GB2-01":{"draws":81,"losses":161,"wins":378},"GB2-02":{"draws":437,"losses":92,"wins":33},"GB2-03":{"draws":256,"losses":268,"wins":86},"GB2-04":{"draws":415,"losses":200,"wins":49},"GB2-05":{"draws":0,"losses":223,"wins":423},"GB2-06":{"draws":23,"losses":141,"wins":438},"GB2-07":{"draws":0,"losses":281,"wins":415},"GB2-08":{"draws":2,"losses":94,"wins":510}}},"per_game_raw_elo_all":{"GB2-01":1803.0267394069008,"GB2-02":1569.0071871475313,"GB2-03":1443.5735937270974,"GB2-04":1584.4753926162246,"GB2-05":1659.6172061886712,"GB2-06":2006.3153499066782,"GB2-07":1683.2522813579087,"GB2-08":1892.468028133461},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1944.4894247122804,"GB2-02":1734.182176378532,"GB2-03":1847.7425431571387,"GB2-04":1838.1274625825351,"GB2-05":1536.736462747822,"GB2-06":2103.511123655774,"GB2-07":1680.664689292102,"GB2-08":1470.4093019282323},"medium":{"GB2-01":1758.9495077000624,"GB2-02":1543.7592455169402,"GB2-03":1168.702231567045,"GB2-04":1517.5490487430852,"GB2-05":1723.115978785838,"GB2-06":1998.5318416331506,"GB2-07":1770.1595526509952,"GB2-08":2205.352525549537},"none":{"GB2-01":1705.64128580836,"GB2-02":1429.0801395471226,"GB2-03":1314.2760064571085,"GB2-04":1397.7496665230526,"GB2-05":1718.999177032354,"GB2-06":1916.9030844311092,"GB2-07":1598.932602130629,"GB2-08":2001.6422569226133}},"per_game_tracks":{"highest":{"GB2-01":71.75887510342196,"GB2-02":46.66116480305427,"GB2-03":56.73059372537796,"GB2-04":66.84875993461759,"GB2-05":47.47231447754674,"GB2-06":76.9171053737359,"GB2-07":56.785074243118295,"GB2-08":31.16652165633641},"medium":{"GB2-01":59.50961116437656,"GB2-02":22.735376438146577,"GB2-03":5.262820504477954,"GB2-04":23.836297737026285,"GB2-05":55.7891246823744,"GB2-06":72.20169615944155,"GB2-07":61.17321092822189,"GB2-08":78.36217050861919},"none":{"GB2-01":55.990225737306105,"GB2-02":8.326460416866615,"GB2-03":16.296566079033678,"GB2-04":7.762644064216704,"GB2-05":55.60542070265357,"GB2-06":68.53513465848795,"GB2-07":52.77756412954815,"GB2-08":65.28056366238147}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.79255116465113,"medium":47.35878851533555,"none":41.32182243131179},"reasoning_agg":{"highest":{"max":76.9171053737359,"mean":56.79255116465113,"min":31.16652165633641},"medium":{"max":78.36217050861919,"mean":47.35878851533555,"min":5.262820504477954},"none":{"max":68.53513465848795,"mean":41.32182243131179,"min":7.762644064216704}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":78.36217050861919,"expected_score":49.55076181440217,"reasoning_variance":15.470728733339342,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.059707777302691},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.9171053737359,"expected_score":51.57026833659429,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.222282828056841},"medium":{"ceiling_score":78.36217050861919,"expected_score":49.2078414890032,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8490529736676535},"none":{"ceiling_score":68.53513465848795,"expected_score":47.87417561760901,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.552353186297225}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:15240191bfce2009","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007552000000003},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656476}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656475999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007551999999994}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.2861911833333333,"median":0.206604,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":30},"recorded_attempt_count":30,"run_count":24,"total":6.868588399999999},"codegen_latency_ms":{"attempt_count":30,"max_ms":235793,"mean_ms":83718.41666666667,"min_ms":17910,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":235793,"mean_ms":170391.375,"min_ms":123596,"run_count":8},"medium":{"attempt_count":11,"max_ms":84789,"mean_ms":58477.125,"min_ms":40383,"run_count":8},"none":{"attempt_count":10,"max_ms":29743,"mean_ms":22286.75,"min_ms":17910,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":29674,"output_mean":12261.208333333334,"output_min":3304,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":29674,"output_mean":22547.25,"output_min":16651,"run_count":8},"medium":{"attempt_count":11,"output_max":17493,"output_mean":10166.125,"output_min":6634,"run_count":8},"none":{"attempt_count":10,"output_max":5361,"output_mean":4070.25,"output_min":3304,"run_count":8}},"display_name":"Muse Wonder","economics":{"all":46.77336357039708,"highest":58.75944687102806,"medium":43.690429901981624,"none":37.87021393818156},"first_seen_at":"2026-10-13T14:28:27Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[943718],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[943718],"total_output_tokens":294269,"total_reasoning_output_tokens":154600,"total_visible_output_tokens":139669,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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":"meta/muse-wonder","is_recent_addition":true,"last_measured_at":"2026-10-13T14:28:27Z","match_totals_all":{"draws":1955,"losses":2591,"wins":5850},"match_totals_tracks":{"highest":{"draws":424,"losses":492,"wins":2488},"medium":{"draws":584,"losses":993,"wins":1829},"none":{"draws":947,"losses":1106,"wins":1533}},"model_slug":"meta-muse-wonder","overall":{"max":82.41583244948515,"mean":46.77336357039709,"min":1.1568593165255132},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":69.57376838060813,"GB2-02":31.4609491507737,"GB2-03":55.345920419302956,"GB2-04":59.27324847336205,"GB2-05":82.41583244948515,"GB2-06":73.89846770703144,"GB2-07":61.06675857009991,"GB2-08":37.04062981756115},"per_game_all":{"GB2-01":55.66507716104591,"GB2-02":19.307584226504485,"GB2-03":24.37548392194336,"GB2-04":30.000251774284802,"GB2-05":74.45155437819507,"GB2-06":67.832758142808,"GB2-07":61.74906442305859,"GB2-08":40.80513453533644},"per_game_match_totals_all":{"GB2-01":{"draws":160,"losses":358,"wins":880},"GB2-02":{"draws":838,"losses":173,"wins":267},"GB2-03":{"draws":238,"losses":630,"wins":452},"GB2-04":{"draws":526,"losses":307,"wins":505},"GB2-05":{"draws":0,"losses":179,"wins":1273},"GB2-06":{"draws":91,"losses":276,"wins":1001},"GB2-07":{"draws":0,"losses":416,"wins":994},"GB2-08":{"draws":102,"losses":252,"wins":478}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":66,"wins":395},"GB2-02":{"draws":236,"losses":29,"wins":161},"GB2-03":{"draws":71,"losses":46,"wins":323},"GB2-04":{"draws":54,"losses":59,"wins":333},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":27,"losses":59,"wins":370},"GB2-07":{"draws":0,"losses":131,"wins":339},"GB2-08":{"draws":31,"losses":69,"wins":116}},"medium":{"GB2-01":{"draws":4,"losses":218,"wins":244},"GB2-02":{"draws":267,"losses":60,"wins":99},"GB2-03":{"draws":85,"losses":251,"wins":104},"GB2-04":{"draws":193,"losses":177,"wins":76},"GB2-05":{"draws":0,"losses":72,"wins":412},"GB2-06":{"draws":26,"losses":93,"wins":337},"GB2-07":{"draws":0,"losses":58,"wins":412},"GB2-08":{"draws":9,"losses":64,"wins":145}},"none":{"GB2-01":{"draws":151,"losses":74,"wins":241},"GB2-02":{"draws":335,"losses":84,"wins":7},"GB2-03":{"draws":82,"losses":333,"wins":25},"GB2-04":{"draws":279,"losses":71,"wins":96},"GB2-05":{"draws":0,"losses":74,"wins":410},"GB2-06":{"draws":38,"losses":124,"wins":294},"GB2-07":{"draws":0,"losses":227,"wins":243},"GB2-08":{"draws":62,"losses":119,"wins":217}}},"per_game_raw_elo_all":{"GB2-01":1700.7162519323522,"GB2-02":1516.4777938309928,"GB2-03":1420.8652475694953,"GB2-04":1563.4899344139887,"GB2-05":2141.340578017585,"GB2-06":1901.2660571923889,"GB2-07":1781.90392925852,"GB2-08":1620.5043507896587},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1911.3915567888537,"GB2-02":1613.205196640599,"GB2-03":1829.4738492858864,"GB2-04":1781.6660250318182,"GB2-05":2319.819857448248,"GB2-06":2036.3071121828261,"GB2-07":1767.9884855379996,"GB2-08":1561.8824799201884},"medium":{"GB2-01":1518.1896998073073,"GB2-02":1521.3769411460426,"GB2-03":1318.5916803821276,"GB2-04":1398.719356171031,"GB2-05":2057.681484284318,"GB2-06":1901.0240480224925,"GB2-07":2076.602365549826,"GB2-08":1712.767957829658},"none":{"GB2-01":1672.567499200896,"GB2-02":1414.8512437063375,"GB2-03":1114.5302130404718,"GB2-04":1510.0844220391175,"GB2-05":2046.520392320189,"GB2-06":1766.467011371848,"GB2-07":1501.1209366877342,"GB2-08":1586.8626146191295}},"per_game_tracks":{"highest":{"GB2-01":69.57376838060813,"GB2-02":31.4609491507737,"GB2-03":55.345920419302956,"GB2-04":59.27324847336205,"GB2-05":82.41583244948515,"GB2-06":73.89846770703144,"GB2-07":61.06675857009991,"GB2-08":37.04062981756115},"medium":{"GB2-01":43.6147542501201,"GB2-02":19.923140143525732,"GB2-03":16.623672030001607,"GB2-04":7.89274870484904,"GB2-05":70.71843595789854,"GB2-06":67.8218876905846,"GB2-07":76.19879897538289,"GB2-08":46.73000146349052},"none":{"GB2-01":53.80670885240951,"GB2-02":6.538663385214032,"GB2-03":1.1568593165255132,"GB2-04":22.834758144643317,"GB2-05":70.22039472720152,"GB2-06":61.77791903080796,"GB2-07":47.98163572369295,"GB2-08":38.64477232495766}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":58.75944687102806,"medium":43.690429901981624,"none":37.87021393818156},"reasoning_agg":{"highest":{"max":82.41583244948515,"mean":58.75944687102806,"min":31.4609491507737},"medium":{"max":76.19879897538289,"mean":43.690429901981624,"min":7.89274870484904},"none":{"max":70.22039472720152,"mean":37.87021393818156,"min":1.1568593165255132}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":82.41583244948515,"expected_score":47.81132084737405,"reasoning_variance":20.889232932846504,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.037957276976961},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.41583244948515,"expected_score":54.325311552262406,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.434135318765655},"medium":{"ceiling_score":76.19879897538289,"expected_score":45.10925655822984,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4188266562482141},"none":{"ceiling_score":70.22039472720152,"expected_score":43.99939443162987,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.12918049344831}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:b16b290371c28436","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":1.8727580000000001},"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":1.8727579999999997}},"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":3.145718},"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":42.34383534788051,"highest":46.66874641265159,"medium":51.11992347173105,"none":29.242836159258875},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:21:25Z","match_totals_all":{"draws":4030,"losses":4294,"wins":6836},"match_totals_tracks":{"highest":{"draws":1207,"losses":1328,"wins":2576},"medium":{"draws":956,"losses":1009,"wins":2894},"none":{"draws":1867,"losses":1957,"wins":1366}},"model_slug":"x-ai-grok-4-6","overall":{"max":71.4022194785355,"mean":42.34383534788051,"min":8.39868138986373},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.485311952659096,"GB2-02":54.90286629186348,"GB2-03":27.209179684961228,"GB2-04":26.094072307501236,"GB2-05":71.4022194785355,"GB2-06":58.73625382368738,"GB2-07":63.381976593024916,"GB2-08":29.138091168979876},"per_game_all":{"GB2-01":48.36965997404258,"GB2-02":27.418338584826653,"GB2-03":29.030178750757646,"GB2-04":24.296428947814572,"GB2-05":61.36894757344151,"GB2-06":50.725906784103266,"GB2-07":59.286021388777634,"GB2-08":38.25520077928018},"per_game_match_totals_all":{"GB2-01":{"draws":592,"losses":540,"wins":844},"GB2-02":{"draws":912,"losses":235,"wins":552},"GB2-03":{"draws":778,"losses":531,"wins":583},"GB2-04":{"draws":1012,"losses":396,"wins":519},"GB2-05":{"draws":0,"losses":556,"wins":1398},"GB2-06":{"draws":96,"losses":860,"wins":864},"GB2-07":{"draws":0,"losses":641,"wins":1309},"GB2-08":{"draws":640,"losses":535,"wins":767}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":354,"losses":168,"wins":170},"GB2-02":{"draws":82,"losses":60,"wins":413},"GB2-03":{"draws":145,"losses":272,"wins":263},"GB2-04":{"draws":323,"losses":133,"wins":212},"GB2-05":{"draws":0,"losses":94,"wins":542},"GB2-06":{"draws":51,"losses":225,"wins":338},"GB2-07":{"draws":0,"losses":167,"wins":455},"GB2-08":{"draws":252,"losses":209,"wins":183}},"medium":{"GB2-01":{"draws":159,"losses":177,"wins":288},"GB2-02":{"draws":367,"losses":86,"wins":121},"GB2-03":{"draws":127,"losses":161,"wins":314},"GB2-04":{"draws":266,"losses":87,"wins":242},"GB2-05":{"draws":0,"losses":118,"wins":518},"GB2-06":{"draws":37,"losses":117,"wins":448},"GB2-07":{"draws":0,"losses":163,"wins":457},"GB2-08":{"draws":0,"losses":100,"wins":506}},"none":{"GB2-01":{"draws":79,"losses":195,"wins":386},"GB2-02":{"draws":463,"losses":89,"wins":18},"GB2-03":{"draws":506,"losses":98,"wins":6},"GB2-04":{"draws":423,"losses":176,"wins":65},"GB2-05":{"draws":0,"losses":344,"wins":338},"GB2-06":{"draws":8,"losses":518,"wins":78},"GB2-07":{"draws":0,"losses":311,"wins":397},"GB2-08":{"draws":388,"losses":226,"wins":78}}},"per_game_raw_elo_all":{"GB2-01":1590.2123795215832,"GB2-02":1581.0304678266987,"GB2-03":1482.2769860052929,"GB2-04":1520.9784765455418,"GB2-05":1848.1596751553018,"GB2-06":1520.4157657986834,"GB2-07":1731.6708313360375,"GB2-08":1580.7961026720757},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1501.0820081791576,"GB2-02":1799.7770453479186,"GB2-03":1458.251626141044,"GB2-04":1534.376585545906,"GB2-05":2073.0050564847643,"GB2-06":1698.7503371479552,"GB2-07":1815.2067322510302,"GB2-08":1438.8220417141492},"medium":{"GB2-01":1612.0178035354468,"GB2-02":1513.659419162021,"GB2-03":1613.2599925364148,"GB2-04":1606.928472602037,"GB2-05":1981.4562783696208,"GB2-06":1961.4644613976773,"GB2-07":1824.6669869335851,"GB2-08":1977.1943412209312},"none":{"GB2-01":1657.5373268501455,"GB2-02":1429.6549389701568,"GB2-03":1375.3193393384195,"GB2-04":1421.6303714886826,"GB2-05":1490.0176906115207,"GB2-06":901.0324988504185,"GB2-07":1555.1387748234968,"GB2-08":1326.3719250811464}},"per_game_tracks":{"highest":{"GB2-01":42.485311952659096,"GB2-02":54.90286629186348,"GB2-03":27.209179684961228,"GB2-04":26.094072307501236,"GB2-05":71.4022194785355,"GB2-06":58.73625382368738,"GB2-07":63.381976593024916,"GB2-08":29.138091168979876},"medium":{"GB2-01":49.80924450307427,"GB2-02":18.953468072752752,"GB2-03":38.95801891115881,"GB2-04":35.828462287135366,"GB2-05":67.3170397964924,"GB2-06":70.53672129064377,"GB2-07":63.845834395192476,"GB2-08":63.710598517398594},"none":{"GB2-01":52.81442346639437,"GB2-02":8.39868138986373,"GB2-03":20.9233376561529,"GB2-04":10.96675224880711,"GB2-05":45.387583445296634,"GB2-06":22.904745237978666,"GB2-07":50.630253178115524,"GB2-08":21.916912651462074}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.66874641265159,"medium":51.11992347173105,"none":29.242836159258875},"reasoning_agg":{"highest":{"max":71.4022194785355,"mean":46.66874641265159,"min":26.094072307501236},"medium":{"max":70.53672129064377,"mean":51.11992347173105,"min":18.953468072752752},"none":{"max":52.81442346639437,"mean":29.242836159258875,"min":8.39868138986373}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":71.4022194785355,"expected_score":41.877455919110304,"reasoning_variance":21.877087312472174,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.4663794287702032},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":71.4022194785355,"expected_score":40.36963750800868,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.299108904642914},"medium":{"ceiling_score":70.53672129064377,"expected_score":53.60245989563907,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.482536423908023},"none":{"ceiling_score":52.81442346639437,"expected_score":31.660270353683163,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.4174341944242883}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:5642a8006ca19523","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000002},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.1879375},"codegen_output_tokens":{"attempt_count":27,"output_max":146534,"output_mean":40675.041666666664,"output_min":3180,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":146534,"output_mean":99672.5,"output_min":71368,"run_count":8},"medium":{"attempt_count":8,"output_max":26272,"output_mean":17600.375,"output_min":12941,"run_count":8},"none":{"attempt_count":10,"output_max":8643,"output_mean":4752.25,"output_min":3180,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":45.20019222639864,"highest":55.66246658619468,"medium":40.34277702953907,"none":31.462825065600587},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:41:54Z","match_totals_all":{"draws":4185,"losses":4860,"wins":7171},"match_totals_tracks":{"highest":{"draws":750,"losses":1040,"wins":3130},"medium":{"draws":1716,"losses":1641,"wins":2291},"none":{"draws":1719,"losses":2179,"wins":1750}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":41.88019009164798,"min":0.6193685545076086},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":87.72941451630335,"GB2-03":22.673008096816968,"GB2-04":27.114620216987902,"GB2-05":73.81359616694667,"GB2-06":72.63472803108257,"GB2-07":66.04774914185796,"GB2-08":39.62414993336731},"per_game_all":{"GB2-01":84.37548276414076,"GB2-03":20.056515449781184,"GB2-04":11.623255792362094,"GB2-05":60.51280644932789,"GB2-06":67.33852953854309,"GB2-07":45.520546091993104,"GB2-08":26.974209498642406},"per_game_match_totals_all":{"GB2-01":{"draws":90,"losses":154,"wins":1830},"GB2-02":{"draws":1012,"losses":221,"wins":50},"GB2-03":{"draws":870,"losses":860,"wins":425},"GB2-04":{"draws":1123,"losses":613,"wins":314},"GB2-05":{"draws":0,"losses":613,"wins":1563},"GB2-06":{"draws":137,"losses":485,"wins":1460},"GB2-07":{"draws":0,"losses":1172,"wins":1030},"GB2-08":{"draws":953,"losses":742,"wins":499}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":29,"wins":644},"GB2-03":{"draws":247,"losses":308,"wins":198},"GB2-04":{"draws":346,"losses":119,"wins":202},"GB2-05":{"draws":0,"losses":87,"wins":633},"GB2-06":{"draws":57,"losses":102,"wins":533},"GB2-07":{"draws":0,"losses":154,"wins":546},"GB2-08":{"draws":83,"losses":241,"wins":374}},"medium":{"GB2-01":{"draws":8,"losses":10,"wins":672},"GB2-02":{"draws":521,"losses":100,"wins":40},"GB2-03":{"draws":339,"losses":245,"wins":140},"GB2-04":{"draws":359,"losses":256,"wins":45},"GB2-05":{"draws":0,"losses":214,"wins":512},"GB2-06":{"draws":47,"losses":129,"wins":514},"GB2-07":{"draws":0,"losses":470,"wins":266},"GB2-08":{"draws":442,"losses":217,"wins":102}},"none":{"GB2-01":{"draws":65,"losses":115,"wins":514},"GB2-02":{"draws":491,"losses":121,"wins":10},"GB2-03":{"draws":284,"losses":307,"wins":87},"GB2-04":{"draws":418,"losses":238,"wins":67},"GB2-05":{"draws":0,"losses":312,"wins":418},"GB2-06":{"draws":33,"losses":254,"wins":413},"GB2-07":{"draws":0,"losses":548,"wins":218},"GB2-08":{"draws":428,"losses":284,"wins":23}}},"per_game_raw_elo_all":{"GB2-01":2135.593506557047,"GB2-03":1363.882916422247,"GB2-04":1426.5233921138686,"GB2-05":1828.9735732192596,"GB2-06":1890.26303249763,"GB2-07":1450.9276778836804,"GB2-08":1405.1254995750544},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2186.395597364912,"GB2-03":1398.40362464661,"GB2-04":1541.9828841243846,"GB2-05":2127.04394989495,"GB2-06":2008.1724418253843,"GB2-07":1869.5744439072294,"GB2-08":1602.113743784023},"medium":{"GB2-01":2372.2584723642267,"GB2-02":1445.8554941776847,"GB2-03":1392.9437501890982,"GB2-04":1344.5097491707052,"GB2-05":1767.9203981327485,"GB2-06":1952.5863490856932,"GB2-07":1283.4833861159063,"GB2-08":1361.8113999498212},"none":{"GB2-01":1848.126449942003,"GB2-02":1398.1787364190109,"GB2-03":1300.301374431033,"GB2-04":1393.0775430465153,"GB2-05":1591.9563716300804,"GB2-06":1710.030306581813,"GB2-07":1199.7252036279056,"GB2-08":1251.4513549913188}},"per_game_tracks":{"highest":{"GB2-01":87.72941451630335,"GB2-03":22.673008096816968,"GB2-04":27.114620216987902,"GB2-05":73.81359616694667,"GB2-06":72.63472803108257,"GB2-07":66.04774914185796,"GB2-08":39.62414993336731},"medium":{"GB2-01":100.0,"GB2-02":10.434208589952098,"GB2-03":22.259177613416394,"GB2-04":0.6193685545076086,"GB2-05":57.78843158029422,"GB2-06":70.13793848517128,"GB2-07":37.310371654709684,"GB2-08":24.19271975826127},"none":{"GB2-01":65.39703377611895,"GB2-02":4.443837520156321,"GB2-03":15.237360639110182,"GB2-04":7.135778605590774,"GB2-05":49.936391600742766,"GB2-06":59.24292209937542,"GB2-07":33.20351747941166,"GB2-08":17.105758804298627}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.8349681798043,"medium":40.34277702953907,"none":31.462825065600587},"reasoning_agg":{"highest":{"max":87.72941451630335,"mean":53.8349681798043,"min":22.673008096816968},"medium":{"max":100.0,"mean":40.34277702953907,"min":0.6193685545076086},"none":{"max":65.39703377611895,"mean":31.462825065600587,"min":4.443837520156321}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":45.49989009650157,"reasoning_variance":22.372143114203713,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.619700004853584},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":87.72941451630335,"expected_score":49.93875615751019,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.896212022294108},"medium":{"ceiling_score":100.0,"expected_score":41.20567345980966,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8628964302705882},"none":{"ceiling_score":65.39703377611895,"expected_score":36.164926320567375,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.702101254966788}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:0c5ad1b0c55c8061","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2555334390339119}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850016},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.9756462500000003},"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":41.28692108017369,"highest":45.13406922524436,"medium":41.244181443859276,"none":37.48251257141744},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:55:14Z","match_totals_all":{"draws":3469,"losses":4620,"wins":6988},"match_totals_tracks":{"highest":{"draws":753,"losses":1503,"wins":2734},"medium":{"draws":1432,"losses":1428,"wins":2189},"none":{"draws":1284,"losses":1689,"wins":2065}},"model_slug":"google-gemini-3-8-flash","overall":{"max":76.47914207980016,"mean":41.28692108017369,"min":4.382875756575589},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.86006108437858,"GB2-02":34.019866474744674,"GB2-03":43.645091696574696,"GB2-04":17.46237063785519,"GB2-05":54.14988123314965,"GB2-06":76.47914207980016,"GB2-07":58.05100169720412,"GB2-08":32.40513889824779},"per_game_all":{"GB2-01":48.80318265256361,"GB2-02":14.395248822526225,"GB2-03":42.97734563595058,"GB2-04":19.220243236910974,"GB2-05":50.005010195422365,"GB2-06":70.91491676136853,"GB2-07":49.65336510307506,"GB2-08":34.32605623357215},"per_game_match_totals_all":{"GB2-01":{"draws":413,"losses":626,"wins":949},"GB2-02":{"draws":1134,"losses":287,"wins":266},"GB2-03":{"draws":286,"losses":480,"wins":1085},"GB2-04":{"draws":838,"losses":523,"wins":464},"GB2-05":{"draws":0,"losses":859,"wins":1109},"GB2-06":{"draws":107,"losses":349,"wins":1350},"GB2-07":{"draws":0,"losses":909,"wins":1073},"GB2-08":{"draws":691,"losses":587,"wins":692}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":290,"wins":338},"GB2-02":{"draws":228,"losses":75,"wins":261},"GB2-03":{"draws":26,"losses":174,"wins":397},"GB2-04":{"draws":108,"losses":265,"wins":220},"GB2-05":{"draws":0,"losses":242,"wins":406},"GB2-06":{"draws":50,"losses":65,"wins":487},"GB2-07":{"draws":0,"losses":221,"wins":405},"GB2-08":{"draws":285,"losses":171,"wins":220}},"medium":{"GB2-01":{"draws":88,"losses":158,"wins":376},"GB2-02":{"draws":451,"losses":109,"wins":3},"GB2-03":{"draws":119,"losses":50,"wins":429},"GB2-04":{"draws":378,"losses":99,"wins":159},"GB2-05":{"draws":0,"losses":299,"wins":339},"GB2-06":{"draws":30,"losses":124,"wins":448},"GB2-07":{"draws":0,"losses":323,"wins":393},"GB2-08":{"draws":366,"losses":266,"wins":42}},"none":{"GB2-01":{"draws":269,"losses":178,"wins":235},"GB2-02":{"draws":455,"losses":103,"wins":2},"GB2-03":{"draws":141,"losses":256,"wins":259},"GB2-04":{"draws":352,"losses":159,"wins":85},"GB2-05":{"draws":0,"losses":318,"wins":364},"GB2-06":{"draws":27,"losses":160,"wins":415},"GB2-07":{"draws":0,"losses":365,"wins":275},"GB2-08":{"draws":40,"losses":150,"wins":430}}},"per_game_raw_elo_all":{"GB2-01":1596.7789587214413,"GB2-02":1477.3810129544765,"GB2-03":1666.2889988598647,"GB2-04":1483.1448934300167,"GB2-05":1593.4941126813517,"GB2-06":1969.8842373230707,"GB2-07":1535.215406189729,"GB2-08":1519.6104165183604},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1537.0523945645461,"GB2-02":1633.5713609329218,"GB2-03":1675.0989096971405,"GB2-04":1470.0432019493394,"GB2-05":1686.3805726372582,"GB2-06":2093.7607350765047,"GB2-07":1706.4829380513718,"GB2-08":1489.6973797646544},"medium":{"GB2-01":1708.3924015185655,"GB2-02":1397.693547905492,"GB2-03":1852.7796573419823,"GB2-04":1529.809939513252,"GB2-05":1553.1885837284776,"GB2-06":1952.3346345249488,"GB2-07":1541.8539888015239,"GB2-08":1273.0542080885505},"none":{"GB2-01":1544.8920800812127,"GB2-02":1400.878130025016,"GB2-03":1470.9884295404713,"GB2-04":1449.5815388274586,"GB2-05":1540.913181678319,"GB2-06":1863.5573423677586,"GB2-07":1357.3092917162915,"GB2-08":1796.0796617018761}},"per_game_tracks":{"highest":{"GB2-01":44.86006108437858,"GB2-02":34.019866474744674,"GB2-03":43.645091696574696,"GB2-04":17.46237063785519,"GB2-05":54.14988123314965,"GB2-06":76.47914207980016,"GB2-07":58.05100169720412,"GB2-08":32.40513889824779},"medium":{"GB2-01":56.17185318979086,"GB2-02":4.382875756575589,"GB2-03":57.11238114819861,"GB2-04":25.481358907691092,"GB2-05":48.20645721260497,"GB2-06":70.12663209084053,"GB2-07":49.978869906396405,"GB2-08":18.49302333877612},"none":{"GB2-01":45.37763368352142,"GB2-02":4.783004236258415,"GB2-03":28.17456406307843,"GB2-04":14.717000165186642,"GB2-05":47.65869214051249,"GB2-06":66.1389761134649,"GB2-07":40.93022370562465,"GB2-08":52.08000646369255}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.13406922524436,"medium":41.244181443859276,"none":37.48251257141744},"reasoning_agg":{"highest":{"max":76.47914207980016,"mean":45.13406922524436,"min":17.46237063785519},"medium":{"max":70.12663209084053,"mean":41.244181443859276,"min":4.382875756575589},"none":{"max":66.1389761134649,"mean":37.48251257141744,"min":4.783004236258415}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":76.47914207980016,"expected_score":41.720848452989884,"reasoning_variance":7.651556653826923,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.43392737281619276},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.47914207980016,"expected_score":39.29791075768296,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.836158467561397},"medium":{"ceiling_score":70.12663209084053,"expected_score":42.62833798189903,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.384156538039754},"none":{"ceiling_score":66.1389761134649,"expected_score":43.23629661938766,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.753784047970221}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:47f41b32a19bbda4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.9894712499999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740124999999995},"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":0.19110975000000002}},"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":0.19110975000000002},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.98947125}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.10824926041666667,"median":0.050446875,"min":0.017614,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":27,"run_count":24,"total":2.59798225},"codegen_latency_ms":{"attempt_count":27,"max_ms":344702,"mean_ms":125679.0,"min_ms":18724,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":344702,"mean_ms":258574.75,"min_ms":141477,"run_count":8},"medium":{"attempt_count":8,"max_ms":148027,"mean_ms":92816.75,"min_ms":70623,"run_count":8},"none":{"attempt_count":9,"max_ms":39588,"mean_ms":25645.5,"min_ms":18724,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":82251,"output_mean":22811.583333333332,"output_min":2043,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":82251,"output_mean":55365.125,"output_min":27171,"run_count":8},"medium":{"attempt_count":8,"output_max":15366,"output_mean":10008.75,"output_min":7655,"run_count":8},"none":{"attempt_count":9,"output_max":5638,"output_mean":3060.875,"output_min":2043,"run_count":8}},"display_name":"Muse Spark 1.3","economics":{"all":40.94845979269307,"highest":49.29897243697418,"medium":46.32856587707573,"none":27.217841064029294},"first_seen_at":"2026-10-13T11:42:06Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":79,"requested_max_output_token_observations":10,"requested_max_output_tokens":[943718],"total_output_tokens":547478,"total_reasoning_output_tokens":432530,"total_visible_output_tokens":114948,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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":"meta/muse-spark-1.3","is_recent_addition":true,"last_measured_at":"2026-10-13T11:42:06Z","match_totals_all":{"draws":2751,"losses":4411,"wins":6273},"match_totals_tracks":{"highest":{"draws":454,"losses":790,"wins":2142},"medium":{"draws":781,"losses":1448,"wins":2778},"none":{"draws":1516,"losses":2173,"wins":1353}},"model_slug":"meta-muse-spark-1-3","overall":{"max":74.09542289284347,"mean":40.948459792693065,"min":10.47888455002134},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.90888509112459,"GB2-02":26.819240005328858,"GB2-03":55.19617111391701,"GB2-04":19.62524483340632,"GB2-05":63.81588401362971,"GB2-06":74.09542289284347,"GB2-07":50.638994300428934,"GB2-08":43.29193724511455},"per_game_all":{"GB2-01":48.41696761803473,"GB2-02":19.6030353716273,"GB2-03":40.0496205478331,"GB2-04":21.232240967811865,"GB2-05":50.49398924359587,"GB2-06":62.9647341916374,"GB2-07":46.03818744081577,"GB2-08":38.78890296018853},"per_game_match_totals_all":{"GB2-01":{"draws":147,"losses":656,"wins":893},"GB2-02":{"draws":1073,"losses":198,"wins":305},"GB2-03":{"draws":264,"losses":524,"wins":948},"GB2-04":{"draws":745,"losses":430,"wins":474},"GB2-05":{"draws":0,"losses":797,"wins":1031},"GB2-06":{"draws":78,"losses":512,"wins":1114},"GB2-07":{"draws":0,"losses":903,"wins":869},"GB2-08":{"draws":444,"losses":391,"wins":639}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":107,"wins":357},"GB2-02":{"draws":246,"losses":42,"wins":138},"GB2-03":{"draws":36,"losses":64,"wins":340},"GB2-04":{"draws":118,"losses":165,"wins":163},"GB2-05":{"draws":0,"losses":103,"wins":381},"GB2-06":{"draws":33,"losses":55,"wins":368},"GB2-07":{"draws":0,"losses":206,"wins":264},"GB2-08":{"draws":19,"losses":48,"wins":131}},"medium":{"GB2-01":{"draws":0,"losses":177,"wins":441},"GB2-02":{"draws":366,"losses":72,"wins":122},"GB2-03":{"draws":85,"losses":214,"wins":318},"GB2-04":{"draws":282,"losses":93,"wins":229},"GB2-05":{"draws":0,"losses":301,"wins":355},"GB2-06":{"draws":23,"losses":115,"wins":482},"GB2-07":{"draws":0,"losses":327,"wins":361},"GB2-08":{"draws":25,"losses":149,"wins":470}},"none":{"GB2-01":{"draws":145,"losses":372,"wins":95},"GB2-02":{"draws":461,"losses":84,"wins":45},"GB2-03":{"draws":143,"losses":246,"wins":290},"GB2-04":{"draws":345,"losses":172,"wins":82},"GB2-05":{"draws":0,"losses":393,"wins":295},"GB2-06":{"draws":22,"losses":342,"wins":264},"GB2-07":{"draws":0,"losses":370,"wins":244},"GB2-08":{"draws":400,"losses":194,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1590.9289496260424,"GB2-02":1518.8292596269214,"GB2-03":1627.6620439389137,"GB2-04":1498.1406181169168,"GB2-05":1604.4521213537637,"GB2-06":1792.889109182522,"GB2-07":1461.4848334843848,"GB2-08":1589.1070552880292},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1780.1443459808042,"GB2-02":1576.2623027972734,"GB2-03":1827.498131110685,"GB2-04":1486.163431843616,"GB2-05":1902.9954617448932,"GB2-06":2040.6919307759829,"GB2-07":1555.3170476538983,"GB2-08":1659.2295054274282},"medium":{"GB2-01":1749.6286641691427,"GB2-02":1528.737995396616,"GB2-03":1563.1910491044196,"GB2-04":1590.2642030787958,"GB2-05":1563.6635040752276,"GB2-06":1988.512737834273,"GB2-07":1514.8889927601608,"GB2-08":1811.1589627646672},"none":{"GB2-01":1243.0138387281797,"GB2-02":1451.4874806868745,"GB2-03":1492.2969516016367,"GB2-04":1417.9942194283385,"GB2-05":1346.6973982411698,"GB2-06":1349.4626589373106,"GB2-07":1314.2484600390956,"GB2-08":1296.9326976719922}},"per_game_tracks":{"highest":{"GB2-01":60.90888509112459,"GB2-02":26.819240005328858,"GB2-03":55.19617111391701,"GB2-04":19.62524483340632,"GB2-05":63.81588401362971,"GB2-06":74.09542289284347,"GB2-07":50.638994300428934,"GB2-08":43.29193724511455},"medium":{"GB2-01":58.894253162802904,"GB2-02":20.84802364019787,"GB2-03":35.163049773120974,"GB2-04":33.59259352000794,"GB2-05":48.67387941804109,"GB2-06":71.7516628437058,"GB2-07":48.65671482506771,"GB2-08":53.048349833661554},"none":{"GB2-01":25.447764600176694,"GB2-02":11.141842469355165,"GB2-03":29.789640756461306,"GB2-04":10.47888455002134,"GB2-05":38.99220429911679,"GB2-06":43.0471168383629,"GB2-07":38.81885319695068,"GB2-08":20.0264218017895}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.29897243697418,"medium":46.32856587707573,"none":27.217841064029294},"reasoning_agg":{"highest":{"max":74.09542289284347,"mean":49.29897243697418,"min":19.62524483340632},"medium":{"max":71.7516628437058,"mean":46.32856587707573,"min":20.84802364019787},"none":{"max":43.0471168383629,"mean":27.217841064029294,"min":10.47888455002134}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.09542289284347,"expected_score":40.524331698294404,"reasoning_variance":22.08113137294489,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.42412809439866095},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.09542289284347,"expected_score":43.97873947732165,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.320232959652529},"medium":{"ceiling_score":71.7516628437058,"expected_score":48.153980805598216,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.825414928522484},"none":{"ceiling_score":43.0471168383629,"expected_score":29.44027481196335,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.222433747934055}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:a83d1736bfc7ecfa","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3826036},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.0249632}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.09558079999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.024963199999999998},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.38260359999999993}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.0653315,"mean":0.020964483333333336,"median":0.012623549999999999,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":0.5031475999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":128000,"output_mean":38910.541666666664,"output_min":1643,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":128000,"output_mean":92691.0,"output_min":56566,"run_count":8},"medium":{"attempt_count":9,"output_max":32619,"output_mean":20970.375,"output_min":8448,"run_count":8},"none":{"attempt_count":10,"output_max":6434,"output_mean":3070.25,"output_min":1643,"run_count":8}},"display_name":"Claude Haiku 5.5","economics":{"all":41.39198868403371,"highest":57.76712807685366,"medium":39.892718364619185,"none":25.668683451519147},"first_seen_at":"2026-10-13T14:25:31Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":933853,"total_reasoning_output_tokens":827092,"total_visible_output_tokens":106761,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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}}},"id":"claude-haiku-5-5","is_recent_addition":true,"last_measured_at":"2026-10-13T14:25:31Z","match_totals_all":{"draws":2242,"losses":3387,"wins":4367},"match_totals_tracks":{"highest":{"draws":356,"losses":620,"wins":1982},"medium":{"draws":874,"losses":1167,"wins":1605},"none":{"draws":1012,"losses":1600,"wins":780}},"model_slug":"claude-haiku-5-5","overall":{"max":81.5354966939596,"mean":40.477310560933624,"min":6.538663385214032},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":36.11052579826498,"GB2-02":34.876291122201124,"GB2-04":57.8735947054095,"GB2-05":71.99910669635669,"GB2-06":81.5354966939596,"GB2-07":56.07295176837495,"GB2-08":65.90192975340877},"per_game_all":{"GB2-01":35.56500552685775,"GB2-02":22.53675868834613,"GB2-04":35.11609926474702,"GB2-05":47.942104306623825,"GB2-06":63.487607670552734,"GB2-07":50.975801870355525,"GB2-08":34.120543460753},"per_game_match_totals_all":{"GB2-01":{"draws":234,"losses":719,"wins":445},"GB2-02":{"draws":763,"losses":172,"wins":343},"GB2-03":{"draws":249,"losses":296,"wins":335},"GB2-04":{"draws":579,"losses":218,"wins":541},"GB2-05":{"draws":0,"losses":676,"wins":776},"GB2-06":{"draws":57,"losses":396,"wins":915},"GB2-07":{"draws":0,"losses":612,"wins":798},"GB2-08":{"draws":360,"losses":298,"wins":214}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":30,"losses":260,"wins":176},"GB2-02":{"draws":191,"losses":39,"wins":196},"GB2-04":{"draws":101,"losses":39,"wins":306},"GB2-05":{"draws":0,"losses":67,"wins":417},"GB2-06":{"draws":34,"losses":22,"wins":400},"GB2-07":{"draws":0,"losses":165,"wins":305},"GB2-08":{"draws":0,"losses":28,"wins":182}},"medium":{"GB2-01":{"draws":123,"losses":194,"wins":149},"GB2-02":{"draws":231,"losses":52,"wins":143},"GB2-03":{"draws":85,"losses":111,"wins":244},"GB2-04":{"draws":190,"losses":54,"wins":202},"GB2-05":{"draws":0,"losses":206,"wins":278},"GB2-06":{"draws":6,"losses":142,"wins":308},"GB2-07":{"draws":0,"losses":212,"wins":258},"GB2-08":{"draws":239,"losses":196,"wins":23}},"none":{"GB2-01":{"draws":81,"losses":265,"wins":120},"GB2-02":{"draws":341,"losses":81,"wins":4},"GB2-03":{"draws":164,"losses":185,"wins":91},"GB2-04":{"draws":288,"losses":125,"wins":33},"GB2-05":{"draws":0,"losses":403,"wins":81},"GB2-06":{"draws":17,"losses":232,"wins":207},"GB2-07":{"draws":0,"losses":235,"wins":235},"GB2-08":{"draws":121,"losses":74,"wins":9}}},"per_game_raw_elo_all":{"GB2-01":1396.2599481491272,"GB2-02":1542.1784669251838,"GB2-04":1601.6191227967165,"GB2-05":1547.2644414832441,"GB2-06":1804.5298554912,"GB2-07":1562.1861471400528,"GB2-08":1516.4101168419263},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1404.5229577788527,"GB2-02":1640.3875581233124,"GB2-04":1771.234192908528,"GB2-05":2086.381284635578,"GB2-06":2206.3304936962077,"GB2-07":1666.1411436176243,"GB2-08":2011.3183353131847},"medium":{"GB2-01":1444.9942175438025,"GB2-02":1571.296598945902,"GB2-03":1612.1912021163437,"GB2-04":1626.8243219433057,"GB2-05":1563.7715193568245,"GB2-06":1759.4712439980144,"GB2-07":1539.718575406656,"GB2-08":1246.2621701772052},"none":{"GB2-01":1339.2626691247272,"GB2-02":1414.8512437063375,"GB2-03":1373.0632627898774,"GB2-04":1406.7988535383158,"GB2-05":991.6405204573302,"GB2-06":1447.787828779378,"GB2-07":1480.6987223958786,"GB2-08":1291.6498450353886}},"per_game_tracks":{"highest":{"GB2-01":36.11052579826498,"GB2-02":34.876291122201124,"GB2-04":57.8735947054095,"GB2-05":71.99910669635669,"GB2-06":81.5354966939596,"GB2-07":56.07295176837495,"GB2-08":65.90192975340877},"medium":{"GB2-01":38.782420616315875,"GB2-02":26.195321557623227,"GB2-03":38.87701007851369,"GB2-04":38.49791671930083,"GB2-05":48.6786993822483,"GB2-06":61.4636864955871,"GB2-07":49.874165731160076,"GB2-08":16.772526336204336},"none":{"GB2-01":31.80207016599242,"GB2-02":6.538663385214032,"GB2-03":20.752338623860616,"GB2-04":8.976786369530728,"GB2-05":23.148506841266475,"GB2-06":47.46363982211149,"GB2-07":46.98028811153155,"GB2-08":19.687174292645896}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.870529866662544,"medium":39.892718364619185,"none":25.668683451519147},"reasoning_agg":{"highest":{"max":81.5354966939596,"mean":55.870529866662544,"min":34.876291122201124},"medium":{"max":61.4636864955871,"mean":39.892718364619185,"min":16.772526336204336},"none":{"max":47.46363982211149,"mean":25.668683451519147,"min":6.538663385214032}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.5354966939596,"expected_score":40.80294118407958,"reasoning_variance":30.201846415143397,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.3256306231459547},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.5354966939596,"expected_score":54.02245239721932,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8480774694432256},"medium":{"ceiling_score":61.4636864955871,"expected_score":40.44645612412998,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5537377595107955},"none":{"ceiling_score":47.46363982211149,"expected_score":27.507277919403272,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8385944678841248}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:a01200a91e174a41","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087455999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998544},"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":40.03537606876819,"highest":44.57458500111015,"medium":42.681969609677985,"none":32.849573595516404},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:51:30Z","match_totals_all":{"draws":3795,"losses":5376,"wins":7691},"match_totals_tracks":{"highest":{"draws":1073,"losses":1730,"wins":3216},"medium":{"draws":1011,"losses":1349,"wins":2366},"none":{"draws":1711,"losses":2297,"wins":2109}},"model_slug":"x-ai-grok-4-5","overall":{"max":72.21345579796284,"mean":40.03537606876818,"min":0.8123521302776869},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.80989748047921,"GB2-02":23.34178708038557,"GB2-03":22.04489505829002,"GB2-04":11.622665914117631,"GB2-05":59.47948058010736,"GB2-06":49.4186726324045,"GB2-07":49.66582546513411,"GB2-08":72.21345579796284},"per_game_all":{"GB2-01":59.70144304538371,"GB2-02":15.807174994559716,"GB2-03":17.312679186436046,"GB2-04":11.048438847403403,"GB2-05":51.702367841741655,"GB2-06":45.93148050274359,"GB2-07":52.65975690447897,"GB2-08":66.11966722739837},"per_game_match_totals_all":{"GB2-01":{"draws":620,"losses":341,"wins":1199},"GB2-02":{"draws":1240,"losses":330,"wins":355},"GB2-03":{"draws":515,"losses":997,"wins":463},"GB2-04":{"draws":1268,"losses":502,"wins":256},"GB2-05":{"draws":0,"losses":839,"wins":1314},"GB2-06":{"draws":141,"losses":1164,"wins":1010},"GB2-07":{"draws":0,"losses":893,"wins":1311},"GB2-08":{"draws":11,"losses":310,"wins":1783}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":150,"losses":57,"wins":541},"GB2-02":{"draws":339,"losses":117,"wins":218},"GB2-03":{"draws":229,"losses":284,"wins":208},"GB2-04":{"draws":310,"losses":239,"wins":163},"GB2-05":{"draws":0,"losses":207,"wins":549},"GB2-06":{"draws":39,"losses":383,"wins":414},"GB2-07":{"draws":0,"losses":366,"wins":460},"GB2-08":{"draws":6,"losses":77,"wins":663}},"medium":{"GB2-01":{"draws":48,"losses":71,"wins":453},"GB2-02":{"draws":354,"losses":97,"wins":107},"GB2-03":{"draws":139,"losses":175,"wins":210},"GB2-04":{"draws":422,"losses":125,"wins":43},"GB2-05":{"draws":0,"losses":198,"wins":404},"GB2-06":{"draws":43,"losses":342,"wins":257},"GB2-07":{"draws":0,"losses":265,"wins":361},"GB2-08":{"draws":5,"losses":76,"wins":531}},"none":{"GB2-01":{"draws":422,"losses":213,"wins":205},"GB2-02":{"draws":547,"losses":116,"wins":30},"GB2-03":{"draws":147,"losses":538,"wins":45},"GB2-04":{"draws":536,"losses":138,"wins":50},"GB2-05":{"draws":0,"losses":434,"wins":361},"GB2-06":{"draws":59,"losses":439,"wins":339},"GB2-07":{"draws":0,"losses":262,"wins":490},"GB2-08":{"draws":0,"losses":157,"wins":589}}},"per_game_raw_elo_all":{"GB2-01":1761.8551901524513,"GB2-02":1488.6183906215444,"GB2-03":1327.6820995884332,"GB2-04":1422.2391941152425,"GB2-05":1631.531856584751,"GB2-06":1413.6773246891019,"GB2-07":1596.5299555708607,"GB2-08":2014.7090012946599},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1899.8211845507146,"GB2-02":1548.5856065145229,"GB2-03":1390.116612275499,"GB2-04":1426.5189956617169,"GB2-05":1805.816765420148,"GB2-06":1491.3127767590936,"GB2-07":1535.4695319109408,"GB2-08":2109.60310117524},"medium":{"GB2-01":1886.8966489083784,"GB2-02":1489.389162161585,"GB2-03":1482.9447306550503,"GB2-04":1419.7112388428166,"GB2-05":1701.2525810406935,"GB2-06":1371.3717471075245,"GB2-07":1564.967949789231,"GB2-08":2041.6250737892356},"none":{"GB2-01":1498.8477369982606,"GB2-02":1427.8804031885254,"GB2-03":1109.98495583475,"GB2-04":1420.4873478411937,"GB2-05":1387.5262232934117,"GB2-06":1378.3474502006873,"GB2-07":1689.1523850124108,"GB2-08":1892.898828919504}},"per_game_tracks":{"highest":{"GB2-01":68.80989748047921,"GB2-02":23.34178708038557,"GB2-03":22.04489505829002,"GB2-04":11.622665914117631,"GB2-05":59.47948058010736,"GB2-06":49.4186726324045,"GB2-07":49.66582546513411,"GB2-08":72.21345579796284},"medium":{"GB2-01":67.95662530637259,"GB2-02":15.904018986306227,"GB2-03":29.080790370740434,"GB2-04":10.709259489410597,"GB2-05":54.81351462959405,"GB2-06":44.03121878918735,"GB2-07":51.11219998078813,"GB2-08":67.84812932502449},"none":{"GB2-01":42.33780634929933,"GB2-02":8.175718916987353,"GB2-03":0.8123521302776869,"GB2-04":10.813391138681983,"GB2-05":40.81410831552355,"GB2-06":44.344550086638904,"GB2-07":57.201245267514665,"GB2-08":58.29741655920778}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.57458500111015,"medium":42.681969609677985,"none":32.849573595516404},"reasoning_agg":{"highest":{"max":72.21345579796284,"mean":44.57458500111015,"min":11.622665914117631},"medium":{"max":67.95662530637259,"mean":42.681969609677985,"min":10.709259489410597},"none":{"max":58.29741655920778,"mean":32.849573595516404,"min":0.8123521302776869}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":72.21345579796284,"expected_score":38.78729767454493,"reasoning_variance":11.725011405593747,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2480783942232492},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.21345579796284,"expected_score":37.85320201385381,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.721382987256341},"medium":{"ceiling_score":67.95662530637259,"expected_score":42.28308930377244,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.3988803059055428},"none":{"ceiling_score":58.29741655920778,"expected_score":36.225601706008526,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.376028110492122}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:ef785d3860d1888f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847899999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847900000000004},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.195345875},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214245,"mean_ms":417506.625,"min_ms":32605,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1196482,"mean_ms":748510.375,"min_ms":448704,"run_count":8},"medium":{"attempt_count":8,"max_ms":672648,"mean_ms":296260.625,"min_ms":146516,"run_count":8},"none":{"attempt_count":11,"max_ms":1214245,"mean_ms":207748.875,"min_ms":32605,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":65809,"output_mean":27118.375,"output_min":2294,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":65809,"output_mean":50033.0,"output_min":27276,"run_count":8},"medium":{"attempt_count":8,"output_max":58608,"output_mean":20833.875,"output_min":10904,"run_count":8},"none":{"attempt_count":11,"output_max":54017,"output_mean":10488.25,"output_min":2294,"run_count":8}},"display_name":"GLM-5.3 Flash","economics":{"all":40.02314573229872,"highest":43.28247918871735,"medium":44.20251123077189,"none":32.58444677740693},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:49:09Z","match_totals_all":{"draws":3542,"losses":4980,"wins":6461},"match_totals_tracks":{"highest":{"draws":947,"losses":1588,"wins":2431},"medium":{"draws":1111,"losses":1429,"wins":2455},"none":{"draws":1484,"losses":1963,"wins":1575}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":71.22472163062038,"mean":40.02314573229872,"min":9.174411787307651},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.73770613146097,"GB2-02":30.813599469734264,"GB2-03":46.012622572217694,"GB2-04":55.359072374141114,"GB2-05":59.614078035008156,"GB2-06":26.739166520087537,"GB2-07":58.56416485553249,"GB2-08":16.419423551556587},"per_game_all":{"GB2-01":47.22703234835192,"GB2-02":16.719151934514894,"GB2-03":41.76186381517942,"GB2-04":45.070518112285185,"GB2-05":46.495163995339965,"GB2-06":47.24413351588337,"GB2-07":60.61276179000493,"GB2-08":15.054540346830116},"per_game_match_totals_all":{"GB2-01":{"draws":332,"losses":699,"wins":931},"GB2-02":{"draws":1164,"losses":249,"wins":289},"GB2-03":{"draws":294,"losses":483,"wins":1050},"GB2-04":{"draws":553,"losses":261,"wins":982},"GB2-05":{"draws":0,"losses":946,"wins":1050},"GB2-06":{"draws":127,"losses":960,"wins":807},"GB2-07":{"draws":0,"losses":585,"wins":1305},"GB2-08":{"draws":1072,"losses":797,"wins":47}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":234,"wins":434},"GB2-02":{"draws":293,"losses":56,"wins":211},"GB2-03":{"draws":59,"losses":146,"wins":403},"GB2-04":{"draws":158,"losses":57,"wins":391},"GB2-05":{"draws":0,"losses":178,"wins":460},"GB2-06":{"draws":25,"losses":480,"wins":99},"GB2-07":{"draws":0,"losses":217,"wins":427},"GB2-08":{"draws":406,"losses":220,"wins":6}},"medium":{"GB2-01":{"draws":23,"losses":191,"wins":406},"GB2-02":{"draws":426,"losses":110,"wins":44},"GB2-03":{"draws":77,"losses":121,"wins":407},"GB2-04":{"draws":161,"losses":102,"wins":333},"GB2-05":{"draws":0,"losses":384,"wins":332},"GB2-06":{"draws":44,"losses":108,"wins":450},"GB2-07":{"draws":0,"losses":168,"wins":454},"GB2-08":{"draws":380,"losses":245,"wins":29}},"none":{"GB2-01":{"draws":303,"losses":274,"wins":91},"GB2-02":{"draws":445,"losses":83,"wins":34},"GB2-03":{"draws":158,"losses":216,"wins":240},"GB2-04":{"draws":234,"losses":102,"wins":258},"GB2-05":{"draws":0,"losses":384,"wins":258},"GB2-06":{"draws":58,"losses":372,"wins":258},"GB2-07":{"draws":0,"losses":200,"wins":424},"GB2-08":{"draws":286,"losses":332,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1572.9049693864536,"GB2-02":1495.876722891973,"GB2-03":1650.2525336573372,"GB2-04":1675.810918425101,"GB2-05":1514.8385440163956,"GB2-06":1442.9009539865367,"GB2-07":1758.72934373918,"GB2-08":1219.5092344326667},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1656.3752873979977,"GB2-02":1608.0530059718624,"GB2-03":1706.3349396026067,"GB2-04":1752.4930760475863,"GB2-05":1808.8330911371636,"GB2-06":986.398322870062,"GB2-07":1716.948762165584,"GB2-08":1240.7635594974174},"medium":{"GB2-01":1707.7919949481766,"GB2-02":1443.748263921718,"GB2-03":1738.2359969065992,"GB2-04":1667.2127926366134,"GB2-05":1427.7633315432656,"GB2-06":1976.781431450482,"GB2-07":1812.9074609031113,"GB2-08":1263.311964846756},"none":{"GB2-01":1354.5476258131869,"GB2-02":1435.8288987823382,"GB2-03":1506.1866644628053,"GB2-04":1607.7268865911035,"GB2-05":1307.9192093687577,"GB2-06":1365.5231076390667,"GB2-07":1746.3318081488446,"GB2-08":1154.4521789538267}},"per_game_tracks":{"highest":{"GB2-01":52.73770613146097,"GB2-02":30.813599469734264,"GB2-03":46.012622572217694,"GB2-04":55.359072374141114,"GB2-05":59.614078035008156,"GB2-06":26.739166520087537,"GB2-07":58.56416485553249,"GB2-08":16.419423551556587},"medium":{"GB2-01":56.132214611365995,"GB2-02":10.16944454650276,"GB2-03":48.43055911413532,"GB2-04":43.91689533395091,"GB2-05":42.60960816238914,"GB2-06":71.22472163062038,"GB2-07":63.26923808969485,"GB2-08":17.867408357515774},"none":{"GB2-01":32.81117630222881,"GB2-02":9.174411787307651,"GB2-03":30.842409759185227,"GB2-04":35.93558662876354,"GB2-05":37.261805788622596,"GB2-06":43.768512396942185,"GB2-07":60.004882424787475,"GB2-08":10.876789131417988}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.28247918871735,"medium":44.20251123077189,"none":32.58444677740693},"reasoning_agg":{"highest":{"max":59.614078035008156,"mean":43.28247918871735,"min":16.419423551556587},"medium":{"max":71.22472163062038,"mean":44.20251123077189,"min":10.16944454650276},"none":{"max":60.004882424787475,"mean":32.58444677740693,"min":9.174411787307651}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":71.22472163062038,"expected_score":39.39834156244201,"reasoning_variance":11.618064453364958,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6248041698567093},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.614078035008156,"expected_score":35.664693465029856,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.617785723687497},"medium":{"ceiling_score":71.22472163062038,"expected_score":45.971541306749806,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7690300759779163},"none":{"ceiling_score":60.004882424787475,"expected_score":36.55878991554638,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.974343138139446}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:8d0d4b30b8e6e2f5","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":0.48296144},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558000000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.06816269999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558000000003},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.06816269999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296143999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.03177873833333334,"median":0.025158225,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":0.76268972},"codegen_latency_ms":{"attempt_count":29,"max_ms":579647,"mean_ms":182597.75,"min_ms":15305,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":579647,"mean_ms":375199.125,"min_ms":217884,"run_count":8},"medium":{"attempt_count":11,"max_ms":196176,"mean_ms":145630.0,"min_ms":61522,"run_count":8},"none":{"attempt_count":10,"max_ms":51111,"mean_ms":26964.125,"min_ms":15305,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":74293,"output_mean":22693.125,"output_min":2253,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":74293,"output_mean":46016.5,"output_min":25493,"run_count":8},"medium":{"attempt_count":11,"output_max":25418,"output_mean":18052.125,"output_min":8262,"run_count":8},"none":{"attempt_count":10,"output_max":6651,"output_mean":4010.75,"output_min":2253,"run_count":8}},"display_name":"GLM-5.3 FlashX","economics":{"all":39.923978805004566,"highest":50.03417024363909,"medium":35.33748588460814,"none":34.40028028676646},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:14:20Z","match_totals_all":{"draws":2502,"losses":3517,"wins":4902},"match_totals_tracks":{"highest":{"draws":623,"losses":874,"wins":2142},"medium":{"draws":802,"losses":1392,"wins":1446},"none":{"draws":1077,"losses":1251,"wins":1314}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":71.80470191410039,"mean":39.92397880500456,"min":6.189998604271213},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":36.04049451046269,"GB2-02":35.157770803375534,"GB2-03":57.65479273612162,"GB2-04":54.31653061453346,"GB2-05":63.23160720548759,"GB2-06":71.80470191410039,"GB2-07":62.023539040334306,"GB2-08":20.04392512469712},"per_game_all":{"GB2-01":49.860874571449635,"GB2-02":19.066665720372026,"GB2-03":37.40793597723175,"GB2-04":33.569681655149616,"GB2-05":48.928799011739045,"GB2-06":60.35981641018194,"GB2-07":56.09824667059714,"GB2-08":14.099810423315356},"per_game_match_totals_all":{"GB2-01":{"draws":105,"losses":488,"wins":802},"GB2-02":{"draws":843,"losses":176,"wins":259},"GB2-03":{"draws":152,"losses":446,"wins":719},"GB2-04":{"draws":715,"losses":161,"wins":467},"GB2-05":{"draws":0,"losses":638,"wins":814},"GB2-06":{"draws":67,"losses":431,"wins":870},"GB2-07":{"draws":0,"losses":499,"wins":911},"GB2-08":{"draws":620,"losses":678,"wins":60}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":274,"wins":189},"GB2-02":{"draws":199,"losses":34,"wins":193},"GB2-03":{"draws":6,"losses":71,"wins":362},"GB2-04":{"draws":142,"losses":28,"wins":277},"GB2-05":{"draws":0,"losses":106,"wins":378},"GB2-06":{"draws":29,"losses":69,"wins":358},"GB2-07":{"draws":0,"losses":125,"wins":345},"GB2-08":{"draws":245,"losses":167,"wins":40}},"medium":{"GB2-01":{"draws":6,"losses":101,"wins":357},"GB2-02":{"draws":314,"losses":54,"wins":58},"GB2-03":{"draws":48,"losses":177,"wins":213},"GB2-04":{"draws":260,"losses":71,"wins":117},"GB2-05":{"draws":0,"losses":288,"wins":196},"GB2-06":{"draws":25,"losses":201,"wins":230},"GB2-07":{"draws":0,"losses":203,"wins":267},"GB2-08":{"draws":149,"losses":297,"wins":8}},"none":{"GB2-01":{"draws":97,"losses":113,"wins":256},"GB2-02":{"draws":330,"losses":88,"wins":8},"GB2-03":{"draws":98,"losses":198,"wins":144},"GB2-04":{"draws":313,"losses":62,"wins":73},"GB2-05":{"draws":0,"losses":244,"wins":240},"GB2-06":{"draws":13,"losses":161,"wins":282},"GB2-07":{"draws":0,"losses":171,"wins":299},"GB2-08":{"draws":226,"losses":214,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1612.799845513591,"GB2-02":1514.5603477959096,"GB2-03":1592.808965950775,"GB2-04":1590.0934374699673,"GB2-05":1569.376246019784,"GB2-06":1734.8957546299243,"GB2-07":1666.657026321492,"GB2-08":1204.641925586637},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1403.4621920551526,"GB2-02":1642.6278264500954,"GB2-03":1859.93596721559,"GB2-04":1744.722853963552,"GB2-05":1889.901832570747,"GB2-06":1989.693548083422,"GB2-07":1787.501764998679,"GB2-08":1297.2052640817067},"medium":{"GB2-01":1790.378457292524,"GB2-02":1488.9769609751781,"GB2-03":1505.342246480299,"GB2-04":1528.3450641887473,"GB2-05":1352.5302646962682,"GB2-06":1532.599926145347,"GB2-07":1563.1592986767662,"GB2-08":1104.2148148370181},"none":{"GB2-01":1644.5588871930959,"GB2-02":1412.076255962455,"GB2-03":1413.1486841564356,"GB2-04":1497.2123942576027,"GB2-05":1465.6966407923367,"GB2-06":1682.3937896610037,"GB2-07":1649.3100152890306,"GB2-08":1212.5056978411858}},"per_game_tracks":{"highest":{"GB2-01":36.04049451046269,"GB2-02":35.157770803375534,"GB2-03":57.65479273612162,"GB2-04":54.31653061453346,"GB2-05":63.23160720548759,"GB2-06":71.80470191410039,"GB2-07":62.023539040334306,"GB2-08":20.04392512469712},"medium":{"GB2-01":61.58453663100627,"GB2-02":15.852227753469332,"GB2-03":30.77840720663351,"GB2-04":25.28481449983525,"GB2-05":39.252484206954215,"GB2-06":51.27318907504821,"GB2-07":51.02351770340051,"GB2-08":7.650710000517847},"none":{"GB2-01":51.957592572879925,"GB2-02":6.189998604271213,"GB2-03":23.790607988940142,"GB2-04":21.107699851080135,"GB2-05":44.30230562277533,"GB2-06":58.00155824139722,"GB2-07":55.247683268056605,"GB2-08":14.604796144731097}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.03417024363909,"medium":35.33748588460814,"none":34.40028028676646},"reasoning_agg":{"highest":{"max":71.80470191410039,"mean":50.03417024363909,"min":20.04392512469712},"medium":{"max":61.58453663100627,"mean":35.33748588460814,"min":7.650710000517847},"none":{"max":58.00155824139722,"mean":34.40028028676646,"min":6.189998604271213}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":71.80470191410039,"expected_score":39.53011413149964,"reasoning_variance":15.633889956872629,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.3938646735049218},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":71.80470191410039,"expected_score":44.575413053767065,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.458757189872024},"medium":{"ceiling_score":61.58453663100627,"expected_score":34.61642008559549,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7210657990126492},"none":{"ceiling_score":58.00155824139722,"expected_score":39.39850925513637,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.998228968369908}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:9f1d6d50ef1e21fb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":7.44989},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":7.44989}},"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-2026-10-09":25},"run_count":24,"token_priced_attempt_count":25,"total":10.456239999999998},"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":41.301141927394305,"highest":55.01391177643867,"medium":32.13767808659456,"none":34.061503633321834},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:25:31Z","match_totals_all":{"draws":3086,"losses":4030,"wins":5616},"match_totals_tracks":{"highest":{"draws":562,"losses":864,"wins":2602},"medium":{"draws":1525,"losses":1601,"wins":1539},"none":{"draws":999,"losses":1565,"wins":1475}},"model_slug":"claude-opus-4-8","overall":{"max":74.09452030429955,"mean":39.42952939179347,"min":4.26212192888473},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":53.97873179216162,"GB2-02":49.76497103684088,"GB2-04":40.20435272295193,"GB2-05":43.48502187049682,"GB2-06":74.09452030429955,"GB2-07":64.26101560095042,"GB2-08":59.30876910736942},"per_game_all":{"GB2-01":45.34436725243597,"GB2-02":20.03720580049622,"GB2-04":19.96781228167129,"GB2-05":38.25836500109465,"GB2-06":64.04712125430116,"GB2-07":56.25441513239195,"GB2-08":45.19870676936887},"per_game_match_totals_all":{"GB2-01":{"draws":301,"losses":618,"wins":786},"GB2-02":{"draws":1087,"losses":235,"wins":338},"GB2-03":{"draws":190,"losses":271,"wins":69},"GB2-04":{"draws":1050,"losses":324,"wins":351},"GB2-05":{"draws":0,"losses":1054,"wins":760},"GB2-06":{"draws":96,"losses":451,"wins":1157},"GB2-07":{"draws":0,"losses":624,"wins":1180},"GB2-08":{"draws":362,"losses":453,"wins":975}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":79,"losses":152,"wins":341},"GB2-02":{"draws":210,"losses":10,"wins":318},"GB2-04":{"draws":240,"losses":57,"wins":267},"GB2-05":{"draws":0,"losses":314,"wins":300},"GB2-06":{"draws":32,"losses":70,"wins":446},"GB2-07":{"draws":0,"losses":141,"wins":455},"GB2-08":{"draws":1,"losses":120,"wins":475}},"medium":{"GB2-01":{"draws":91,"losses":287,"wins":198},"GB2-02":{"draws":464,"losses":97,"wins":3},"GB2-03":{"draws":190,"losses":271,"wins":69},"GB2-04":{"draws":412,"losses":132,"wins":43},"GB2-05":{"draws":0,"losses":306,"wins":306},"GB2-06":{"draws":10,"losses":99,"wins":459},"GB2-07":{"draws":0,"losses":192,"wins":428},"GB2-08":{"draws":358,"losses":217,"wins":33}},"none":{"GB2-01":{"draws":131,"losses":179,"wins":247},"GB2-02":{"draws":413,"losses":128,"wins":17},"GB2-04":{"draws":398,"losses":135,"wins":41},"GB2-05":{"draws":0,"losses":434,"wins":154},"GB2-06":{"draws":54,"losses":282,"wins":252},"GB2-07":{"draws":0,"losses":291,"wins":297},"GB2-08":{"draws":3,"losses":116,"wins":467}}},"per_game_raw_elo_all":{"GB2-01":1544.3881925910257,"GB2-02":1522.2847781786077,"GB2-04":1488.7166390674508,"GB2-05":1330.252077277172,"GB2-06":1816.9863214381548,"GB2-07":1669.842039950794,"GB2-08":1688.9222286961442},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1675.173135108868,"GB2-02":1758.8850564195093,"GB2-04":1639.5426486658255,"GB2-05":1447.3813316216426,"GB2-06":2040.6718364229803,"GB2-07":1833.1344955699096,"GB2-08":1908.6478803689276},"medium":{"GB2-01":1406.4187800619684,"GB2-02":1411.2367977180206,"GB2-03":1274.811410363539,"GB2-04":1415.494332666732,"GB2-05":1452.2566069904096,"GB2-06":1982.0447172805973,"GB2-07":1703.7799213962141,"GB2-08":1269.2731567671337},"none":{"GB2-01":1551.5726626022401,"GB2-02":1396.7324803982924,"GB2-04":1411.1129358697954,"GB2-05":1091.1182932194638,"GB2-06":1428.2424106108874,"GB2-07":1472.6117028862577,"GB2-08":1888.845648952371}},"per_game_tracks":{"highest":{"GB2-01":53.97873179216162,"GB2-02":49.76497103684088,"GB2-04":40.20435272295193,"GB2-05":43.48502187049682,"GB2-06":74.09452030429955,"GB2-07":64.26101560095042,"GB2-08":59.30876910736942},"medium":{"GB2-01":36.23568715384475,"GB2-02":6.084524435763052,"GB2-03":13.305352085799695,"GB2-04":10.143471184086746,"GB2-05":43.70257120639077,"GB2-06":71.46113538791244,"GB2-07":57.918466643238204,"GB2-08":18.250216595720833},"none":{"GB2-01":45.81868281130156,"GB2-02":4.26212192888473,"GB2-04":9.5556129379752,"GB2-05":27.58750192639636,"GB2-06":46.58570807069148,"GB2-07":46.583763152987224,"GB2-08":58.037134605016334}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.20770658527888,"medium":32.13767808659456,"none":32.943203503506986},"reasoning_agg":{"highest":{"max":74.09452030429955,"mean":53.20770658527888,"min":40.20435272295193},"medium":{"max":71.46113538791244,"mean":32.13767808659456,"min":6.084524435763052},"none":{"max":58.037134605016334,"mean":32.943203503506986,"min":4.26212192888473}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":74.09452030429955,"expected_score":41.134223876019966,"reasoning_variance":21.070028498684316,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7046944842264935},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.09452030429955,"expected_score":50.35963825792397,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.848068327354909},"medium":{"ceiling_score":71.46113538791244,"expected_score":32.41430062111539,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.2766225345208255},"none":{"ceiling_score":58.037134605016334,"expected_score":37.37315562076788,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.429952117260896}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:25dfa6ac02cd1ccf","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.0866157440000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.9693815250000001}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.183515394},"codegen_latency_ms":{"attempt_count":28,"max_ms":1122981,"mean_ms":579882.5416666666,"min_ms":29109,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":995043,"mean_ms":822481.25,"min_ms":674828,"run_count":8},"medium":{"attempt_count":10,"max_ms":1122981,"mean_ms":860540.0,"min_ms":640692,"run_count":8},"none":{"attempt_count":9,"max_ms":99413,"mean_ms":56626.375,"min_ms":29109,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":69581,"output_mean":33844.916666666664,"output_min":1323,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":57331,"output_mean":47325.375,"output_min":39792,"run_count":8},"medium":{"attempt_count":10,"output_max":69581,"output_mean":50814.0,"output_min":36329,"run_count":8},"none":{"attempt_count":9,"output_max":6014,"output_mean":3395.375,"output_min":1323,"run_count":8}},"display_name":"Hy4 Preview","economics":{"all":40.43525339429776,"highest":46.107081587961446,"medium":43.149181472686415,"none":29.331547809423753},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:25:27Z","match_totals_all":{"draws":3644,"losses":4826,"wins":6139},"match_totals_tracks":{"highest":{"draws":1355,"losses":1245,"wins":2452},"medium":{"draws":725,"losses":1571,"wins":2199},"none":{"draws":1564,"losses":2010,"wins":1488}},"model_slug":"tencent-hy4-preview","overall":{"max":72.61243426259449,"mean":39.05704867035445,"min":2.178257511113724},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":22,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.84808340500449,"GB2-02":48.8567158875765,"GB2-03":42.89765933034412,"GB2-04":27.020654198156805,"GB2-05":56.669645557278415,"GB2-06":70.79317029100042,"GB2-07":57.4771601388487,"GB2-08":20.293563895482087},"per_game_all":{"GB2-01":42.58666455658766,"GB2-03":32.16602799583119,"GB2-04":12.805640505063119,"GB2-05":48.94261362975136,"GB2-06":55.600550911390506,"GB2-07":53.54663663272158,"GB2-08":37.3986395287389},"per_game_match_totals_all":{"GB2-01":{"draws":490,"losses":776,"wins":778},"GB2-02":{"draws":643,"losses":125,"wins":392},"GB2-03":{"draws":568,"losses":537,"wins":712},"GB2-04":{"draws":1042,"losses":480,"wins":274},"GB2-05":{"draws":0,"losses":918,"wins":1168},"GB2-06":{"draws":78,"losses":744,"wins":1092},"GB2-07":{"draws":0,"losses":761,"wins":1113},"GB2-08":{"draws":823,"losses":485,"wins":610}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":340,"losses":149,"wins":201},"GB2-02":{"draws":161,"losses":45,"wins":382},"GB2-03":{"draws":62,"losses":163,"wins":375},"GB2-04":{"draws":311,"losses":117,"wins":182},"GB2-05":{"draws":0,"losses":216,"wins":434},"GB2-06":{"draws":35,"losses":116,"wins":451},"GB2-07":{"draws":0,"losses":227,"wins":399},"GB2-08":{"draws":446,"losses":212,"wins":28}},"medium":{"GB2-01":{"draws":40,"losses":301,"wins":319},"GB2-03":{"draws":345,"losses":197,"wins":63},"GB2-04":{"draws":322,"losses":223,"wins":49},"GB2-05":{"draws":0,"losses":345,"wins":369},"GB2-06":{"draws":18,"losses":287,"wins":391},"GB2-07":{"draws":0,"losses":153,"wins":469},"GB2-08":{"draws":0,"losses":65,"wins":539}},"none":{"GB2-01":{"draws":110,"losses":326,"wins":258},"GB2-02":{"draws":482,"losses":80,"wins":10},"GB2-03":{"draws":161,"losses":177,"wins":274},"GB2-04":{"draws":409,"losses":140,"wins":43},"GB2-05":{"draws":0,"losses":357,"wins":365},"GB2-06":{"draws":25,"losses":341,"wins":250},"GB2-07":{"draws":0,"losses":381,"wins":245},"GB2-08":{"draws":377,"losses":208,"wins":43}}},"per_game_raw_elo_all":{"GB2-01":1502.617198686559,"GB2-03":1523.6498279841956,"GB2-04":1435.3358849677868,"GB2-05":1569.685831276147,"GB2-06":1628.9400989672934,"GB2-07":1614.617628264441,"GB2-08":1567.4575025678107},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1536.8709683459483,"GB2-02":1751.656345504941,"GB2-03":1665.2376572065891,"GB2-04":1541.2825411137171,"GB2-05":1742.8484303489045,"GB2-06":1967.1737923824091,"GB2-07":1694.7795943453723,"GB2-08":1301.0927055599625},"medium":{"GB2-01":1517.9139535431596,"GB2-03":1345.8539233405481,"GB2-04":1356.1283853409593,"GB2-05":1487.652406139761,"GB2-06":1607.2274054533386,"GB2-07":1849.4236682369294,"GB2-08":2115.8161001716016},"none":{"GB2-01":1453.066674170569,"GB2-02":1422.9502585098053,"GB2-03":1559.8579034054494,"GB2-04":1408.5967284486837,"GB2-05":1478.5566573397755,"GB2-06":1312.4190990661327,"GB2-07":1299.6496222110209,"GB2-08":1285.463701971868}},"per_game_tracks":{"highest":{"GB2-01":44.84808340500449,"GB2-02":48.8567158875765,"GB2-03":42.89765933034412,"GB2-04":27.020654198156805,"GB2-05":56.669645557278415,"GB2-06":70.79317029100042,"GB2-07":57.4771601388487,"GB2-08":20.293563895482087},"medium":{"GB2-01":43.59654960270976,"GB2-03":18.69001023427021,"GB2-04":2.178257511113724,"GB2-05":45.28203739361551,"GB2-06":54.62527052186768,"GB2-07":65.05971078263353,"GB2-08":72.61243426259449},"none":{"GB2-01":39.31536066204872,"GB2-02":7.556268320057035,"GB2-03":34.91041442287925,"GB2-04":9.218009805918825,"GB2-05":44.876157938360144,"GB2-06":41.38321192130343,"GB2-07":38.103038976682505,"GB2-08":19.289920428140107}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.107081587961446,"medium":41.732516613678136,"none":29.331547809423753},"reasoning_agg":{"highest":{"max":70.79317029100042,"mean":46.107081587961446,"min":20.293563895482087},"medium":{"max":72.61243426259449,"mean":41.732516613678136,"min":2.178257511113724},"none":{"max":44.876157938360144,"mean":29.331547809423753,"min":7.556268320057035}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":72.61243426259449,"expected_score":39.338630516213435,"reasoning_variance":16.775533778537692,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.2815818458589874},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.79317029100042,"expected_score":39.997728050975155,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.109353536986291},"medium":{"ceiling_score":72.61243426259449,"expected_score":43.310867246159255,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.5783506324811185},"none":{"ceiling_score":44.876157938360144,"expected_score":32.29658542734626,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.965037617922505}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:6d65a4dc2972889b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.189024},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.278232,"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":0.846868},"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":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.1890240000000003}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.20856941666666665,"median":0.124697,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":20,"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":30,"run_count":24,"total":5.005666},"codegen_latency_ms":{"attempt_count":30,"max_ms":1906796,"mean_ms":726982.5833333334,"min_ms":135091,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1906796,"mean_ms":1528927.125,"min_ms":1229561,"run_count":8},"medium":{"attempt_count":10,"max_ms":878124,"mean_ms":297986.875,"min_ms":135091,"run_count":8},"none":{"attempt_count":10,"max_ms":640944,"mean_ms":354033.75,"min_ms":208254,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78760,"output_mean":31343.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":78760,"output_mean":62794.5,"output_min":52930,"run_count":8},"medium":{"attempt_count":10,"output_max":40870,"output_mean":14338.625,"output_min":6298,"run_count":8},"none":{"attempt_count":10,"output_max":30162,"output_mean":16898.125,"output_min":10952,"run_count":8}},"display_name":"Qwen3.8 Max 0902","economics":{"all":38.08455450814023,"highest":51.63653104511338,"medium":30.088895420032898,"none":32.528237059274396},"first_seen_at":"2026-10-13T14:11:15Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[131072],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":31,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[131072],"total_output_tokens":752250,"total_reasoning_output_tokens":630868,"total_visible_output_tokens":121382,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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":"qwen/qwen3.8-max-0902","is_recent_addition":true,"last_measured_at":"2026-10-13T14:11:15Z","match_totals_all":{"draws":2757,"losses":3524,"wins":4397},"match_totals_tracks":{"highest":{"draws":586,"losses":679,"wins":2125},"medium":{"draws":994,"losses":1560,"wins":1092},"none":{"draws":1177,"losses":1285,"wins":1180}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":82.0510440907314,"mean":38.08455450814023,"min":5.598247774124889},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.60997893374414,"GB2-02":13.667906260831323,"GB2-03":41.52518685945299,"GB2-04":67.00643103052995,"GB2-05":82.0510440907314,"GB2-06":57.699948142232174,"GB2-07":64.20660281338498,"GB2-08":27.325150230000055},"per_game_all":{"GB2-01":40.25388083953708,"GB2-02":11.062157922911338,"GB2-03":34.047550682663456,"GB2-04":29.167087891594388,"GB2-05":57.490846062050984,"GB2-06":61.13214004822985,"GB2-07":47.38642215656071,"GB2-08":24.136350461574008},"per_game_match_totals_all":{"GB2-01":{"draws":283,"losses":598,"wins":517},"GB2-02":{"draws":931,"losses":230,"wins":117},"GB2-03":{"draws":238,"losses":429,"wins":652},"GB2-04":{"draws":634,"losses":280,"wins":427},"GB2-05":{"draws":0,"losses":507,"wins":945},"GB2-06":{"draws":92,"losses":401,"wins":875},"GB2-07":{"draws":0,"losses":709,"wins":701},"GB2-08":{"draws":579,"losses":370,"wins":163}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":114,"wins":350},"GB2-02":{"draws":291,"losses":75,"wins":60},"GB2-03":{"draws":77,"losses":101,"wins":262},"GB2-04":{"draws":77,"losses":30,"wins":339},"GB2-05":{"draws":0,"losses":34,"wins":450},"GB2-06":{"draws":45,"losses":147,"wins":264},"GB2-07":{"draws":0,"losses":112,"wins":358},"GB2-08":{"draws":94,"losses":66,"wins":42}},"medium":{"GB2-01":{"draws":88,"losses":303,"wins":75},"GB2-02":{"draws":317,"losses":65,"wins":44},"GB2-03":{"draws":80,"losses":163,"wins":196},"GB2-04":{"draws":287,"losses":101,"wins":59},"GB2-05":{"draws":0,"losses":279,"wins":205},"GB2-06":{"draws":14,"losses":182,"wins":260},"GB2-07":{"draws":0,"losses":306,"wins":164},"GB2-08":{"draws":208,"losses":161,"wins":89}},"none":{"GB2-01":{"draws":193,"losses":181,"wins":92},"GB2-02":{"draws":323,"losses":90,"wins":13},"GB2-03":{"draws":81,"losses":165,"wins":194},"GB2-04":{"draws":270,"losses":149,"wins":29},"GB2-05":{"draws":0,"losses":194,"wins":290},"GB2-06":{"draws":33,"losses":72,"wins":351},"GB2-07":{"draws":0,"losses":291,"wins":179},"GB2-08":{"draws":277,"losses":143,"wins":32}}},"per_game_raw_elo_all":{"GB2-01":1467.2824635201987,"GB2-02":1450.8532794372943,"GB2-03":1548.4737065313948,"GB2-04":1557.2802374486248,"GB2-05":1761.2515138484944,"GB2-06":1752.0900165331307,"GB2-07":1488.9817166309183,"GB2-08":1360.9336022369373},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1760.4697808929523,"GB2-02":1471.59216703534,"GB2-03":1647.1299351125567,"GB2-04":1839.3026092087318,"GB2-05":2311.644959129496,"GB2-06":1675.6790359201966,"GB2-07":1832.0247614532227,"GB2-08":1410.5904421847274},"medium":{"GB2-01":1242.0934243224854,"GB2-02":1466.116427570206,"GB2-03":1501.2718978131015,"GB2-04":1450.920010910167,"GB2-05":1376.09175244791,"GB2-06":1611.2600112535483,"GB2-07":1297.6052061351431,"GB2-08":1356.703538001404},"none":{"GB2-01":1399.2841853451582,"GB2-02":1414.8512437063375,"GB2-03":1497.0192866685259,"GB2-04":1381.6180922269762,"GB2-05":1596.0178299680776,"GB2-06":1969.3310024256468,"GB2-07":1337.3151823043893,"GB2-08":1315.5068265246805}},"per_game_tracks":{"highest":{"GB2-01":59.60997893374414,"GB2-02":13.667906260831323,"GB2-03":41.52518685945299,"GB2-04":67.00643103052995,"GB2-05":82.0510440907314,"GB2-06":57.699948142232174,"GB2-07":64.20660281338498,"GB2-08":27.325150230000055},"medium":{"GB2-01":25.38699924482781,"GB2-02":12.979904122688655,"GB2-03":30.469895652079767,"GB2-04":14.896584870128319,"GB2-05":40.303868103314414,"GB2-06":54.80640518178874,"GB2-07":38.002796606947854,"GB2-08":23.86470957848764},"none":{"GB2-01":35.76466434003929,"GB2-02":6.538663385214032,"GB2-03":30.147569536457613,"GB2-04":5.598247774124889,"GB2-05":50.117625992107136,"GB2-06":70.89006682066862,"GB2-07":39.94986704934931,"GB2-08":21.21919157623432}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.63653104511338,"medium":30.088895420032898,"none":32.528237059274396},"reasoning_agg":{"highest":{"max":82.0510440907314,"mean":51.63653104511338,"min":13.667906260831323},"medium":{"max":54.80640518178874,"mean":30.088895420032898,"min":12.979904122688655},"none":{"max":70.89006682066862,"mean":32.528237059274396,"min":5.598247774124889}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":82.0510440907314,"expected_score":37.377014005689595,"reasoning_variance":21.54763562508048,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7075405024506338},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.0510440907314,"expected_score":46.03689564512377,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.599635399989609},"medium":{"ceiling_score":54.80640518178874,"expected_score":29.068731224017178,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0201641960157204},"none":{"ceiling_score":70.89006682066862,"expected_score":37.02541514792785,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.497178088653456}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:925bbdc6068158b7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0},"medium":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"none":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":79,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":112,"run_count":88,"total":0.0},"codegen_latency_ms":{"attempt_count":112,"max_ms":1487583,"mean_ms":467860.5227272727,"min_ms":38538,"run_count":88},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":31,"max_ms":1487583,"mean_ms":1029047.25,"min_ms":343277,"run_count":28},"medium":{"attempt_count":39,"max_ms":676327,"mean_ms":324151.5,"min_ms":151453,"run_count":30},"none":{"attempt_count":42,"max_ms":287181,"mean_ms":87795.26666666666,"min_ms":38538,"run_count":30}},"codegen_output_tokens":{"attempt_count":112,"output_max":85105,"output_mean":23027.329545454544,"output_min":1660,"run_count":88},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":31,"output_max":85105,"output_mean":50628.67857142857,"output_min":15800,"run_count":28},"medium":{"attempt_count":39,"output_max":33467,"output_mean":16156.733333333334,"output_min":6647,"run_count":30},"none":{"attempt_count":42,"output_max":9871,"output_mean":4136.666666666667,"output_min":1660,"run_count":30}},"display_name":"Ox Alpha","economics":{"all":37.92799965761809,"highest":50.83996243648869,"medium":34.292543504605035,"none":28.651493031760523},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":26,"evaluated_cells":30,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":21,"first_pass_rate":0.7241379310344828,"model_code_failure_rate":0.10344827586206896,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":5,"repaired_rate":0.1724137931034483},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"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":"2026-10-13T14:28:27Z","match_totals_all":{"draws":11514,"losses":17793,"wins":20160},"match_totals_tracks":{"highest":{"draws":1836,"losses":4297,"wins":8985},"medium":{"draws":3785,"losses":6287,"wins":6367},"none":{"draws":5893,"losses":7209,"wins":4808}},"model_slug":"stealth-ox-alpha","overall":{"max":62.690689130890995,"mean":37.45684407313924,"min":7.811446878402371},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":47.3284118061045,"GB2-02":43.23600487375214,"GB2-03":47.63992435699646,"GB2-04":49.038845949848245,"GB2-05":51.641842726380624,"GB2-06":62.690689130890995,"GB2-07":56.6518398007398,"GB2-08":48.49214084719679},"per_game_all":{"GB2-01":44.84347223370589,"GB2-02":21.73713642905298,"GB2-03":34.070319352349166,"GB2-04":31.20810212576781,"GB2-05":47.02563734088982,"GB2-06":45.21934658817255,"GB2-07":45.76201909364956,"GB2-08":33.55796409735691},"per_game_match_totals_all":{"GB2-01":{"draws":850,"losses":2062,"wins":2284},"GB2-02":{"draws":3057,"losses":637,"wins":872},"GB2-03":{"draws":2893,"losses":4197,"wins":4851},"GB2-04":{"draws":2825,"losses":940,"wins":1750},"GB2-05":{"draws":0,"losses":2780,"wins":3222},"GB2-06":{"draws":272,"losses":2661,"wins":2385},"GB2-07":{"draws":0,"losses":3065,"wins":2893},"GB2-08":{"draws":1617,"losses":1451,"wins":1903}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":95,"losses":810,"wins":1019},"GB2-02":{"draws":410,"losses":94,"wins":612},"GB2-03":{"draws":300,"losses":616,"wins":1618},"GB2-04":{"draws":633,"losses":210,"wins":940},"GB2-05":{"draws":0,"losses":796,"wins":1196},"GB2-06":{"draws":171,"losses":576,"wins":1205},"GB2-07":{"draws":0,"losses":718,"wins":1264},"GB2-08":{"draws":227,"losses":477,"wins":1131}},"medium":{"GB2-01":{"draws":271,"losses":382,"wins":657},"GB2-02":{"draws":1270,"losses":241,"wins":205},"GB2-03":{"draws":619,"losses":1704,"wins":2086},"GB2-04":{"draws":992,"losses":318,"wins":492},"GB2-05":{"draws":0,"losses":1026,"wins":970},"GB2-06":{"draws":48,"losses":942,"wins":348},"GB2-07":{"draws":0,"losses":1087,"wins":853},"GB2-08":{"draws":585,"losses":587,"wins":756}},"none":{"GB2-01":{"draws":484,"losses":870,"wins":608},"GB2-02":{"draws":1377,"losses":302,"wins":55},"GB2-03":{"draws":1974,"losses":1877,"wins":1147},"GB2-04":{"draws":1200,"losses":412,"wins":318},"GB2-05":{"draws":0,"losses":958,"wins":1056},"GB2-06":{"draws":53,"losses":1143,"wins":832},"GB2-07":{"draws":0,"losses":1260,"wins":776},"GB2-08":{"draws":805,"losses":387,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1536.8011228152839,"GB2-02":1535.8143541998495,"GB2-03":1548.7741050835436,"GB2-04":1572.4922265416765,"GB2-05":1526.7264388919166,"GB2-06":1397.8230682167257,"GB2-07":1455.8524545802381,"GB2-08":1507.649481043248},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1574.4405666494204,"GB2-02":1706.9216747616229,"GB2-03":1727.804753465441,"GB2-04":1705.3874685402009,"GB2-05":1630.1754902097455,"GB2-06":1786.7880366325953,"GB2-07":1677.947408799031,"GB2-08":1740.2084619995355},"medium":{"GB2-01":1620.0718409294018,"GB2-02":1475.540188979069,"GB2-03":1527.6518531426493,"GB2-04":1538.1934120084231,"GB2-05":1451.0947674943154,"GB2-06":1052.6011565751946,"GB2-07":1388.1520974507782,"GB2-08":1529.3858536412924},"none":{"GB2-01":1415.8909608670292,"GB2-02":1424.9811988588565,"GB2-03":1390.86570864254,"GB2-04":1473.8957990764059,"GB2-05":1498.9090589716889,"GB2-06":1354.080011442387,"GB2-07":1301.4578574909042,"GB2-08":1253.3541274889167}},"per_game_tracks":{"highest":{"GB2-01":47.3284118061045,"GB2-02":43.23600487375214,"GB2-03":47.63992435699646,"GB2-04":49.038845949848245,"GB2-05":51.641842726380624,"GB2-06":62.690689130890995,"GB2-07":56.6518398007398,"GB2-08":48.49214084719679},"medium":{"GB2-01":50.340968519136005,"GB2-02":14.163957535004437,"GB2-03":32.46936097881315,"GB2-04":26.606181348055685,"GB2-05":43.65072646087959,"GB2-06":29.71283376233733,"GB2-07":42.44251661535594,"GB2-08":34.95380281725817},"none":{"GB2-01":36.86103637587717,"GB2-02":7.811446878402371,"GB2-03":22.101672721237897,"GB2-04":17.979279079399493,"GB2-05":45.784342835409255,"GB2-06":43.25451687128932,"GB2-07":38.19170086485294,"GB2-08":17.227948627615753}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.8399624364887,"medium":33.369026419368964,"none":28.16154336356006},"reasoning_agg":{"highest":{"max":62.690689130890995,"mean":50.8399624364887,"min":43.23600487375214},"medium":{"max":50.340968519136005,"mean":33.369026419368964,"min":14.163957535004437},"none":{"max":45.784342835409255,"mean":28.16154336356006,"min":7.811446878402371}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":62.690689130890995,"expected_score":36.241527233120934,"reasoning_variance":22.678419072928637,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2153168400183034},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.690689130890995,"expected_score":44.92727253297913,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.912689903509566},"medium":{"ceiling_score":50.340968519136005,"expected_score":32.09733454923588,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2716918701330826},"none":{"ceiling_score":45.784342835409255,"expected_score":31.699974617147788,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.538431253587728}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:50f9212c2d1a966c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.4542268568195333},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.4708879999999995},"codegen_output_tokens":{"attempt_count":27,"output_max":128921,"output_mean":35057.208333333336,"output_min":6291,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":128921,"output_mean":72806.0,"output_min":45821,"run_count":8},"medium":{"attempt_count":8,"output_max":25498,"output_mean":11826.75,"output_min":6291,"run_count":8},"none":{"attempt_count":9,"output_max":34088,"output_mean":20538.875,"output_min":10484,"run_count":8}},"display_name":"Qwen3.8 2.4T A95B","economics":{"all":37.32082275598246,"highest":48.52975062430238,"medium":28.313285860452435,"none":35.11943178319257},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:22:27Z","match_totals_all":{"draws":4256,"losses":5084,"wins":5853},"match_totals_tracks":{"highest":{"draws":1111,"losses":1136,"wins":2688},"medium":{"draws":1841,"losses":2053,"wins":1293},"none":{"draws":1304,"losses":1895,"wins":1872}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":74.0018663131759,"mean":37.32082275598246,"min":7.340797382270133},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":46.89029865226857,"GB2-02":18.857063452624313,"GB2-03":46.18829388975182,"GB2-04":17.819817383199737,"GB2-05":55.49557323837003,"GB2-06":70.96712843666941,"GB2-07":58.01796362835923,"GB2-08":74.0018663131759},"per_game_all":{"GB2-01":40.59826632153181,"GB2-02":13.220830039816681,"GB2-03":31.569372093324887,"GB2-04":13.377023679428888,"GB2-05":45.63552197596914,"GB2-06":57.70396260158879,"GB2-07":44.87743773549291,"GB2-08":51.58416760070657},"per_game_match_totals_all":{"GB2-01":{"draws":766,"losses":628,"wins":538},"GB2-02":{"draws":1290,"losses":282,"wins":186},"GB2-03":{"draws":460,"losses":676,"wins":781},"GB2-04":{"draws":1178,"losses":446,"wins":230},"GB2-05":{"draws":0,"losses":972,"wins":1036},"GB2-06":{"draws":167,"losses":671,"wins":1080},"GB2-07":{"draws":0,"losses":994,"wins":910},"GB2-08":{"draws":395,"losses":415,"wins":1092}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":206,"losses":193,"wins":289},"GB2-02":{"draws":385,"losses":75,"wins":102},"GB2-03":{"draws":107,"losses":115,"wins":379},"GB2-04":{"draws":349,"losses":143,"wins":104},"GB2-05":{"draws":0,"losses":227,"wins":423},"GB2-06":{"draws":62,"losses":101,"wins":439},"GB2-07":{"draws":0,"losses":221,"wins":405},"GB2-08":{"draws":2,"losses":61,"wins":547}},"medium":{"GB2-01":{"draws":309,"losses":167,"wins":152},"GB2-02":{"draws":449,"losses":120,"wins":23},"GB2-03":{"draws":266,"losses":264,"wins":153},"GB2-04":{"draws":370,"losses":169,"wins":53},"GB2-05":{"draws":0,"losses":354,"wins":368},"GB2-06":{"draws":58,"losses":329,"wins":265},"GB2-07":{"draws":0,"losses":420,"wins":212},"GB2-08":{"draws":389,"losses":230,"wins":67}},"none":{"GB2-01":{"draws":251,"losses":268,"wins":97},"GB2-02":{"draws":456,"losses":87,"wins":61},"GB2-03":{"draws":87,"losses":297,"wins":249},"GB2-04":{"draws":459,"losses":134,"wins":73},"GB2-05":{"draws":0,"losses":391,"wins":245},"GB2-06":{"draws":47,"losses":241,"wins":376},"GB2-07":{"draws":0,"losses":353,"wins":293},"GB2-08":{"draws":4,"losses":124,"wins":478}}},"per_game_raw_elo_all":{"GB2-01":1472.498879303831,"GB2-02":1468.0339325886541,"GB2-03":1515.7778454872835,"GB2-04":1439.5944905526346,"GB2-05":1495.5739871021026,"GB2-06":1675.768409936706,"GB2-07":1437.8116565242435,"GB2-08":1788.3583267648312},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1567.8044554014973,"GB2-02":1512.8921445362712,"GB2-03":1708.652659968783,"GB2-04":1472.7073068342963,"GB2-05":1716.5374980079505,"GB2-06":1971.0466272530196,"GB2-07":1705.8091355540723,"GB2-08":2137.452706407341},"medium":{"GB2-01":1516.5036803075945,"GB2-02":1422.933246891619,"GB2-03":1395.1331594271483,"GB2-04":1394.6055791290173,"GB2-05":1481.9017976584926,"GB2-06":1387.9684421353788,"GB2-07":1229.361719414109,"GB2-08":1315.581681092446},"none":{"GB2-01":1333.1885022024012,"GB2-02":1468.2764063380719,"GB2-03":1443.54771706592,"GB2-04":1451.4705856945907,"GB2-05":1288.2826656398645,"GB2-06":1668.2901604217195,"GB2-07":1378.2641146045494,"GB2-08":1912.0405927947072}},"per_game_tracks":{"highest":{"GB2-01":46.89029865226857,"GB2-02":18.857063452624313,"GB2-03":46.18829388975182,"GB2-04":17.819817383199737,"GB2-05":55.49557323837003,"GB2-06":70.96712843666941,"GB2-07":58.01796362835923,"GB2-08":74.0018663131759},"medium":{"GB2-01":43.50344398227623,"GB2-02":7.554130886426402,"GB2-03":22.42512360547073,"GB2-04":7.340797382270133,"GB2-05":45.02542808204703,"GB2-06":44.77670120393955,"GB2-07":34.65666324956125,"GB2-08":21.22399849162819},"none":{"GB2-01":31.401056330050636,"GB2-02":13.251295780399326,"GB2-03":26.094698784752108,"GB2-04":14.970456272816794,"GB2-05":36.38556460749037,"GB2-06":57.36805816415741,"GB2-07":41.95768632855825,"GB2-08":59.52663799731564}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.52975062430238,"medium":28.313285860452435,"none":35.11943178319257},"reasoning_agg":{"highest":{"max":74.0018663131759,"mean":48.52975062430238,"min":17.819817383199737},"medium":{"max":45.02542808204703,"mean":28.313285860452435,"min":7.340797382270133},"none":{"max":59.52663799731564,"mean":35.11943178319257,"min":13.251295780399326}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.0018663131759,"expected_score":36.409752400673746,"reasoning_variance":20.216464763849945,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9110703553087163},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.0018663131759,"expected_score":43.17922489513286,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.350525729169519},"medium":{"ceiling_score":45.02542808204703,"expected_score":26.374294464514467,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9389913959379683},"none":{"ceiling_score":59.52663799731564,"expected_score":39.67573784237392,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.5563060591813525}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:bbbf1d6020828606","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":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513},"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":7.6379623500000005}},"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":40.92706927415025,"highest":48.40102841272145,"medium":39.946479208022296,"none":26.066595317871844},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:07:29Z","match_totals_all":{"draws":7660,"losses":10640,"wins":12757},"match_totals_tracks":{"highest":{"draws":1595,"losses":2376,"wins":4917},"medium":{"draws":2163,"losses":3020,"wins":4785},"none":{"draws":3902,"losses":5244,"wins":3055}},"model_slug":"google-gemini-3-6-flash","overall":{"max":74.31817745351213,"mean":36.581264113686856,"min":2.491219903975955},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.60292565802856,"GB2-03":41.37657608659191,"GB2-04":29.61809224429166,"GB2-05":71.1560918896744,"GB2-06":74.31817745351213,"GB2-07":46.62779063155177,"GB2-08":31.107544925399658},"per_game_all":{"GB2-01":45.226095363585436,"GB2-03":31.34395437233965,"GB2-04":16.536011661974023,"GB2-05":58.42818418443795,"GB2-06":58.93334813604713,"GB2-07":44.90001476511145,"GB2-08":31.121876435556104},"per_game_match_totals_all":{"GB2-01":{"draws":1134,"losses":1601,"wins":1615},"GB2-02":{"draws":1538,"losses":354,"wins":17},"GB2-03":{"draws":627,"losses":1438,"wins":1600},"GB2-04":{"draws":2486,"losses":934,"wins":790},"GB2-05":{"draws":0,"losses":1600,"wins":3225},"GB2-06":{"draws":291,"losses":1529,"wins":2648},"GB2-07":{"draws":0,"losses":1978,"wins":1873},"GB2-08":{"draws":1584,"losses":1206,"wins":989}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":386,"losses":506,"wins":582},"GB2-03":{"draws":58,"losses":200,"wins":440},"GB2-04":{"draws":572,"losses":288,"wins":558},"GB2-05":{"draws":0,"losses":245,"wins":1271},"GB2-06":{"draws":47,"losses":247,"wins":1178},"GB2-07":{"draws":0,"losses":414,"wins":410},"GB2-08":{"draws":532,"losses":476,"wins":478}},"medium":{"GB2-01":{"draws":443,"losses":233,"wins":706},"GB2-02":{"draws":425,"losses":132,"wins":7},"GB2-03":{"draws":215,"losses":674,"wins":527},"GB2-04":{"draws":863,"losses":333,"wins":123},"GB2-05":{"draws":0,"losses":487,"wins":1125},"GB2-06":{"draws":106,"losses":207,"wins":1175},"GB2-07":{"draws":0,"losses":749,"wins":711},"GB2-08":{"draws":111,"losses":205,"wins":411}},"none":{"GB2-01":{"draws":305,"losses":862,"wins":327},"GB2-02":{"draws":1113,"losses":222,"wins":10},"GB2-03":{"draws":354,"losses":564,"wins":633},"GB2-04":{"draws":1051,"losses":313,"wins":109},"GB2-05":{"draws":0,"losses":868,"wins":829},"GB2-06":{"draws":138,"losses":1075,"wins":295},"GB2-07":{"draws":0,"losses":815,"wins":752},"GB2-08":{"draws":941,"losses":525,"wins":100}}},"per_game_raw_elo_all":{"GB2-01":1542.59672523826,"GB2-03":1512.8037957097895,"GB2-04":1463.1389077991998,"GB2-05":1782.2572385568756,"GB2-06":1703.1382531191812,"GB2-07":1438.2721089498984,"GB2-08":1469.714074650348},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1533.157557625503,"GB2-03":1645.1692381716553,"GB2-04":1560.6416413914683,"GB2-05":2067.489343156485,"GB2-06":2045.6511215447017,"GB2-07":1473.509631428809,"GB2-08":1469.4909005542208},"medium":{"GB2-01":1798.8838038769966,"GB2-02":1382.6380502082109,"GB2-03":1414.3531678890072,"GB2-04":1409.1840440985166,"GB2-05":1842.002799982129,"GB2-06":2022.8567254515706,"GB2-07":1421.1447648096337,"GB2-08":1659.465689176539},"none":{"GB2-01":1295.7488142122806,"GB2-02":1402.2241087548746,"GB2-03":1478.8889810687058,"GB2-04":1419.591037907615,"GB2-05":1437.2795725320127,"GB2-06":1040.9069123612717,"GB2-07":1420.1619306112525,"GB2-08":1280.1856342202839}},"per_game_tracks":{"highest":{"GB2-01":44.60292565802856,"GB2-03":41.37657608659191,"GB2-04":29.61809224429166,"GB2-05":71.1560918896744,"GB2-06":74.31817745351213,"GB2-07":46.62779063155177,"GB2-08":31.107544925399658},"medium":{"GB2-01":62.146055881871305,"GB2-02":2.491219903975955,"GB2-03":23.881901678781755,"GB2-04":9.296810782827844,"GB2-05":61.0942094296873,"GB2-06":73.29430966454532,"GB2-07":44.06022212987501,"GB2-08":43.30710419261388},"none":{"GB2-01":28.92930455085644,"GB2-02":4.952120435072056,"GB2-03":28.77338535164527,"GB2-04":10.693131958802562,"GB2-05":43.03425123395215,"GB2-06":29.187557290083916,"GB2-07":44.01203153390756,"GB2-08":18.950980188654782}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.04223222641736,"medium":38.634964796771364,"none":26.066595317871844},"reasoning_agg":{"highest":{"max":74.31817745351213,"mean":45.04223222641736,"min":29.61809224429166},"medium":{"max":73.29430966454532,"mean":38.634964796771364,"min":2.491219903975955},"none":{"max":44.01203153390756,"mean":26.066595317871844,"min":4.952120435072056}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":74.31817745351213,"expected_score":39.957768370721865,"reasoning_variance":18.975636908545518,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.376504257035009},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.31817745351213,"expected_score":42.122370192984064,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.919862033433297},"medium":{"ceiling_score":73.29430966454532,"expected_score":41.18925214298537,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.5542873462140037},"none":{"ceiling_score":44.01203153390756,"expected_score":27.49402325576096,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4274279378891173}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:c2e28936a24e27ca","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999993}},"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":0.21121388999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.392731284},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":36.22799697817453,"highest":48.18721981396381,"medium":36.72309165814723,"none":23.773679462412566},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:24:55Z","match_totals_all":{"draws":3058,"losses":3687,"wins":4179},"match_totals_tracks":{"highest":{"draws":740,"losses":804,"wins":2097},"medium":{"draws":1137,"losses":1097,"wins":1408},"none":{"draws":1181,"losses":1786,"wins":674}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":73.02673177085074,"mean":36.22799697817453,"min":6.086164517789267},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.33598267418984,"GB2-02":21.57910588339248,"GB2-03":34.094097861833525,"GB2-04":48.343384421716365,"GB2-05":66.94701573372387,"GB2-06":73.02673177085074,"GB2-07":62.843960780009596,"GB2-08":28.327479385994092},"per_game_all":{"GB2-01":47.076980960244136,"GB2-02":17.081694849935097,"GB2-03":29.115340495380295,"GB2-04":20.33393694160763,"GB2-05":48.5544945522898,"GB2-06":58.04985886837219,"GB2-07":50.14901904568728,"GB2-08":19.462650111879856},"per_game_match_totals_all":{"GB2-01":{"draws":436,"losses":370,"wins":590},"GB2-02":{"draws":894,"losses":171,"wins":213},"GB2-03":{"draws":284,"losses":493,"wins":539},"GB2-04":{"draws":659,"losses":349,"wins":336},"GB2-05":{"draws":0,"losses":657,"wins":795},"GB2-06":{"draws":89,"losses":478,"wins":801},"GB2-07":{"draws":0,"losses":636,"wins":774},"GB2-08":{"draws":696,"losses":533,"wins":131}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":162,"wins":283},"GB2-02":{"draws":265,"losses":54,"wins":107},"GB2-03":{"draws":52,"losses":155,"wins":233},"GB2-04":{"draws":139,"losses":47,"wins":262},"GB2-05":{"draws":0,"losses":88,"wins":396},"GB2-06":{"draws":28,"losses":63,"wins":365},"GB2-07":{"draws":0,"losses":120,"wins":350},"GB2-08":{"draws":236,"losses":115,"wins":101}},"medium":{"GB2-01":{"draws":271,"losses":22,"wins":173},"GB2-02":{"draws":282,"losses":40,"wins":104},"GB2-03":{"draws":122,"losses":150,"wins":166},"GB2-04":{"draws":238,"losses":161,"wins":49},"GB2-05":{"draws":0,"losses":227,"wins":257},"GB2-06":{"draws":30,"losses":90,"wins":336},"GB2-07":{"draws":0,"losses":153,"wins":317},"GB2-08":{"draws":194,"losses":254,"wins":6}},"none":{"GB2-01":{"draws":145,"losses":186,"wins":134},"GB2-02":{"draws":347,"losses":77,"wins":2},"GB2-03":{"draws":110,"losses":188,"wins":140},"GB2-04":{"draws":282,"losses":141,"wins":25},"GB2-05":{"draws":0,"losses":342,"wins":142},"GB2-06":{"draws":31,"losses":325,"wins":100},"GB2-07":{"draws":0,"losses":363,"wins":107},"GB2-08":{"draws":266,"losses":164,"wins":24}}},"per_game_raw_elo_all":{"GB2-01":1570.6321371382771,"GB2-02":1498.7621653051756,"GB2-03":1483.4005678893566,"GB2-04":1491.4454217679324,"GB2-05":1560.9880921140323,"GB2-06":1683.469107816998,"GB2-07":1545.3241345750505,"GB2-08":1288.1534946470383},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1619.9963202073284,"GB2-02":1534.5566050627524,"GB2-03":1549.0878269618945,"GB2-04":1700.2040881387097,"GB2-05":1973.164048050215,"GB2-06":2016.899631615466,"GB2-07":1804.2340449520714,"GB2-08":1426.1989789661907},"medium":{"GB2-01":1653.7822537086972,"GB2-02":1545.0312765533972,"GB2-03":1481.7651863556102,"GB2-04":1388.8775673388375,"GB2-05":1509.0878982416848,"GB2-06":1904.8247249233555,"GB2-07":1700.6846673122789,"GB2-08":1152.6570340176809},"none":{"GB2-01":1438.1178374988062,"GB2-02":1416.6986142993778,"GB2-03":1419.3486903505657,"GB2-04":1385.2546098262499,"GB2-05":1200.7123300501971,"GB2-06":1128.6829669121728,"GB2-07":1131.0536914608017,"GB2-08":1285.6044709572432}},"per_game_tracks":{"highest":{"GB2-01":50.33598267418984,"GB2-02":21.57910588339248,"GB2-03":34.094097861833525,"GB2-04":48.343384421716365,"GB2-05":66.94701573372387,"GB2-06":73.02673177085074,"GB2-07":62.843960780009596,"GB2-08":28.327479385994092},"medium":{"GB2-01":52.56651518465793,"GB2-02":22.895201440493523,"GB2-03":28.991386962030532,"GB2-04":6.572261885317254,"GB2-05":46.23855301962679,"GB2-06":67.9926046790569,"GB2-07":57.7666992960893,"GB2-08":10.761510797905595},"none":{"GB2-01":38.32844502188463,"GB2-02":6.770777225919291,"GB2-03":24.260536662276827,"GB2-04":6.086164517789267,"GB2-05":32.47791490351874,"GB2-06":33.13024015520891,"GB2-07":29.83639706096296,"GB2-08":19.298960151739877}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.18721981396381,"medium":36.72309165814723,"none":23.773679462412566},"reasoning_agg":{"highest":{"max":73.02673177085074,"mean":48.18721981396381,"min":21.57910588339248},"medium":{"max":67.9926046790569,"mean":36.72309165814723,"min":6.572261885317254},"none":{"max":38.32844502188463,"mean":23.773679462412566,"min":6.086164517789267}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":73.02673177085074,"expected_score":34.95834855046382,"reasoning_variance":24.41354035155124,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2696484277107132},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.02673177085074,"expected_score":42.50096783052191,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.686251983441899},"medium":{"ceiling_score":67.9926046790569,"expected_score":37.23782687835872,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5147352202114845},"none":{"ceiling_score":38.32844502188463,"expected_score":25.136250942510824,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3625714800982571}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:881f6033db92eb7a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.542855},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566349999999993},"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":37.65707692413114,"highest":50.747101882958816,"medium":34.51527117177814,"none":25.416632241166667},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:08:15Z","match_totals_all":{"draws":4087,"losses":3743,"wins":4855},"match_totals_tracks":{"highest":{"draws":836,"losses":822,"wins":2352},"medium":{"draws":1500,"losses":1474,"wins":1666},"none":{"draws":1751,"losses":1447,"wins":837}},"model_slug":"gpt-5-5","overall":{"max":76.59193289535415,"mean":36.05947119390595,"min":3.8011315261005487},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":62.21868125068563,"GB2-03":26.619039946508146,"GB2-04":3.8011315261005487,"GB2-05":64.5937551677739,"GB2-06":72.32848374000116,"GB2-07":76.59193289535415,"GB2-08":49.076688654288155},"per_game_all":{"GB2-01":51.184329011331805,"GB2-03":20.910032498499394,"GB2-04":7.31809703691173,"GB2-05":56.477516728099,"GB2-07":56.264906943224524,"GB2-08":33.78757932672036},"per_game_match_totals_all":{"GB2-01":{"draws":879,"losses":204,"wins":647},"GB2-02":{"draws":820,"losses":161,"wins":119},"GB2-03":{"draws":519,"losses":687,"wins":394},"GB2-04":{"draws":1046,"losses":517,"wins":162},"GB2-05":{"draws":0,"losses":563,"wins":1183},"GB2-06":{"draws":47,"losses":504,"wins":615},"GB2-07":{"draws":0,"losses":676,"wins":1142},"GB2-08":{"draws":776,"losses":431,"wins":593}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":152,"losses":54,"wins":354},"GB2-03":{"draws":158,"losses":194,"wins":176},"GB2-04":{"draws":332,"losses":199,"wins":41},"GB2-05":{"draws":0,"losses":133,"wins":455},"GB2-06":{"draws":33,"losses":81,"wins":444},"GB2-07":{"draws":0,"losses":72,"wins":530},"GB2-08":{"draws":161,"losses":89,"wins":352}},"medium":{"GB2-01":{"draws":340,"losses":42,"wins":198},"GB2-02":{"draws":353,"losses":72,"wins":119},"GB2-03":{"draws":193,"losses":236,"wins":105},"GB2-04":{"draws":353,"losses":169,"wins":64},"GB2-05":{"draws":0,"losses":151,"wins":427},"GB2-06":{"draws":14,"losses":423,"wins":171},"GB2-07":{"draws":0,"losses":227,"wins":371},"GB2-08":{"draws":247,"losses":154,"wins":211}},"none":{"GB2-01":{"draws":387,"losses":108,"wins":95},"GB2-02":{"draws":467,"losses":89,"wins":0},"GB2-03":{"draws":168,"losses":257,"wins":113},"GB2-04":{"draws":361,"losses":149,"wins":57},"GB2-05":{"draws":0,"losses":279,"wins":301},"GB2-07":{"draws":0,"losses":377,"wins":241},"GB2-08":{"draws":368,"losses":188,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1632.8462440700357,"GB2-03":1375.1437976774268,"GB2-04":1394.4363900071487,"GB2-05":1738.5428279223124,"GB2-07":1670.0560176010424,"GB2-08":1511.2251105973435},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1799.9838622127336,"GB2-03":1450.465614685663,"GB2-04":1368.2239118698933,"GB2-05":1920.4275355422692,"GB2-06":2001.3545169454405,"GB2-07":2084.620225742972,"GB2-08":1749.3111962589824},"medium":{"GB2-01":1621.2624413949195,"GB2-02":1513.443108697363,"GB2-03":1343.1835918763852,"GB2-04":1403.755770819917,"GB2-05":1815.950111473978,"GB2-06":1147.1602890752833,"GB2-07":1609.8222786532076,"GB2-08":1491.43678379007},"none":{"GB2-01":1477.2924286024536,"GB2-02":1412.3624257494537,"GB2-03":1331.7821864702323,"GB2-04":1411.3294873316368,"GB2-05":1479.2508367506903,"GB2-07":1315.7255484069483,"GB2-08":1292.9273517429779}},"per_game_tracks":{"highest":{"GB2-01":62.21868125068563,"GB2-03":26.619039946508146,"GB2-04":3.8011315261005487,"GB2-05":64.5937551677739,"GB2-06":72.32848374000116,"GB2-07":76.59193289535415,"GB2-08":49.076688654288155},"medium":{"GB2-01":50.41957143964456,"GB2-02":18.926289631715694,"GB2-03":18.48761280384323,"GB2-04":8.568491628716313,"GB2-05":59.93166072125737,"GB2-06":33.96019568076337,"GB2-07":53.31150973540945,"GB2-08":32.516837732875125},"none":{"GB2-01":40.91473434366522,"GB2-02":6.225954556262826,"GB2-03":17.623444745146813,"GB2-04":9.58466795591833,"GB2-05":44.90713429526569,"GB2-07":38.891278198909966,"GB2-08":19.769211592997802}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.08098369762063,"medium":34.51527117177814,"none":24.58215871231908},"reasoning_agg":{"highest":{"max":76.59193289535415,"mean":49.08098369762063,"min":3.8011315261005487},"medium":{"max":59.93166072125737,"mean":34.51527117177814,"min":8.568491628716313},"none":{"max":44.90713429526569,"mean":24.58215871231908,"min":6.225954556262826}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":76.59193289535415,"expected_score":37.0657633448054,"reasoning_variance":24.49882498530155,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.0062921508994478},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.59193289535415,"expected_score":44.94535930805217,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.135624389568463},"medium":{"ceiling_score":59.93166072125737,"expected_score":32.608499288088915,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.906771883689224},"none":{"ceiling_score":44.90713429526569,"expected_score":28.201637076186813,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.6194783638677315}}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:3aefb0e11d772bd6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399969999999997},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.582672}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.139997},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.582672},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816},"codegen_latency_ms":{"attempt_count":28,"max_ms":413691,"mean_ms":128683.25,"min_ms":28133,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":413691,"mean_ms":243828.625,"min_ms":115297,"run_count":8},"medium":{"attempt_count":10,"max_ms":159798,"mean_ms":101243.125,"min_ms":39983,"run_count":8},"none":{"attempt_count":9,"max_ms":84315,"mean_ms":40978.0,"min_ms":28133,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":30544,"output_mean":9612.333333333334,"output_min":2170,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":30544,"output_mean":18138.375,"output_min":8542,"run_count":8},"medium":{"attempt_count":10,"output_max":11696,"output_mean":7576.625,"output_min":3317,"run_count":8},"none":{"attempt_count":9,"output_max":6625,"output_mean":3122.0,"output_min":2170,"run_count":8}},"display_name":"Ember-1","economics":{"all":35.59827814078718,"highest":44.90236880712234,"medium":36.314548418081266,"none":25.577917197157937},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[262144],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[262144],"total_output_tokens":230696,"total_reasoning_output_tokens":146257,"total_visible_output_tokens":84439,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:14:18Z","match_totals_all":{"draws":3003,"losses":3794,"wins":4136},"match_totals_tracks":{"highest":{"draws":660,"losses":976,"wins":2014},"medium":{"draws":1067,"losses":1171,"wins":1403},"none":{"draws":1276,"losses":1647,"wins":719}},"model_slug":"fireworks-ember-1","overall":{"max":64.17150231439402,"mean":35.59827814078719,"min":7.581284044833798},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":61.48194984959719,"GB2-02":7.581284044833798,"GB2-03":52.080748327553344,"GB2-04":8.260718095922,"GB2-05":52.24102241845821,"GB2-06":49.71384640367569,"GB2-07":63.687879002544435,"GB2-08":64.17150231439402},"per_game_all":{"GB2-01":48.34261171420999,"GB2-02":8.810334098835924,"GB2-03":34.050616192636745,"GB2-04":12.950985762835197,"GB2-05":40.93085324776555,"GB2-06":49.42407842553654,"GB2-07":52.04588910770597,"GB2-08":38.23085657677152},"per_game_match_totals_all":{"GB2-01":{"draws":434,"losses":355,"wins":609},"GB2-02":{"draws":970,"losses":240,"wins":68},"GB2-03":{"draws":267,"losses":438,"wins":615},"GB2-04":{"draws":820,"losses":349,"wins":174},"GB2-05":{"draws":0,"losses":808,"wins":644},"GB2-06":{"draws":84,"losses":638,"wins":646},"GB2-07":{"draws":0,"losses":598,"wins":812},"GB2-08":{"draws":428,"losses":368,"wins":568}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":101,"wins":357},"GB2-02":{"draws":328,"losses":83,"wins":15},"GB2-03":{"draws":14,"losses":86,"wins":340},"GB2-04":{"draws":284,"losses":131,"wins":33},"GB2-05":{"draws":0,"losses":177,"wins":307},"GB2-06":{"draws":21,"losses":214,"wins":221},"GB2-07":{"draws":0,"losses":115,"wins":355},"GB2-08":{"draws":5,"losses":69,"wins":386}},"medium":{"GB2-01":{"draws":239,"losses":115,"wins":112},"GB2-02":{"draws":323,"losses":76,"wins":27},"GB2-03":{"draws":36,"losses":164,"wins":240},"GB2-04":{"draws":273,"losses":81,"wins":93},"GB2-05":{"draws":0,"losses":253,"wins":231},"GB2-06":{"draws":30,"losses":188,"wins":238},"GB2-07":{"draws":0,"losses":173,"wins":297},"GB2-08":{"draws":166,"losses":121,"wins":165}},"none":{"GB2-01":{"draws":187,"losses":139,"wins":140},"GB2-02":{"draws":319,"losses":81,"wins":26},"GB2-03":{"draws":217,"losses":188,"wins":35},"GB2-04":{"draws":263,"losses":137,"wins":48},"GB2-05":{"draws":0,"losses":378,"wins":106},"GB2-06":{"draws":33,"losses":236,"wins":187},"GB2-07":{"draws":0,"losses":310,"wins":160},"GB2-08":{"draws":257,"losses":178,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1589.802678831841,"GB2-02":1432.9312412655734,"GB2-03":1548.5141513518556,"GB2-04":1436.4191652501759,"GB2-05":1390.1424744083554,"GB2-06":1491.433126076825,"GB2-07":1584.010287535195,"GB2-08":1580.4170082618218},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1788.8245726669736,"GB2-02":1423.1493561343837,"GB2-03":1786.3947857122446,"GB2-04":1401.4618879328664,"GB2-05":1643.6030926533365,"GB2-06":1497.8842383590804,"GB2-07":1821.445529331814,"GB2-08":1984.3716579986562},"medium":{"GB2-01":1488.2313003691904,"GB2-02":1440.566411031945,"GB2-03":1546.8999059686616,"GB2-04":1498.3122835699437,"GB2-05":1442.8091782785623,"GB2-06":1566.0491336984549,"GB2-07":1643.7569479610563,"GB2-08":1497.3136240126123},"none":{"GB2-01":1492.3521634593585,"GB2-02":1435.0779566303913,"GB2-03":1312.2477623746609,"GB2-04":1409.4833242477175,"GB2-05":1084.0151522931676,"GB2-06":1410.3660061729393,"GB2-07":1286.8283853127143,"GB2-08":1259.5657427741967}},"per_game_tracks":{"highest":{"GB2-01":61.48194984959719,"GB2-02":7.581284044833798,"GB2-03":52.080748327553344,"GB2-04":8.260718095922,"GB2-05":52.24102241845821,"GB2-06":49.71384640367569,"GB2-07":63.687879002544435,"GB2-08":64.17150231439402},"medium":{"GB2-01":41.63691385966289,"GB2-02":9.769658982314008,"GB2-03":33.928264671104,"GB2-04":21.255273566047407,"GB2-05":43.28099874397464,"GB2-06":52.77564459263098,"GB2-07":54.97540374784533,"GB2-08":32.894229181070855},"none":{"GB2-01":41.90897143336988,"GB2-02":9.080059269359962,"GB2-03":16.142835579252893,"GB2-04":9.336965626536188,"GB2-05":27.2705385808638,"GB2-06":45.78274428030294,"GB2-07":37.47438457272814,"GB2-08":17.6268382348497}},"provider_color":"#6720FF","provider_company":"Fireworks AI","provider_key":"fireworks","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.90236880712234,"medium":36.314548418081266,"none":25.577917197157937},"reasoning_agg":{"highest":{"max":64.17150231439402,"mean":44.90236880712234,"min":7.581284044833798},"medium":{"max":54.97540374784533,"mean":36.314548418081266,"min":9.769658982314008},"none":{"max":45.78274428030294,"mean":25.577917197157937,"min":9.080059269359962}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":64.17150231439402,"expected_score":34.167982033415555,"reasoning_variance":19.324451609964406,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4302961073716318},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.17150231439402,"expected_score":38.7619800484709,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.14038875865144},"medium":{"ceiling_score":54.97540374784533,"expected_score":35.92405612447831,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.39049229360295357},"none":{"ceiling_score":45.78274428030294,"expected_score":27.817909927297446,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.239992730139509}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:a48cab159a322be4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.164549388465127},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870414}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.13084687320145388,"mean":0.0871504498983802,"median":0.08084431374719805,"min":0.0619993303028941,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.6972035991870416},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.164549388465127}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":32,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.5094276945411561,"mean":0.1819473937669366,"median":0.18692147314407714,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"recorded_attempt_count":14,"run_count":32,"token_priced_attempt_count":32,"total":4.9824165},"codegen_output_tokens":{"attempt_count":32,"output_max":60921,"output_mean":18651.916666666668,"output_min":1790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":60921,"output_mean":31693.5,"output_min":21144,"run_count":8},"medium":{"attempt_count":10,"output_max":28586,"output_mean":21214.875,"output_min":16507,"run_count":8},"none":{"attempt_count":11,"output_max":4623,"output_mean":3047.375,"output_min":1790,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"all":35.24821169677406,"highest":43.91792366487602,"medium":38.247024213675836,"none":23.579687211770327},"first_seen_at":"2026-10-13T14:14:48Z","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":true,"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":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":true,"last_measured_at":"2026-10-13T14:14:48Z","match_totals_all":{"draws":4470,"losses":7089,"wins":6559},"match_totals_tracks":{"highest":{"draws":1020,"losses":1506,"wins":2577},"medium":{"draws":1210,"losses":1645,"wins":2128},"none":{"draws":2240,"losses":3938,"wins":1854}},"model_slug":"google-gemini-3-5-flash","overall":{"max":77.06622146625956,"mean":35.248211696774064,"min":4.179701323537015},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.06622146625956,"GB2-02":26.62875478921695,"GB2-03":40.46376811860384,"GB2-04":11.235105676827715,"GB2-05":45.86961736979906,"GB2-06":67.26865676905828,"GB2-07":47.118099463159105,"GB2-08":35.69316566608365},"per_game_all":{"GB2-01":58.63296075559017,"GB2-02":13.153166316108432,"GB2-03":29.53868804881793,"GB2-04":14.679625906445288,"GB2-05":40.87191004322363,"GB2-06":58.19584388567299,"GB2-07":46.52717469300413,"GB2-08":20.386323925329933},"per_game_match_totals_all":{"GB2-01":{"draws":264,"losses":683,"wins":1395},"GB2-02":{"draws":1296,"losses":278,"wins":200},"GB2-03":{"draws":295,"losses":740,"wins":778},"GB2-04":{"draws":1399,"losses":603,"wins":348},"GB2-05":{"draws":0,"losses":1535,"wins":971},"GB2-06":{"draws":58,"losses":1014,"wins":1318},"GB2-07":{"draws":0,"losses":1320,"wins":1250},"GB2-08":{"draws":1158,"losses":916,"wins":299}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":26,"losses":53,"wins":535},"GB2-02":{"draws":322,"losses":74,"wins":192},"GB2-03":{"draws":98,"losses":162,"wins":346},"GB2-04":{"draws":331,"losses":207,"wins":102},"GB2-05":{"draws":0,"losses":337,"wins":369},"GB2-06":{"draws":17,"losses":155,"wins":430},"GB2-07":{"draws":0,"losses":350,"wins":352},"GB2-08":{"draws":226,"losses":168,"wins":251}},"medium":{"GB2-01":{"draws":14,"losses":179,"wins":423},"GB2-02":{"draws":505,"losses":89,"wins":6},"GB2-03":{"draws":86,"losses":168,"wins":345},"GB2-04":{"draws":339,"losses":128,"wins":143},"GB2-05":{"draws":0,"losses":229,"wins":411},"GB2-06":{"draws":23,"losses":173,"wins":408},"GB2-07":{"draws":0,"losses":321,"wins":389},"GB2-08":{"draws":243,"losses":358,"wins":3}},"none":{"GB2-01":{"draws":224,"losses":451,"wins":437},"GB2-02":{"draws":469,"losses":115,"wins":2},"GB2-03":{"draws":111,"losses":410,"wins":87},"GB2-04":{"draws":729,"losses":268,"wins":103},"GB2-05":{"draws":0,"losses":969,"wins":191},"GB2-06":{"draws":18,"losses":686,"wins":480},"GB2-07":{"draws":0,"losses":649,"wins":509},"GB2-08":{"draws":689,"losses":390,"wins":45}}},"per_game_raw_elo_all":{"GB2-01":1745.670861333689,"GB2-02":1467.495403852003,"GB2-03":1488.9860058558177,"GB2-04":1449.3029828003546,"GB2-05":1388.8215586166407,"GB2-06":1686.7191761792183,"GB2-07":1471.4575965178144,"GB2-08":1302.5371894693365},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2024.879937041524,"GB2-02":1574.7462502190003,"GB2-03":1633.126101890157,"GB2-04":1423.6304503474103,"GB2-05":1500.820059230023,"GB2-06":1888.7074531533792,"GB2-07":1483.5093477178018,"GB2-08":1540.899408995566},"medium":{"GB2-01":1729.5243381908704,"GB2-02":1431.6634582045153,"GB2-03":1631.2627530544792,"GB2-04":1505.3338189426777,"GB2-05":1695.763824799295,"GB2-06":1840.3185785100227,"GB2-07":1542.604385040124,"GB2-08":1102.7847479509874},"none":{"GB2-01":1482.6083087686725,"GB2-02":1396.0765031324934,"GB2-03":1202.5691626228158,"GB2-04":1418.9446791109756,"GB2-05":969.8807918206035,"GB2-06":1331.1314968742531,"GB2-07":1388.2590567955176,"GB2-08":1263.927411461456}},"per_game_tracks":{"highest":{"GB2-01":77.06622146625956,"GB2-02":26.62875478921695,"GB2-03":40.46376811860384,"GB2-04":11.235105676827715,"GB2-05":45.86961736979906,"GB2-06":67.26865676905828,"GB2-07":47.118099463159105,"GB2-08":35.69316566608365},"medium":{"GB2-01":57.56697437993998,"GB2-02":8.65104283557133,"GB2-03":40.32253583287764,"GB2-04":22.19736296368234,"GB2-05":54.568589946395704,"GB2-06":65.09514842563634,"GB2-07":50.01566354057137,"GB2-08":7.558875784731999},"none":{"GB2-01":41.26568642057094,"GB2-02":4.179701323537015,"GB2-03":7.82976019497232,"GB2-04":10.606409078825815,"GB2-05":22.177522813476116,"GB2-06":42.223726462324365,"GB2-07":42.4477610752819,"GB2-08":17.906930325174145}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.91792366487602,"medium":38.247024213675836,"none":23.579687211770327},"reasoning_agg":{"highest":{"max":77.06622146625956,"mean":43.91792366487602,"min":11.235105676827715},"medium":{"max":65.09514842563634,"mean":38.247024213675836,"min":7.558875784731999},"none":{"max":42.4477610752819,"mean":23.579687211770327,"min":4.179701323537015}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":77.06622146625956,"expected_score":33.79611143296387,"reasoning_variance":20.338236453105694,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4521002638101947},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.06622146625956,"expected_score":37.42537228932393,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.49255137555209},"medium":{"ceiling_score":65.09514842563634,"expected_score":38.891640766316456,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6446165526406205},"none":{"ceiling_score":42.4477610752819,"expected_score":25.071321243251212,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.491634031480885}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:f823de08c5bf7106","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405000000001},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616799999999995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616799999999995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.19141049999999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.714719},"codegen_latency_ms":{"attempt_count":27,"max_ms":194716,"mean_ms":65710.04166666667,"min_ms":14709,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":194716,"mean_ms":132597.5,"min_ms":94687,"run_count":8},"medium":{"attempt_count":9,"max_ms":66794,"mean_ms":45688.625,"min_ms":28293,"run_count":8},"none":{"attempt_count":9,"max_ms":26924,"mean_ms":18844.0,"min_ms":14709,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":46299,"output_mean":14240.0,"output_min":2554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":46299,"output_mean":31097.375,"output_min":22420,"run_count":8},"medium":{"attempt_count":9,"output_max":11293,"output_mean":8521.75,"output_min":5500,"run_count":8},"none":{"attempt_count":9,"output_max":3991,"output_mean":3100.875,"output_min":2554,"run_count":8}},"display_name":"Muse Spark 1.2","economics":{"all":35.29208676746872,"highest":40.28559123139038,"medium":36.85029345441817,"none":27.60788152598178},"first_seen_at":"2026-10-13T14:18:46Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":87,"requested_max_output_token_observations":9,"requested_max_output_tokens":[943718],"total_output_tokens":341760,"total_reasoning_output_tokens":238816,"total_visible_output_tokens":102944,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":"meta/muse-spark-1.2","is_recent_addition":true,"last_measured_at":"2026-10-13T14:18:46Z","match_totals_all":{"draws":3176,"losses":5402,"wins":5596},"match_totals_tracks":{"highest":{"draws":615,"losses":1137,"wins":1656},"medium":{"draws":1193,"losses":1579,"wins":2250},"none":{"draws":1368,"losses":2686,"wins":1690}},"model_slug":"meta-muse-spark-1-2","overall":{"max":68.69738521477176,"mean":34.91458873726344,"min":5.733699732325232},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.95357795165837,"GB2-02":12.521461976195827,"GB2-03":32.294255217716746,"GB2-04":18.32632854754115,"GB2-05":51.10257486540925,"GB2-06":32.211894891812896,"GB2-07":62.843960780009596,"GB2-08":48.030675620779185},"per_game_all":{"GB2-01":55.50132762865098,"GB2-02":9.581510576138689,"GB2-03":27.675346059596123,"GB2-04":15.212650791431921,"GB2-05":46.84014413460276,"GB2-07":51.03237015304,"GB2-08":41.20125802882054},"per_game_match_totals_all":{"GB2-01":{"draws":298,"losses":487,"wins":1051},"GB2-02":{"draws":1298,"losses":307,"wins":112},"GB2-03":{"draws":321,"losses":827,"wins":785},"GB2-04":{"draws":1110,"losses":428,"wins":290},"GB2-05":{"draws":0,"losses":976,"wins":1120},"GB2-06":{"draws":23,"losses":910,"wins":241},"GB2-07":{"draws":0,"losses":882,"wins":1046},"GB2-08":{"draws":126,"losses":585,"wins":951}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":87,"wins":377},"GB2-02":{"draws":327,"losses":62,"wins":37},"GB2-03":{"draws":18,"losses":183,"wins":239},"GB2-04":{"draws":247,"losses":106,"wins":93},"GB2-05":{"draws":0,"losses":186,"wins":298},"GB2-06":{"draws":19,"losses":337,"wins":100},"GB2-07":{"draws":0,"losses":120,"wins":350},"GB2-08":{"draws":2,"losses":56,"wins":162}},"medium":{"GB2-01":{"draws":30,"losses":105,"wins":551},"GB2-02":{"draws":493,"losses":113,"wins":53},"GB2-03":{"draws":190,"losses":288,"wins":259},"GB2-04":{"draws":370,"losses":193,"wins":105},"GB2-05":{"draws":0,"losses":403,"wins":409},"GB2-07":{"draws":0,"losses":281,"wins":447},"GB2-08":{"draws":110,"losses":196,"wins":426}},"none":{"GB2-01":{"draws":266,"losses":295,"wins":123},"GB2-02":{"draws":478,"losses":132,"wins":22},"GB2-03":{"draws":113,"losses":356,"wins":287},"GB2-04":{"draws":493,"losses":129,"wins":92},"GB2-05":{"draws":0,"losses":387,"wins":413},"GB2-06":{"draws":4,"losses":573,"wins":141},"GB2-07":{"draws":0,"losses":481,"wins":249},"GB2-08":{"draws":14,"losses":333,"wins":363}}},"per_game_raw_elo_all":{"GB2-01":1698.2359335391384,"GB2-02":1439.0689568877217,"GB2-03":1464.4019944292986,"GB2-04":1453.2756982282924,"GB2-05":1522.5695406142506,"GB2-07":1563.3398419979364,"GB2-08":1626.6728914143362},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1841.4094131242455,"GB2-02":1462.467732871657,"GB2-03":1525.3415944480328,"GB2-04":1476.482411475147,"GB2-05":1618.0905104558058,"GB2-06":1108.2378216408058,"GB2-07":1804.2340449520714,"GB2-08":1733.022402493203},"medium":{"GB2-01":1898.1169583583412,"GB2-02":1446.2945184221544,"GB2-03":1446.3449687357227,"GB2-04":1418.069748793636,"GB2-05":1468.3382918744169,"GB2-07":1637.8144408732494,"GB2-08":1652.5865955425},"none":{"GB2-01":1355.1814291348285,"GB2-02":1408.4446193693539,"GB2-03":1421.5194201041404,"GB2-04":1465.2749344160943,"GB2-05":1481.2798195125295,"GB2-06":1008.9942423464886,"GB2-07":1247.9710401684886,"GB2-08":1494.4096762073063}},"per_game_tracks":{"highest":{"GB2-01":64.95357795165837,"GB2-02":12.521461976195827,"GB2-03":32.294255217716746,"GB2-04":18.32632854754115,"GB2-05":51.10257486540925,"GB2-06":32.211894891812896,"GB2-07":62.843960780009596,"GB2-08":48.030675620779185},"medium":{"GB2-01":68.69738521477176,"GB2-02":10.489370019895008,"GB2-03":26.306716115867626,"GB2-04":10.489018432495715,"GB2-05":44.42018397735029,"GB2-07":54.684029110522054,"GB2-08":42.86535131002472},"none":{"GB2-01":32.853019719522784,"GB2-02":5.733699732325232,"GB2-03":24.425066845204004,"GB2-04":16.822605394258904,"GB2-05":44.99767356104875,"GB2-06":27.75411923124852,"GB2-07":35.569120568588346,"GB2-08":32.70774715565769}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.28559123139038,"medium":36.85029345441817,"none":27.60788152598178},"reasoning_agg":{"highest":{"max":64.95357795165837,"mean":40.28559123139038,"min":12.521461976195827},"medium":{"max":68.69738521477176,"mean":36.85029345441817,"min":10.489018432495715},"none":{"max":44.99767356104875,"mean":27.60788152598178,"min":5.733699732325232}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":68.69738521477176,"expected_score":34.6736729979394,"reasoning_variance":12.677709705408596,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.24091573932404486},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.95357795165837,"expected_score":32.79273064799517,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.492860583395206},"medium":{"ceiling_score":68.69738521477176,"expected_score":37.1997606529642,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.34946719854603003},"none":{"ceiling_score":44.99767356104875,"expected_score":29.70630249717959,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.0984209711978075}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:61da32d02ed7ac9c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659585999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.45275},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":34.115975169252835,"highest":37.18869675705275,"medium":33.24937014329755,"none":31.90985860740821},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04"],"performance_rejections":1}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-13T14:22:35Z","match_totals_all":{"draws":4380,"losses":5533,"wins":5456},"match_totals_tracks":{"highest":{"draws":1315,"losses":1827,"wins":2052},"medium":{"draws":1476,"losses":1876,"wins":1785},"none":{"draws":1589,"losses":1830,"wins":1619}},"model_slug":"qwen-qwen3-8-max","overall":{"max":78.98043978937257,"mean":33.75628043428054,"min":5.3567255369337525},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":30.40041722071838,"GB2-02":16.68336868664601,"GB2-03":31.79352618450069,"GB2-04":36.77272122712215,"GB2-05":42.68482078101782,"GB2-06":48.96894436429389,"GB2-07":65.85527557382461,"GB2-08":24.35050001829848},"per_game_all":{"GB2-01":30.306851991525786,"GB2-02":9.894946578068375,"GB2-03":26.890028795052064,"GB2-04":17.698035424054762,"GB2-05":58.69502403920745,"GB2-06":41.543132152922176,"GB2-07":55.22684380425299,"GB2-08":32.672938568939095},"per_game_match_totals_all":{"GB2-01":{"draws":510,"losses":1018,"wins":400},"GB2-02":{"draws":1375,"losses":286,"wins":107},"GB2-03":{"draws":451,"losses":743,"wins":667},"GB2-04":{"draws":1077,"losses":394,"wins":346},"GB2-05":{"draws":0,"losses":673,"wins":1348},"GB2-06":{"draws":160,"losses":1134,"wins":735},"GB2-07":{"draws":0,"losses":723,"wins":1184},"GB2-08":{"draws":807,"losses":562,"wins":669}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":122,"losses":345,"wins":147},"GB2-02":{"draws":433,"losses":72,"wins":84},"GB2-03":{"draws":56,"losses":260,"wins":305},"GB2-04":{"draws":252,"losses":91,"wins":262},"GB2-05":{"draws":0,"losses":381,"wins":337},"GB2-06":{"draws":66,"losses":320,"wins":315},"GB2-07":{"draws":0,"losses":149,"wins":489},"GB2-08":{"draws":386,"losses":209,"wins":113}},"medium":{"GB2-01":{"draws":236,"losses":284,"wins":168},"GB2-02":{"draws":496,"losses":103,"wins":7},"GB2-03":{"draws":153,"losses":219,"wins":245},"GB2-04":{"draws":416,"losses":162,"wins":26},"GB2-05":{"draws":0,"losses":234,"wins":420},"GB2-06":{"draws":56,"losses":334,"wins":318},"GB2-07":{"draws":0,"losses":372,"wins":258},"GB2-08":{"draws":119,"losses":168,"wins":343}},"none":{"GB2-01":{"draws":152,"losses":389,"wins":85},"GB2-02":{"draws":446,"losses":111,"wins":16},"GB2-03":{"draws":242,"losses":264,"wins":117},"GB2-04":{"draws":409,"losses":141,"wins":58},"GB2-05":{"draws":0,"losses":58,"wins":591},"GB2-06":{"draws":38,"losses":480,"wins":102},"GB2-07":{"draws":0,"losses":202,"wins":437},"GB2-08":{"draws":302,"losses":185,"wins":213}}},"per_game_raw_elo_all":{"GB2-01":1316.6145608476743,"GB2-02":1441.563562340829,"GB2-03":1454.0409073520648,"GB2-04":1471.7996473955598,"GB2-05":1788.237113264456,"GB2-06":1315.9794074790982,"GB2-07":1648.8850000492114,"GB2-08":1493.8676276169217},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1318.0317957889745,"GB2-02":1495.5919276396278,"GB2-03":1518.7352235588573,"GB2-04":1613.9661779034468,"GB2-05":1429.4488445121474,"GB2-06":1481.3004642436897,"GB2-07":1865.6489974347394,"GB2-08":1364.2683962144238},"medium":{"GB2-01":1409.1008466793244,"GB2-02":1423.6544395250955,"GB2-03":1504.0278859132563,"GB2-04":1384.0612427967133,"GB2-05":1692.4297044634782,"GB2-06":1468.2297661423522,"GB2-07":1327.3473396765514,"GB2-08":1655.7711323396177},"none":{"GB2-01":1222.711040074724,"GB2-02":1405.444319857764,"GB2-03":1339.3596125840802,"GB2-04":1417.3715214865183,"GB2-05":2242.8327908177425,"GB2-06":998.407992051253,"GB2-07":1753.6586630363438,"GB2-08":1461.5633542967234}},"per_game_tracks":{"highest":{"GB2-01":30.40041722071838,"GB2-02":16.68336868664601,"GB2-03":31.79352618450069,"GB2-04":36.77272122712215,"GB2-05":42.68482078101782,"GB2-06":48.96894436429389,"GB2-07":65.85527557382461,"GB2-08":24.35050001829848},"medium":{"GB2-01":36.412756015506105,"GB2-02":7.644745510625364,"GB2-03":30.67878541623252,"GB2-04":5.926048764420103,"GB2-05":54.41981154723199,"GB2-06":48.38184099421155,"GB2-07":39.4611210558374,"GB2-08":43.06985184231534},"none":{"GB2-01":24.107382738352868,"GB2-02":5.3567255369337525,"GB2-03":18.197774784422993,"GB2-04":10.395336280622036,"GB2-05":78.98043978937257,"GB2-06":27.278611100261084,"GB2-07":60.364134783096944,"GB2-08":30.598463846203455}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.10961255213587,"medium":33.24937014329755,"none":31.90985860740821},"reasoning_agg":{"highest":{"max":65.85527557382461,"mean":36.10961255213587,"min":16.68336868664601},"medium":{"max":54.41981154723199,"mean":33.24937014329755,"min":5.926048764420103},"none":{"max":78.98043978937257,"mean":31.90985860740821,"min":5.3567255369337525}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":78.98043978937257,"expected_score":32.05132382209893,"reasoning_variance":4.199753944727661,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.7049566121816113},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.85527557382461,"expected_score":29.669764481303357,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.4398480708325145},"medium":{"ceiling_score":54.41981154723199,"expected_score":32.19961551357082,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0497546297267277},"none":{"ceiling_score":78.98043978937257,"expected_score":34.2845914714226,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3747328640143905}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:f253398d34d2d321","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.715746},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.7157459999999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.27696257500000004,"median":0.2537256,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":6.6471018},"codegen_latency_ms":{"attempt_count":35,"max_ms":754602,"mean_ms":294629.0833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":415982,"mean_ms":310768.0,"min_ms":108461,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":41670,"output_mean":16512.916666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":41670,"output_mean":28939.0,"output_min":14510,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":32.67968528069537,"highest":32.54472710848051,"medium":32.61841961492942,"none":36.80830187030274},"first_seen_at":"2026-10-13T14:28:07Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[262144],"finish_reason_observations":35,"finish_reasons":["length","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":10,"provider_post_attempts":13,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[262144],"total_output_tokens":396310,"total_reasoning_output_tokens":285325,"total_visible_output_tokens":110985,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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}}},"id":"moonshotai/kimi-k3","is_recent_addition":true,"last_measured_at":"2026-10-13T14:28:07Z","match_totals_all":{"draws":4181,"losses":5528,"wins":5673},"match_totals_tracks":{"highest":{"draws":641,"losses":1063,"wins":1232},"medium":{"draws":1924,"losses":2215,"wins":2009},"none":{"draws":1616,"losses":2250,"wins":2432}},"model_slug":"moonshotai-kimi-k3","overall":{"max":87.12932672073447,"mean":33.63431565067845,"min":0.9459761627087111},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":0.9459761627087111,"GB2-02":7.465665999089938,"GB2-03":47.70157595948544,"GB2-04":21.87971778856413,"GB2-05":51.35258834635519,"GB2-07":87.12932672073447,"GB2-08":11.338238782425684},"per_game_all":{"GB2-01":32.41859913016822,"GB2-02":6.7417905733492525,"GB2-03":37.524679793871506,"GB2-04":18.017202007772614,"GB2-05":48.34978045613459,"GB2-07":49.34155757704871,"GB2-08":36.36418742652267},"per_game_match_totals_all":{"GB2-01":{"draws":602,"losses":826,"wins":615},"GB2-02":{"draws":1376,"losses":340,"wins":62},"GB2-03":{"draws":351,"losses":586,"wins":974},"GB2-04":{"draws":1111,"losses":474,"wins":408},"GB2-05":{"draws":0,"losses":959,"wins":1258},"GB2-06":{"draws":133,"losses":782,"wins":765},"GB2-07":{"draws":0,"losses":1133,"wins":847},"GB2-08":{"draws":608,"losses":428,"wins":744}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":437,"wins":21},"GB2-02":{"draws":303,"losses":96,"wins":27},"GB2-03":{"draws":31,"losses":95,"wins":314},"GB2-04":{"draws":227,"losses":101,"wins":118},"GB2-05":{"draws":0,"losses":184,"wins":300},"GB2-07":{"draws":0,"losses":28,"wins":442},"GB2-08":{"draws":72,"losses":122,"wins":10}},"medium":{"GB2-01":{"draws":131,"losses":196,"wins":403},"GB2-02":{"draws":514,"losses":122,"wins":18},"GB2-03":{"draws":148,"losses":185,"wins":370},"GB2-04":{"draws":529,"losses":137,"wins":113},"GB2-05":{"draws":0,"losses":403,"wins":459},"GB2-06":{"draws":66,"losses":364,"wins":414},"GB2-07":{"draws":0,"losses":557,"wins":191},"GB2-08":{"draws":536,"losses":251,"wins":41}},"none":{"GB2-01":{"draws":463,"losses":193,"wins":191},"GB2-02":{"draws":559,"losses":122,"wins":17},"GB2-03":{"draws":172,"losses":306,"wins":290},"GB2-04":{"draws":355,"losses":236,"wins":177},"GB2-05":{"draws":0,"losses":372,"wins":499},"GB2-06":{"draws":67,"losses":418,"wins":351},"GB2-07":{"draws":0,"losses":548,"wins":214},"GB2-08":{"draws":0,"losses":55,"wins":693}}},"per_game_raw_elo_all":{"GB2-01":1348.6012492564016,"GB2-02":1416.4679124619267,"GB2-03":1594.3492260527037,"GB2-04":1474.1784444216119,"GB2-05":1556.400454158146,"GB2-07":1528.8561758515468,"GB2-08":1551.348738705613},"per_game_raw_elo_tracks":{"highest":{"GB2-01":871.8846169267093,"GB2-02":1422.2291637965075,"GB2-03":1728.618154177076,"GB2-04":1502.9663612060021,"GB2-05":1623.6933065319547,"GB2-07":2299.527528827355,"GB2-08":1161.6379959157248},"medium":{"GB2-01":1673.2350063259569,"GB2-02":1406.7846849861246,"GB2-03":1600.3331735818863,"GB2-04":1468.466479912271,"GB2-05":1498.449885965948,"GB2-06":1523.6725670873232,"GB2-07":1131.4732731634492,"GB2-08":1294.175657475712},"none":{"GB2-01":1500.6841245165388,"GB2-02":1420.3898886031477,"GB2-03":1454.0963503991488,"GB2-04":1451.1024921465626,"GB2-05":1547.0581699765357,"GB2-06":1417.0122374199682,"GB2-07":1155.5677255638352,"GB2-08":2198.232562725402}},"per_game_tracks":{"highest":{"GB2-01":0.9459761627087111,"GB2-02":7.465665999089938,"GB2-03":47.70157595948544,"GB2-04":21.87971778856413,"GB2-05":51.35258834635519,"GB2-07":87.12932672073447,"GB2-08":11.338238782425684},"medium":{"GB2-01":53.85077738002195,"GB2-02":5.525136411862301,"GB2-03":37.97823232844275,"GB2-04":17.25081959733668,"GB2-05":45.76385316561556,"GB2-06":50.87219422777494,"GB2-07":29.856970106081786,"GB2-08":19.84937370229941},"none":{"GB2-01":42.459043847773984,"GB2-02":7.2345693090955185,"GB2-03":26.894231093686333,"GB2-04":14.921068637417031,"GB2-05":47.93289985643302,"GB2-06":46.08127651884328,"GB2-07":31.038375904329865,"GB2-08":77.90494979484292}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.476225466803182,"medium":32.61841961492942,"none":36.80830187030274},"reasoning_agg":{"highest":{"max":87.12932672073447,"mean":31.476225466803182,"min":0.9459761627087111},"medium":{"max":53.85077738002195,"mean":32.61841961492942,"min":5.525136411862301},"none":{"max":77.90494979484292,"mean":36.80830187030274,"min":7.2345693090955185}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":87.12932672073447,"expected_score":32.40823734655056,"reasoning_variance":5.33207640349956,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2260783041278955},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":87.12932672073447,"expected_score":26.858253319376466,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.617972147426716},"medium":{"ceiling_score":53.85077738002195,"expected_score":31.603597870014532,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0148217449148902},"none":{"ceiling_score":77.90494979484292,"expected_score":41.737511484084436,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.929209613781694}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:b25498cf4a1e2d4f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.43048093750000005,"median":0.4308725,"min":0.32672249999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887695},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.266665,"mean":0.20888499999999996,"median":0.20905875000000002,"min":0.14104,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":8},"run_count":16,"token_priced_attempt_count":16,"total":3.3421600000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709264999999999},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":17},"run_count":16,"token_priced_attempt_count":17,"total":4.096070000000001}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-10-09":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203784999999998},"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":33.36809668526938,"highest":32.477823585594216,"medium":35.194127808307975,"none":32.43233866190596},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:18:58Z","match_totals_all":{"draws":4642,"losses":6356,"wins":6077},"match_totals_tracks":{"highest":{"draws":1732,"losses":2399,"wins":2193},"medium":{"draws":1527,"losses":2227,"wins":2405},"none":{"draws":1383,"losses":1730,"wins":1479}},"model_slug":"claude-opus-4-5","overall":{"max":56.955297872023515,"mean":33.368096685269386,"min":7.455089612287103},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.955297872023515,"GB2-02":7.601277441344102,"GB2-03":25.255157481091793,"GB2-04":8.81043514144306,"GB2-05":45.40839947049673,"GB2-06":50.800846413248195,"GB2-07":45.218568039915276,"GB2-08":19.772606825191033},"per_game_all":{"GB2-01":46.957748263147096,"GB2-02":7.967632754746746,"GB2-03":23.60279054111793,"GB2-04":12.720089036864481,"GB2-05":43.8570225767034,"GB2-06":47.79414082612167,"GB2-07":41.09190667807431,"GB2-08":42.95344280537944},"per_game_match_totals_all":{"GB2-01":{"draws":611,"losses":610,"wins":926},"GB2-02":{"draws":1587,"losses":327,"wins":60},"GB2-03":{"draws":622,"losses":795,"wins":580},"GB2-04":{"draws":1198,"losses":485,"wins":236},"GB2-05":{"draws":0,"losses":1149,"wins":1165},"GB2-06":{"draws":150,"losses":1063,"wins":1047},"GB2-07":{"draws":0,"losses":1311,"wins":985},"GB2-08":{"draws":474,"losses":616,"wins":1078}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":99,"losses":181,"wins":451},"GB2-02":{"draws":569,"losses":114,"wins":15},"GB2-03":{"draws":149,"losses":315,"wins":278},"GB2-04":{"draws":435,"losses":252,"wins":96},"GB2-05":{"draws":0,"losses":420,"wins":454},"GB2-06":{"draws":64,"losses":362,"wins":408},"GB2-07":{"draws":0,"losses":430,"wins":408},"GB2-08":{"draws":416,"losses":325,"wins":83}},"medium":{"GB2-01":{"draws":224,"losses":242,"wins":366},"GB2-02":{"draws":574,"losses":119,"wins":19},"GB2-03":{"draws":253,"losses":271,"wins":195},"GB2-04":{"draws":407,"losses":121,"wins":46},"GB2-05":{"draws":0,"losses":434,"wins":418},"GB2-06":{"draws":61,"losses":391,"wins":398},"GB2-07":{"draws":0,"losses":477,"wins":377},"GB2-08":{"draws":8,"losses":172,"wins":586}},"none":{"GB2-01":{"draws":288,"losses":187,"wins":109},"GB2-02":{"draws":444,"losses":94,"wins":26},"GB2-03":{"draws":220,"losses":209,"wins":107},"GB2-04":{"draws":356,"losses":112,"wins":94},"GB2-05":{"draws":0,"losses":295,"wins":293},"GB2-06":{"draws":25,"losses":310,"wins":241},"GB2-07":{"draws":0,"losses":404,"wins":200},"GB2-08":{"draws":50,"losses":119,"wins":409}}},"per_game_raw_elo_all":{"GB2-01":1568.8261163982054,"GB2-02":1426.2242664593502,"GB2-03":1410.6707137623434,"GB2-04":1434.6982568810529,"GB2-05":1455.717858472807,"GB2-06":1455.145781510939,"GB2-07":1360.606772302063,"GB2-08":1653.9583797883795},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1720.2592583393875,"GB2-02":1423.3084815560126,"GB2-03":1432.471224869853,"GB2-04":1405.5590125686078,"GB2-05":1490.4841772340455,"GB2-06":1522.0841487756747,"GB2-07":1444.7689170137573,"GB2-08":1292.980223203668},"medium":{"GB2-01":1578.4385654213108,"GB2-02":1422.1449874031446,"GB2-03":1428.2976390570486,"GB2-04":1425.8259461755654,"GB2-05":1425.9574533765096,"GB2-06":1473.621325458597,"GB2-07":1393.8599261095817,"GB2-08":1859.6401021760207},"none":{"GB2-01":1407.7805254339185,"GB2-02":1433.2193304188934,"GB2-03":1371.243277360128,"GB2-04":1472.709811898986,"GB2-05":1450.7119448078652,"GB2-06":1369.7318702985458,"GB2-07":1243.1914737828506,"GB2-08":1809.2548139854493}},"per_game_tracks":{"highest":{"GB2-01":56.955297872023515,"GB2-02":7.601277441344102,"GB2-03":25.255157481091793,"GB2-04":8.81043514144306,"GB2-05":45.40839947049673,"GB2-06":50.800846413248195,"GB2-07":45.218568039915276,"GB2-08":19.772606825191033},"medium":{"GB2-01":47.592357931409914,"GB2-02":7.455089612287103,"GB2-03":24.938821080343548,"GB2-04":11.52967847785475,"GB2-05":42.52902448943396,"GB2-06":48.62401647864434,"GB2-07":42.72238443558533,"GB2-08":56.16164996090485},"none":{"GB2-01":36.32558898600786,"GB2-02":8.846531210609033,"GB2-03":20.614393061918452,"GB2-04":17.820153491295635,"GB2-05":43.63364377017951,"GB2-06":43.957559586472485,"GB2-07":35.33476755872231,"GB2-08":52.92607163004242}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.477823585594216,"medium":35.194127808307975,"none":32.43233866190596},"reasoning_agg":{"highest":{"max":56.955297872023515,"mean":32.477823585594216,"min":7.601277441344102},"medium":{"max":56.16164996090485,"mean":35.194127808307975,"min":7.455089612287103},"none":{"max":52.92607163004242,"mean":32.43233866190596,"min":8.846531210609033}},"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":56.955297872023515,"expected_score":31.643703000499475,"reasoning_variance":2.761789146402016,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.724393684769911},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.955297872023515,"expected_score":24.4229288577206,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.054894727873616},"medium":{"ceiling_score":56.16164996090485,"expected_score":34.269485384059344,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9246424242486313},"none":{"ceiling_score":52.92607163004242,"expected_score":36.23869475971848,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.806356097812518}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:4805358587e278d4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688899999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.02545105}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688899999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.025451049999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.00625249375,"median":0.0043227375,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16,"boardgame-list-prices-2026-10-09":11},"run_count":24,"token_priced_attempt_count":27,"total":0.15005985},"codegen_latency_ms":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":26534,"output_mean":10296.416666666666,"output_min":1575,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":26534,"output_mean":21543.25,"output_min":15583,"run_count":8},"medium":{"attempt_count":8,"output_max":6895,"output_mean":5735.5,"output_min":3866,"run_count":8},"none":{"attempt_count":11,"output_max":9509,"output_mean":3610.5,"output_min":1575,"run_count":8}},"display_name":"GPT-6 Luna","economics":{"all":33.203839035600126,"highest":40.601367367230864,"medium":29.26427823082131,"none":29.745871508748184},"first_seen_at":"2026-10-13T14:11:15Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"requested_max_output_token_observations":27,"requested_max_output_tokens":[65536,128000],"total_output_tokens":247114,"total_reasoning_output_tokens":163396,"total_visible_output_tokens":83718,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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":true,"last_measured_at":"2026-10-13T14:11:15Z","match_totals_all":{"draws":2807,"losses":4183,"wins":3680},"match_totals_tracks":{"highest":{"draws":544,"losses":1335,"wins":1762},"medium":{"draws":1157,"losses":1509,"wins":975},"none":{"draws":1106,"losses":1339,"wins":943}},"model_slug":"gpt-6-luna","overall":{"max":76.14194061589478,"mean":33.20383903560012,"min":8.273940991761664},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.88980502878725,"GB2-02":27.19575849669799,"GB2-03":25.00210664549612,"GB2-04":33.45523399223698,"GB2-05":47.04367147253586,"GB2-06":76.14194061589478,"GB2-07":38.5269968260462,"GB2-08":49.555425860151736},"per_game_all":{"GB2-01":33.85662831839048,"GB2-02":14.7348377050356,"GB2-03":24.9362618245756,"GB2-04":21.859662895563705,"GB2-05":42.71957226266543,"GB2-06":59.14075612617355,"GB2-07":40.65226792041428,"GB2-08":27.73072523198232},"per_game_match_totals_all":{"GB2-01":{"draws":433,"losses":654,"wins":311},"GB2-02":{"draws":953,"losses":173,"wins":152},"GB2-03":{"draws":194,"losses":621,"wins":504},"GB2-04":{"draws":770,"losses":262,"wins":309},"GB2-05":{"draws":0,"losses":772,"wins":680},"GB2-06":{"draws":70,"losses":468,"wins":830},"GB2-07":{"draws":0,"losses":854,"wins":556},"GB2-08":{"draws":387,"losses":379,"wins":338}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":331,"wins":134},"GB2-02":{"draws":249,"losses":39,"wins":138},"GB2-03":{"draws":22,"losses":228,"wins":190},"GB2-04":{"draws":212,"losses":62,"wins":173},"GB2-05":{"draws":0,"losses":220,"wins":264},"GB2-06":{"draws":25,"losses":49,"wins":382},"GB2-07":{"draws":0,"losses":302,"wins":168},"GB2-08":{"draws":35,"losses":104,"wins":313}},"medium":{"GB2-01":{"draws":176,"losses":203,"wins":87},"GB2-02":{"draws":354,"losses":65,"wins":7},"GB2-03":{"draws":89,"losses":184,"wins":166},"GB2-04":{"draws":267,"losses":91,"wins":90},"GB2-05":{"draws":0,"losses":240,"wins":244},"GB2-06":{"draws":24,"losses":300,"wins":132},"GB2-07":{"draws":0,"losses":227,"wins":243},"GB2-08":{"draws":247,"losses":199,"wins":6}},"none":{"GB2-01":{"draws":256,"losses":120,"wins":90},"GB2-02":{"draws":350,"losses":69,"wins":7},"GB2-03":{"draws":83,"losses":209,"wins":148},"GB2-04":{"draws":291,"losses":109,"wins":46},"GB2-05":{"draws":0,"losses":312,"wins":172},"GB2-06":{"draws":21,"losses":119,"wins":316},"GB2-07":{"draws":0,"losses":325,"wins":145},"GB2-08":{"draws":105,"losses":76,"wins":19}}},"per_game_raw_elo_all":{"GB2-01":1370.3831144828846,"GB2-02":1480.083766540239,"GB2-03":1428.2638735038618,"GB2-04":1502.8168890423706,"GB2-05":1430.227624377453,"GB2-06":1707.7557827756154,"GB2-07":1351.6404584956533,"GB2-08":1416.906164218977},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1280.003488124223,"GB2-02":1579.258975406618,"GB2-03":1429.1325974628828,"GB2-04":1589.2404416550423,"GB2-05":1527.130583347011,"GB2-06":2086.2536098262817,"GB2-07":1308.2961281249172,"GB2-08":1756.7662196329818},"medium":{"GB2-01":1370.6993479241735,"GB2-02":1432.3301814620297,"GB2-03":1449.502323786936,"GB2-04":1486.6633878956277,"GB2-05":1475.8738999812201,"GB2-06":1222.6495096512635,"GB2-07":1501.1209366877342,"GB2-08":1221.3771035685938},"none":{"GB2-01":1460.4465074002576,"GB2-02":1428.6621427520695,"GB2-03":1406.156699261766,"GB2-04":1432.5468375764417,"GB2-05":1287.6783898041272,"GB2-06":1814.364228849301,"GB2-07":1245.5043106743087,"GB2-08":1272.575169455355}},"per_game_tracks":{"highest":{"GB2-01":27.88980502878725,"GB2-02":27.19575849669799,"GB2-03":25.00210664549612,"GB2-04":33.45523399223698,"GB2-05":47.04367147253586,"GB2-06":76.14194061589478,"GB2-07":38.5269968260462,"GB2-08":49.555425860151736},"medium":{"GB2-01":33.87750591147706,"GB2-02":8.734813626647146,"GB2-03":26.546027436536026,"GB2-04":19.69232464870036,"GB2-05":44.756445299058306,"GB2-06":37.35098440998295,"GB2-07":47.98163572369295,"GB2-08":15.174488790475689},"none":{"GB2-01":39.80257401490712,"GB2-02":8.273940991761664,"GB2-03":23.260651391694648,"GB2-04":12.431430045753785,"GB2-05":36.35860001640212,"GB2-06":63.9293433526429,"GB2-07":35.448171211503684,"GB2-08":18.462261045319536}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.601367367230864,"medium":29.26427823082131,"none":29.745871508748184},"reasoning_agg":{"highest":{"max":76.14194061589478,"mean":40.601367367230864,"min":25.00210664549612},"medium":{"max":47.98163572369295,"mean":29.26427823082131,"min":8.734813626647146},"none":{"max":63.9293433526429,"mean":29.745871508748184,"min":8.273940991761664}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":76.14194061589478,"expected_score":31.54961479160557,"reasoning_variance":11.337089136409553,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6542242439945483},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.14194061589478,"expected_score":33.87762748026412,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.723739886966747},"medium":{"ceiling_score":47.98163572369295,"expected_score":27.084607394429856,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.1796708363914554},"none":{"ceiling_score":63.9293433526429,"expected_score":33.68660950012274,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.940737991374558}}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:aa95c9efa1088490","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.642066},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.6420659999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.6014779999999997},"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":32.098115810242405,"highest":48.09516041508297,"medium":28.457950651271478,"none":19.741236364372764},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:14:01Z","match_totals_all":{"draws":2711,"losses":4629,"wins":3584},"match_totals_tracks":{"highest":{"draws":477,"losses":1022,"wins":2143},"medium":{"draws":1112,"losses":1580,"wins":949},"none":{"draws":1122,"losses":2027,"wins":492}},"model_slug":"gemini-3-1-pro-preview","overall":{"max":70.4684198770467,"mean":32.098115810242405,"min":7.1184831697286635},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.711928251850715,"GB2-02":7.1184831697286635,"GB2-03":37.702326361202815,"GB2-04":58.55549878435876,"GB2-05":70.4684198770467,"GB2-06":27.513103357794606,"GB2-07":62.513110717087315,"GB2-08":62.17841280159423},"per_game_all":{"GB2-01":41.89959689841661,"GB2-02":7.734227438231973,"GB2-03":29.21559822566583,"GB2-04":27.87605703318657,"GB2-05":38.73716789843318,"GB2-06":28.375122625959758,"GB2-07":50.27094947978126,"GB2-08":32.67620688226407},"per_game_match_totals_all":{"GB2-01":{"draws":258,"losses":578,"wins":562},"GB2-02":{"draws":1032,"losses":223,"wins":23},"GB2-03":{"draws":250,"losses":515,"wins":555},"GB2-04":{"draws":624,"losses":285,"wins":433},"GB2-05":{"draws":0,"losses":882,"wins":570},"GB2-06":{"draws":25,"losses":1094,"wins":249},"GB2-07":{"draws":0,"losses":633,"wins":777},"GB2-08":{"draws":522,"losses":419,"wins":415}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":111,"wins":337},"GB2-02":{"draws":338,"losses":80,"wins":8},"GB2-03":{"draws":28,"losses":146,"wins":266},"GB2-04":{"draws":90,"losses":43,"wins":315},"GB2-05":{"draws":0,"losses":73,"wins":411},"GB2-06":{"draws":3,"losses":374,"wins":79},"GB2-07":{"draws":0,"losses":122,"wins":348},"GB2-08":{"draws":0,"losses":73,"wins":379}},"medium":{"GB2-01":{"draws":162,"losses":228,"wins":76},"GB2-02":{"draws":343,"losses":70,"wins":13},"GB2-03":{"draws":78,"losses":117,"wins":245},"GB2-04":{"draws":250,"losses":121,"wins":76},"GB2-05":{"draws":0,"losses":400,"wins":84},"GB2-06":{"draws":19,"losses":324,"wins":113},"GB2-07":{"draws":0,"losses":146,"wins":324},"GB2-08":{"draws":260,"losses":174,"wins":18}},"none":{"GB2-01":{"draws":78,"losses":239,"wins":149},"GB2-02":{"draws":351,"losses":73,"wins":2},"GB2-03":{"draws":144,"losses":252,"wins":44},"GB2-04":{"draws":284,"losses":121,"wins":42},"GB2-05":{"draws":0,"losses":409,"wins":75},"GB2-06":{"draws":3,"losses":396,"wins":57},"GB2-07":{"draws":0,"losses":365,"wins":105},"GB2-08":{"draws":262,"losses":172,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1492.2101671364844,"GB2-02":1424.3666171409013,"GB2-03":1484.723318732301,"GB2-04":1547.6579883686982,"GB2-05":1340.9820386548831,"GB2-06":1022.8196576069017,"GB2-07":1547.8108728700481,"GB2-08":1493.918522663166},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1746.866984037531,"GB2-02":1419.4659707554472,"GB2-03":1596.6930068865047,"GB2-04":1776.316527582046,"GB2-05":2052.0786299443403,"GB2-06":1003.6284994806208,"GB2-07":1797.4864472133718,"GB2-08":1953.334736860278},"medium":{"GB2-01":1331.528876003338,"GB2-02":1433.246398203615,"GB2-03":1606.1811296322312,"GB2-04":1448.291760618508,"GB2-05":1003.384280460897,"GB2-06":1152.1913320719761,"GB2-07":1721.4719760661653,"GB2-08":1264.007663993181},"none":{"GB2-01":1398.2346413685846,"GB2-02":1420.387482463642,"GB2-03":1251.295819678167,"GB2-04":1418.3656769055403,"GB2-05":967.483205559412,"GB2-06":912.6391412681082,"GB2-07":1124.474195330608,"GB2-08":1264.4131671360385}},"per_game_tracks":{"highest":{"GB2-01":58.711928251850715,"GB2-02":7.1184831697286635,"GB2-03":37.702326361202815,"GB2-04":58.55549878435876,"GB2-05":70.4684198770467,"GB2-06":27.513103357794606,"GB2-07":62.513110717087315,"GB2-08":62.17841280159423},"medium":{"GB2-01":31.291488536338935,"GB2-02":8.849932156523607,"GB2-03":38.42147740633826,"GB2-04":14.543948786613328,"GB2-05":23.672548458698238,"GB2-06":34.18617766546588,"GB2-07":58.78594832004392,"GB2-08":17.91208388014966},"none":{"GB2-01":35.69537390706017,"GB2-02":7.234266988443652,"GB2-03":11.522990909456405,"GB2-04":10.52872352858762,"GB2-05":22.070535359554604,"GB2-06":23.42608685461879,"GB2-07":29.51378940221255,"GB2-08":17.938123965048323}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.09516041508297,"medium":28.457950651271478,"none":19.741236364372764},"reasoning_agg":{"highest":{"max":70.4684198770467,"mean":48.09516041508297,"min":7.1184831697286635},"medium":{"max":58.78594832004392,"mean":28.457950651271478,"min":8.849932156523607},"none":{"max":35.69537390706017,"mean":19.741236364372764,"min":7.234266988443652}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":70.4684198770467,"expected_score":29.071145554967405,"reasoning_variance":28.35392405071021,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.0269702552749997},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.4684198770467,"expected_score":41.364493361627275,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.730667053455697},"medium":{"ceiling_score":58.78594832004392,"expected_score":26.00252254813217,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.455428103139308},"none":{"ceiling_score":35.69537390706017,"expected_score":19.846420755142777,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.10518439077001318}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:8583d72c67ca4ec4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.52499},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337000000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":31.989240103037687,"highest":38.6037534696035,"medium":28.933609844719363,"none":28.43035699479019},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T10:48:58Z","match_totals_all":{"draws":4646,"losses":6846,"wins":5754},"match_totals_tracks":{"highest":{"draws":1172,"losses":1914,"wins":2449},"medium":{"draws":1808,"losses":2430,"wins":1646},"none":{"draws":1666,"losses":2502,"wins":1659}},"model_slug":"claude-sonnet-5","overall":{"max":59.02156848043256,"mean":31.989240103037684,"min":6.297211927160863},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.49422167953298,"GB2-02":6.297211927160863,"GB2-03":30.525609054103473,"GB2-04":24.32556912176672,"GB2-05":47.585184944103766,"GB2-06":33.440681234262165,"GB2-07":57.13998131546543,"GB2-08":59.02156848043256},"per_game_all":{"GB2-01":43.33032023993136,"GB2-02":7.292565661365469,"GB2-03":26.469257264459355,"GB2-04":16.68242884272561,"GB2-05":39.064563541845466,"GB2-06":39.77318484593857,"GB2-07":46.80250417472205,"GB2-08":36.499096253313596},"per_game_match_totals_all":{"GB2-01":{"draws":354,"losses":938,"wins":983},"GB2-02":{"draws":1623,"losses":317,"wins":36},"GB2-03":{"draws":606,"losses":825,"wins":727},"GB2-04":{"draws":1225,"losses":449,"wins":349},"GB2-05":{"draws":0,"losses":1313,"wins":925},"GB2-06":{"draws":102,"losses":1275,"wins":797},"GB2-07":{"draws":0,"losses":1122,"wins":1098},"GB2-08":{"draws":736,"losses":607,"wins":839}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":80,"losses":251,"wins":429},"GB2-02":{"draws":516,"losses":96,"wins":8},"GB2-03":{"draws":185,"losses":230,"wins":266},"GB2-04":{"draws":355,"losses":131,"wins":178},"GB2-05":{"draws":0,"losses":344,"wins":392},"GB2-06":{"draws":30,"losses":481,"wins":179},"GB2-07":{"draws":0,"losses":250,"wins":452},"GB2-08":{"draws":6,"losses":131,"wins":545}},"medium":{"GB2-01":{"draws":147,"losses":339,"wins":265},"GB2-02":{"draws":561,"losses":99,"wins":14},"GB2-03":{"draws":212,"losses":340,"wins":184},"GB2-04":{"draws":428,"losses":174,"wins":99},"GB2-05":{"draws":0,"losses":434,"wins":348},"GB2-06":{"draws":32,"losses":405,"wins":263},"GB2-07":{"draws":0,"losses":393,"wins":385},"GB2-08":{"draws":428,"losses":246,"wins":88}},"none":{"GB2-01":{"draws":127,"losses":348,"wins":289},"GB2-02":{"draws":546,"losses":122,"wins":14},"GB2-03":{"draws":209,"losses":255,"wins":277},"GB2-04":{"draws":442,"losses":144,"wins":72},"GB2-05":{"draws":0,"losses":535,"wins":185},"GB2-06":{"draws":40,"losses":389,"wins":355},"GB2-07":{"draws":0,"losses":479,"wins":261},"GB2-08":{"draws":302,"losses":230,"wins":206}}},"per_game_raw_elo_all":{"GB2-01":1513.8813705143405,"GB2-02":1420.8514757078271,"GB2-03":1448.489456155301,"GB2-04":1464.2301772863677,"GB2-05":1348.3189671249731,"GB2-06":1276.5750230320912,"GB2-07":1477.072866987549,"GB2-08":1553.4495749154728},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1622.3931705050736,"GB2-02":1412.929555960795,"GB2-03":1502.0069528485612,"GB2-04":1521.1956626880526,"GB2-05":1539.265887180241,"GB2-06":1135.5943249954853,"GB2-07":1687.902923245168,"GB2-08":1904.1755156548058},"medium":{"GB2-01":1452.243034608304,"GB2-02":1430.9595755982837,"GB2-03":1368.88962657777,"GB2-04":1444.172588570827,"GB2-05":1393.5767682618534,"GB2-06":1281.7873834530963,"GB2-07":1464.238900945592,"GB2-08":1326.9398166213205},"none":{"GB2-01":1467.0079064296442,"GB2-02":1418.6652955644022,"GB2-03":1474.571789039572,"GB2-04":1427.3222806002236,"GB2-05":1112.1142459328253,"GB2-06":1412.3433606476917,"GB2-07":1279.0767767718871,"GB2-08":1429.2333924702912}},"per_game_tracks":{"highest":{"GB2-01":50.49422167953298,"GB2-02":6.297211927160863,"GB2-03":30.525609054103473,"GB2-04":24.32556912176672,"GB2-05":47.585184944103766,"GB2-06":33.440681234262165,"GB2-07":57.13998131546543,"GB2-08":59.02156848043256},"medium":{"GB2-01":39.26098433941535,"GB2-02":8.562603138764649,"GB2-03":20.43599840310367,"GB2-04":13.991273608443064,"GB2-05":41.08410168822895,"GB2-06":40.00731116004438,"GB2-07":46.17322563190511,"GB2-08":21.953380787849774},"none":{"GB2-01":40.23575470084577,"GB2-02":7.017881918170894,"GB2-03":28.44616433617091,"GB2-04":11.730443797967041,"GB2-05":28.524403993203673,"GB2-06":45.87156214350917,"GB2-07":37.09430557679562,"GB2-08":28.522339491658453}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.6037534696035,"medium":28.933609844719363,"none":28.43035699479019},"reasoning_agg":{"highest":{"max":59.02156848043256,"mean":38.6037534696035,"min":6.297211927160863},"medium":{"max":46.17322563190511,"mean":28.933609844719363,"min":8.562603138764649},"none":{"max":45.87156214350917,"mean":28.43035699479019,"min":7.017881918170894}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":59.02156848043256,"expected_score":29.691899186910646,"reasoning_variance":10.173396474813305,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.2973409161270375},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.02156848043256,"expected_score":30.961350082173876,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.642403387429621},"medium":{"ceiling_score":46.17322563190511,"expected_score":26.79953545532049,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.1340743893988723},"none":{"ceiling_score":45.87156214350917,"expected_score":31.314812023237586,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.8844550284473947}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:3f7b3092f4efde2e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.9135725942490001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.37262013029400004},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.37262013029400004},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100005},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249}},"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":1.4885651789639998},"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":32.831272834545075,"highest":33.11379050696251,"medium":36.769114677016624,"none":27.089206289630113},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:50:44Z","match_totals_all":{"draws":3775,"losses":5419,"wins":4826},"match_totals_tracks":{"highest":{"draws":1524,"losses":1885,"wins":1700},"medium":{"draws":1050,"losses":1910,"wins":2193},"none":{"draws":1201,"losses":1624,"wins":933}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":69.48167429506533,"mean":31.697417395442688,"min":4.179886727000819},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":24.272263732971634,"GB2-02":9.642228435086778,"GB2-03":24.197187433363542,"GB2-04":15.658850608372518,"GB2-05":41.75388930701683,"GB2-06":69.48167429506533,"GB2-07":61.994228713961625,"GB2-08":17.91000152986184},"per_game_all":{"GB2-01":33.97934146480676,"GB2-03":18.866173913065523,"GB2-04":13.412952429474473,"GB2-05":40.74328290961872,"GB2-07":57.170006664430765,"GB2-08":32.8158796258742},"per_game_match_totals_all":{"GB2-01":{"draws":278,"losses":1004,"wins":626},"GB2-02":{"draws":893,"losses":234,"wins":49},"GB2-03":{"draws":628,"losses":853,"wins":423},"GB2-04":{"draws":1158,"losses":465,"wins":248},"GB2-05":{"draws":0,"losses":1137,"wins":920},"GB2-06":{"draws":49,"losses":486,"wins":773},"GB2-07":{"draws":0,"losses":704,"wins":1244},"GB2-08":{"draws":769,"losses":536,"wins":543}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":49,"losses":428,"wins":133},"GB2-02":{"draws":447,"losses":111,"wins":40},"GB2-03":{"draws":249,"losses":256,"wins":181},"GB2-04":{"draws":358,"losses":163,"wins":100},"GB2-05":{"draws":0,"losses":387,"wins":315},"GB2-06":{"draws":34,"losses":130,"wins":458},"GB2-07":{"draws":0,"losses":184,"wins":444},"GB2-08":{"draws":387,"losses":226,"wins":29}},"medium":{"GB2-01":{"draws":51,"losses":240,"wins":393},"GB2-02":{"draws":446,"losses":123,"wins":9},"GB2-03":{"draws":148,"losses":363,"wins":99},"GB2-04":{"draws":388,"losses":179,"wins":87},"GB2-05":{"draws":0,"losses":355,"wins":358},"GB2-06":{"draws":15,"losses":356,"wins":315},"GB2-07":{"draws":0,"losses":195,"wins":429},"GB2-08":{"draws":2,"losses":99,"wins":503}},"none":{"GB2-01":{"draws":178,"losses":336,"wins":100},"GB2-03":{"draws":231,"losses":234,"wins":143},"GB2-04":{"draws":412,"losses":123,"wins":61},"GB2-05":{"draws":0,"losses":395,"wins":247},"GB2-07":{"draws":0,"losses":325,"wins":371},"GB2-08":{"draws":380,"losses":211,"wins":11}}},"per_game_raw_elo_all":{"GB2-01":1372.2418536786179,"GB2-03":1348.1781396773733,"GB2-04":1439.8622729838737,"GB2-05":1385.9390276558252,"GB2-07":1688.5152821336405,"GB2-08":1496.093543855525},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1225.2084967554429,"GB2-02":1439.5522041889265,"GB2-03":1418.5128919966007,"GB2-04":1456.6012932363894,"GB2-05":1408.5866926395286,"GB2-06":1937.9759217900867,"GB2-07":1786.9039888030027,"GB2-08":1263.9752370794622},"medium":{"GB2-01":1611.7008191121097,"GB2-02":1396.0779787399188,"GB2-03":1252.7490799458374,"GB2-04":1432.7626614777498,"GB2-05":1463.9383235107,"GB2-06":1444.8522017575624,"GB2-07":1756.973003692774,"GB2-08":1981.8398500949936},"none":{"GB2-01":1279.816245168301,"GB2-03":1373.2724470896817,"GB2-04":1430.222864237482,"GB2-05":1285.2920668172471,"GB2-07":1521.668853905145,"GB2-08":1242.4655443921197}},"per_game_tracks":{"highest":{"GB2-01":24.272263732971634,"GB2-02":9.642228435086778,"GB2-03":24.197187433363542,"GB2-04":15.658850608372518,"GB2-05":41.75388930701683,"GB2-06":69.48167429506533,"GB2-07":61.994228713961625,"GB2-08":17.91000152986184},"medium":{"GB2-01":49.78831733048226,"GB2-02":4.179886727000819,"GB2-03":11.633140584830254,"GB2-04":12.460387445864328,"GB2-05":44.22384425844677,"GB2-06":47.33177873064948,"GB2-07":60.52664444315517,"GB2-08":64.00891789570392},"none":{"GB2-01":27.877443330966383,"GB2-03":20.768193721002774,"GB2-04":12.119619234186569,"GB2-05":36.252115163392574,"GB2-07":48.98914683617549,"GB2-08":16.52871945205685}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.11379050696251,"medium":36.769114677016624,"none":25.209347002348938},"reasoning_agg":{"highest":{"max":69.48167429506533,"mean":33.11379050696251,"min":9.642228435086778},"medium":{"max":64.00891789570392,"mean":36.769114677016624,"min":4.179886727000819},"none":{"max":48.98914683617549,"mean":25.209347002348938,"min":12.119619234186569}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":69.48167429506533,"expected_score":31.24654853302297,"reasoning_variance":11.559767674667686,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.4508688624197177},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":69.48167429506533,"expected_score":25.831288923598567,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.282501583363942},"medium":{"ceiling_score":64.00891789570392,"expected_score":35.95508162812867,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.814033048887957},"none":{"ceiling_score":48.98914683617549,"expected_score":29.31939286122554,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.110045858876603}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:3102bc1eaa5e56ef","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.77569875},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.06723375}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675000000001},"codegen_output_tokens":{"attempt_count":28,"output_max":28998,"output_mean":10500.666666666666,"output_min":2419,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":28998,"output_mean":23512.0,"output_min":18631,"run_count":8},"medium":{"attempt_count":9,"output_max":6917,"output_mean":4677.5,"output_min":3936,"run_count":8},"none":{"attempt_count":9,"output_max":6065,"output_mean":3312.5,"output_min":2419,"run_count":8}},"display_name":"GPT-5.6 Terra","economics":{"all":30.72507580285448,"highest":36.67076585448049,"medium":33.188819610863185,"none":26.00966840245281},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:48:31Z","match_totals_all":{"draws":4484,"losses":5472,"wins":4795},"match_totals_tracks":{"highest":{"draws":1318,"losses":1747,"wins":2025},"medium":{"draws":1396,"losses":1967,"wins":1804},"none":{"draws":1770,"losses":1758,"wins":966}},"model_slug":"gpt-5-6-terra","overall":{"max":70.43261015426121,"mean":31.671769966772843,"min":8.734207344844247},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.804578543773026,"GB2-02":22.702872420361032,"GB2-03":17.951500484209177,"GB2-04":11.020320462097887,"GB2-05":47.532609053509155,"GB2-06":70.43261015426121,"GB2-07":42.21534013603469,"GB2-08":24.706295581597782},"per_game_all":{"GB2-01":54.48033909516024,"GB2-02":13.939771421663005,"GB2-03":15.690518810672392,"GB2-04":12.0803470080689,"GB2-06":50.237716226416005,"GB2-07":43.15943417840868,"GB2-08":25.487403879592147},"per_game_match_totals_all":{"GB2-01":{"draws":314,"losses":502,"wins":1097},"GB2-02":{"draws":1327,"losses":273,"wins":204},"GB2-03":{"draws":757,"losses":814,"wins":243},"GB2-04":{"draws":1151,"losses":495,"wins":236},"GB2-05":{"draws":0,"losses":622,"wins":788},"GB2-06":{"draws":129,"losses":874,"wins":901},"GB2-07":{"draws":0,"losses":1170,"wins":870},"GB2-08":{"draws":806,"losses":722,"wins":456}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":90,"losses":148,"wins":378},"GB2-02":{"draws":319,"losses":86,"wins":159},"GB2-03":{"draws":217,"losses":272,"wins":117},"GB2-04":{"draws":404,"losses":131,"wins":57},"GB2-05":{"draws":0,"losses":318,"wins":402},"GB2-06":{"draws":53,"losses":110,"wins":439},"GB2-07":{"draws":0,"losses":417,"wins":303},"GB2-08":{"draws":235,"losses":265,"wins":170}},"medium":{"GB2-01":{"draws":5,"losses":152,"wins":460},"GB2-02":{"draws":492,"losses":95,"wins":35},"GB2-03":{"draws":286,"losses":268,"wins":52},"GB2-04":{"draws":335,"losses":218,"wins":109},"GB2-05":{"draws":0,"losses":304,"wins":386},"GB2-06":{"draws":74,"losses":394,"wins":218},"GB2-07":{"draws":0,"losses":269,"wins":371},"GB2-08":{"draws":204,"losses":267,"wins":173}},"none":{"GB2-01":{"draws":219,"losses":202,"wins":259},"GB2-02":{"draws":516,"losses":92,"wins":10},"GB2-03":{"draws":254,"losses":274,"wins":74},"GB2-04":{"draws":412,"losses":146,"wins":70},"GB2-06":{"draws":2,"losses":370,"wins":244},"GB2-07":{"draws":0,"losses":484,"wins":196},"GB2-08":{"draws":367,"losses":190,"wins":113}}},"per_game_raw_elo_all":{"GB2-01":1682.7709938728078,"GB2-02":1473.7559143666779,"GB2-03":1306.2801189299742,"GB2-04":1429.9301623712436,"GB2-06":1509.5471662971015,"GB2-07":1402.7734376571582,"GB2-08":1381.9725661768261},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1717.9763087846316,"GB2-02":1543.5005493253204,"GB2-03":1336.1103914290077,"GB2-04":1422.0296235187125,"GB2-05":1538.0876627404668,"GB2-06":1959.1466323713291,"GB2-07":1383.5188944686954,"GB2-08":1369.8089395611162},"medium":{"GB2-01":1796.2967053067227,"GB2-02":1445.4418376482622,"GB2-03":1285.1876284896398,"GB2-04":1422.6959218933202,"GB2-05":1552.7113501568808,"GB2-06":1294.9311187808876,"GB2-07":1612.835855809412,"GB2-08":1385.4295748375878},"none":{"GB2-01":1534.039967527069,"GB2-02":1432.3253561264514,"GB2-03":1297.5423368712748,"GB2-04":1445.0649417016982,"GB2-06":1274.5637477390883,"GB2-07":1211.9655626933675,"GB2-08":1390.6791841317745}},"per_game_tracks":{"highest":{"GB2-01":56.804578543773026,"GB2-02":22.702872420361032,"GB2-03":17.951500484209177,"GB2-04":11.020320462097887,"GB2-05":47.532609053509155,"GB2-06":70.43261015426121,"GB2-07":42.21534013603469,"GB2-08":24.706295581597782},"medium":{"GB2-01":61.97525676902314,"GB2-02":10.382234499783731,"GB2-03":14.091816206249629,"GB2-04":11.109718663638949,"GB2-05":48.1851616264659,"GB2-06":40.59769518135591,"GB2-07":53.4592722770371,"GB2-08":25.70940166335112},"none":{"GB2-01":44.661181972684545,"GB2-02":8.734207344844247,"GB2-03":15.028239741558364,"GB2-04":14.111001898469867,"GB2-06":39.68284334363087,"GB2-07":33.803690122154244,"GB2-08":26.046514393827536}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.67076585448049,"medium":33.188819610863185,"none":25.15572443497484},"reasoning_agg":{"highest":{"max":70.43261015426121,"mean":36.67076585448049,"min":11.020320462097887},"medium":{"max":61.97525676902314,"mean":33.188819610863185,"min":10.382234499783731},"none":{"max":44.661181972684545,"mean":25.15572443497484,"min":8.734207344844247}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":70.43261015426121,"expected_score":28.45895182555908,"reasoning_variance":11.515041419505653,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.212818141213763},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.43261015426121,"expected_score":29.359690332848565,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.311075521631928},"medium":{"ceiling_score":61.97525676902314,"expected_score":31.49895097718919,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6898686336739956},"none":{"ceiling_score":44.661181972684545,"expected_score":29.074418581528594,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.9186941465537544}}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:e111031353bc7327","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.39097600000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.34510199999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.345102},"historical-provider-setting-intensive":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.66363},"codegen_latency_ms":{"attempt_count":26,"max_ms":79649,"mean_ms":37254.041666666664,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":10,"max_ms":74310,"mean_ms":41174.25,"min_ms":21597,"run_count":8}},"codegen_output_tokens":{"attempt_count":58,"output_max":15813,"output_mean":7191.916666666667,"output_min":1943,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":10,"output_max":6022,"output_mean":2920.75,"output_min":1943,"run_count":8}},"display_name":"o3","economics":{"all":39.208288843092284,"highest":37.141183073330524,"medium":34.845540790707936,"none":27.756560116070283},"first_seen_at":"2026-10-13T14:28:18Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[100000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":82,"output_token_observations":58,"provider_post_attempt_observations":10,"provider_post_attempts":10,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[100000],"total_output_tokens":345212,"total_reasoning_output_tokens":5824,"total_visible_output_tokens":17542,"visible_token_observations":10},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6785714285714286,"model_code_failure_rate":0.32142857142857145,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4}},"id":"o3","is_recent_addition":true,"last_measured_at":"2026-10-13T14:28:18Z","match_totals_all":{"draws":3142,"losses":10125,"wins":8437},"match_totals_tracks":{"highest":{"draws":1425,"losses":7075,"wins":6203},"medium":{"draws":852,"losses":1507,"wins":1262},"none":{"draws":865,"losses":1543,"wins":972}},"model_slug":"o3","overall":{"max":51.36724768624216,"mean":31.297889792591956,"min":7.002641230792495},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.54695274931972,"GB2-03":16.937911443870327,"GB2-05":43.76286378016479,"GB2-06":42.79025293252236,"GB2-07":41.418528945002734,"GB2-08":29.390588589103235},"per_game_all":{"GB2-01":39.16144466226292,"GB2-05":43.586056133413045,"GB2-06":45.21231525224152,"GB2-07":43.98755950646599,"GB2-08":24.094068661077912},"per_game_match_totals_all":{"GB2-01":{"draws":367,"losses":1365,"wins":1498},"GB2-02":{"draws":343,"losses":78,"wins":5},"GB2-03":{"draws":338,"losses":551,"wins":269},"GB2-04":{"draws":643,"losses":271,"wins":110},"GB2-05":{"draws":0,"losses":2128,"wins":2125},"GB2-06":{"draws":109,"losses":2350,"wins":1778},"GB2-07":{"draws":0,"losses":2390,"wins":1902},"GB2-08":{"draws":1342,"losses":992,"wins":750}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":222,"losses":804,"wins":1166},"GB2-03":{"draws":216,"losses":344,"wins":158},"GB2-05":{"draws":0,"losses":1563,"wins":1590},"GB2-06":{"draws":56,"losses":1802,"wins":1313},"GB2-07":{"draws":0,"losses":1843,"wins":1369},"GB2-08":{"draws":931,"losses":719,"wins":607}},"medium":{"GB2-01":{"draws":108,"losses":289,"wins":175},"GB2-04":{"draws":406,"losses":136,"wins":36},"GB2-05":{"draws":0,"losses":326,"wins":290},"GB2-06":{"draws":45,"losses":305,"wins":260},"GB2-07":{"draws":0,"losses":250,"wins":360},"GB2-08":{"draws":293,"losses":201,"wins":141}},"none":{"GB2-01":{"draws":37,"losses":272,"wins":157},"GB2-02":{"draws":343,"losses":78,"wins":5},"GB2-03":{"draws":122,"losses":207,"wins":111},"GB2-04":{"draws":237,"losses":135,"wins":74},"GB2-05":{"draws":0,"losses":239,"wins":245},"GB2-06":{"draws":8,"losses":243,"wins":205},"GB2-07":{"draws":0,"losses":297,"wins":173},"GB2-08":{"draws":118,"losses":72,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1450.7353045495684,"GB2-05":1449.6455070160328,"GB2-06":1397.6665293959886,"GB2-07":1419.6628302164465,"GB2-08":1360.2751787696727},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1592.897837764256,"GB2-03":1322.7375995885302,"GB2-05":1453.607762114061,"GB2-06":1343.7440909006439,"GB2-07":1367.2681452825273,"GB2-08":1442.7539988418569},"medium":{"GB2-01":1387.539741398518,"GB2-04":1404.2924220613365,"GB2-05":1416.9086585778475,"GB2-06":1421.744227319065,"GB2-07":1570.1695789060027,"GB2-08":1384.6156616969067},"none":{"GB2-01":1371.768334485931,"GB2-02":1418.5439964742875,"GB2-03":1371.0449106186966,"GB2-04":1434.310670510432,"GB2-05":1478.4201003561898,"GB2-06":1427.5112699682563,"GB2-07":1321.5507664608097,"GB2-08":1253.455875770255}},"per_game_tracks":{"highest":{"GB2-01":48.54695274931972,"GB2-03":16.937911443870327,"GB2-05":43.76286378016479,"GB2-06":42.79025293252236,"GB2-07":41.418528945002734,"GB2-08":29.390588589103235},"medium":{"GB2-01":34.98930130206699,"GB2-04":8.640494889816763,"GB2-05":42.12524026183915,"GB2-06":46.29382577944253,"GB2-07":51.36724768624216,"GB2-08":25.65713482484002},"none":{"GB2-01":33.94807993540205,"GB2-02":7.002641230792495,"GB2-03":20.59935788022407,"GB2-04":12.668086021705166,"GB2-05":44.8700643582352,"GB2-06":46.55286704475967,"GB2-07":39.1769018881531,"GB2-08":17.234482569290478}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.70967968383236,"medium":32.42742957787322,"none":27.756560116070283},"reasoning_agg":{"highest":{"max":48.54695274931972,"mean":33.70967968383236,"min":16.937911443870327},"medium":{"max":51.36724768624216,"mean":32.42742957787322,"min":8.640494889816763},"none":{"max":46.55286704475967,"mean":27.756560116070283,"min":7.002641230792495}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":51.36724768624216,"expected_score":36.17986427971147,"reasoning_variance":5.95311956776208,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.8819744871195105},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.54695274931972,"expected_score":26.805697937273123,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.903981746559239},"medium":{"ceiling_score":51.36724768624216,"expected_score":33.427218111565494,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9997885336922749},"none":{"ceiling_score":46.55286704475967,"expected_score":30.463404527781652,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.7068444117113692}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:e630610a8ce59c4d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.98845232184},"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":0.9884523218399999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.37737643796},"codegen_latency_ms":{"attempt_count":31,"max_ms":1461124,"mean_ms":482100.7083333333,"min_ms":19301,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1461124,"mean_ms":902169.625,"min_ms":499972,"run_count":8},"medium":{"attempt_count":9,"max_ms":676490,"mean_ms":489467.75,"min_ms":326732,"run_count":8},"none":{"attempt_count":12,"max_ms":131002,"mean_ms":54664.75,"min_ms":19301,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":106197,"output_mean":33246.666666666664,"output_min":2345,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":106197,"output_mean":60744.125,"output_min":32963,"run_count":8},"medium":{"attempt_count":9,"output_max":42157,"output_mean":35085.125,"output_min":20989,"run_count":8},"none":{"attempt_count":12,"output_max":10866,"output_mean":3910.75,"output_min":2345,"run_count":8}},"display_name":"DeepSeek V4 Pro 0813","economics":{"all":32.6637452533387,"highest":37.305625338896476,"medium":30.00650762597766,"none":27.507963371931634},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:01:51Z","match_totals_all":{"draws":3901,"losses":5386,"wins":4669},"match_totals_tracks":{"highest":{"draws":1268,"losses":1649,"wins":2171},"medium":{"draws":1386,"losses":2093,"wins":1703},"none":{"draws":1247,"losses":1644,"wins":795}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":67.1044944137916,"mean":30.970392447598766,"min":0.4881983506273939},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":41,"overall_ranking_status":"ranked","per_game":{"GB2-01":37.69844401104104,"GB2-02":8.819027535698567,"GB2-03":36.71918964554881,"GB2-04":12.736409262056856,"GB2-05":60.72936755085117,"GB2-06":61.09638272867829,"GB2-07":67.1044944137916,"GB2-08":13.541687563505466},"per_game_all":{"GB2-01":37.00282423807864,"GB2-03":24.871434953192647,"GB2-04":8.840573358735602,"GB2-06":52.53424420834358,"GB2-07":52.91974031583043,"GB2-08":19.813654445851302},"per_game_match_totals_all":{"GB2-01":{"draws":550,"losses":803,"wins":583},"GB2-02":{"draws":904,"losses":249,"wins":39},"GB2-03":{"draws":398,"losses":841,"wins":653},"GB2-04":{"draws":1026,"losses":616,"wins":250},"GB2-05":{"draws":0,"losses":504,"wins":806},"GB2-06":{"draws":60,"losses":885,"wins":1005},"GB2-07":{"draws":0,"losses":784,"wins":1098},"GB2-08":{"draws":963,"losses":704,"wins":235}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":326,"wins":282},"GB2-02":{"draws":485,"losses":102,"wins":21},"GB2-03":{"draws":46,"losses":220,"wins":342},"GB2-04":{"draws":343,"losses":209,"wins":120},"GB2-05":{"draws":0,"losses":169,"wins":481},"GB2-06":{"draws":21,"losses":213,"wins":436},"GB2-07":{"draws":0,"losses":137,"wins":485},"GB2-08":{"draws":355,"losses":273,"wins":4}},"medium":{"GB2-01":{"draws":392,"losses":151,"wins":149},"GB2-02":{"draws":419,"losses":147,"wins":18},"GB2-03":{"draws":81,"losses":368,"wins":229},"GB2-04":{"draws":229,"losses":278,"wins":85},"GB2-05":{"draws":0,"losses":335,"wins":325},"GB2-06":{"draws":32,"losses":396,"wins":238},"GB2-07":{"draws":0,"losses":180,"wins":462},"GB2-08":{"draws":233,"losses":238,"wins":197}},"none":{"GB2-01":{"draws":140,"losses":326,"wins":152},"GB2-03":{"draws":271,"losses":253,"wins":82},"GB2-04":{"draws":454,"losses":129,"wins":45},"GB2-06":{"draws":7,"losses":276,"wins":331},"GB2-07":{"draws":0,"losses":467,"wins":151},"GB2-08":{"draws":375,"losses":193,"wins":34}}},"per_game_raw_elo_all":{"GB2-01":1418.0386252750386,"GB2-03":1427.408579866922,"GB2-04":1405.7836372797253,"GB2-06":1560.6748304575706,"GB2-07":1601.832247077291,"GB2-08":1293.6194276935664},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1428.5751959285697,"GB2-02":1433.0004314507157,"GB2-03":1583.7219879370728,"GB2-04":1434.8198939982597,"GB2-05":1833.8267022796224,"GB2-06":1751.2939503672937,"GB2-07":1891.126478518618,"GB2-08":1195.9506876496553},"medium":{"GB2-01":1494.90129697037,"GB2-02":1397.912876555276,"GB2-03":1376.9750705639494,"GB2-04":1343.532117717994,"GB2-05":1406.0030818809284,"GB2-06":1296.548501244925,"GB2-07":1790.727330215465,"GB2-08":1413.8846086260264},"none":{"GB2-01":1330.6393829261763,"GB2-03":1321.5286810997436,"GB2-04":1438.9989001229228,"GB2-06":1634.1820397604931,"GB2-07":1123.6429324977894,"GB2-08":1271.0229868050171}},"per_game_tracks":{"highest":{"GB2-01":37.69844401104104,"GB2-02":8.819027535698567,"GB2-03":36.71918964554881,"GB2-04":12.736409262056856,"GB2-05":60.72936755085117,"GB2-06":61.09638272867829,"GB2-07":67.1044944137916,"GB2-08":13.541687563505466},"medium":{"GB2-01":42.077264109657904,"GB2-02":4.410433419055344,"GB2-03":21.048833591778262,"GB2-04":0.4881983506273939,"GB2-05":41.638600884881185,"GB2-06":40.67034399383604,"GB2-07":62.18169583868832,"GB2-08":27.53669081929683},"none":{"GB2-01":31.23276459353697,"GB2-03":16.846281622250867,"GB2-04":13.297112463522557,"GB2-06":55.8360059025164,"GB2-07":29.473030695011378,"GB2-08":18.362584954751615}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.305625338896476,"medium":30.00650762597766,"none":25.599044377922155},"reasoning_agg":{"highest":{"max":67.1044944137916,"mean":37.305625338896476,"min":8.819027535698567},"medium":{"max":62.18169583868832,"mean":30.00650762597766,"min":0.4881983506273939},"none":{"max":55.8360059025164,"mean":25.599044377922155,"min":13.297112463522557}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":67.1044944137916,"expected_score":30.363447438593766,"reasoning_variance":11.706580960974321,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.606945009004999},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.1044944137916,"expected_score":30.588380217910686,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.71724512098579},"medium":{"ceiling_score":62.18169583868832,"expected_score":28.09504215175912,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9114654742185415},"none":{"ceiling_score":55.8360059025164,"expected_score":31.01812036303892,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.419075985116766}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:46d75de3b4280668","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.168814505}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.16881450499999998},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.3521656,"mean":0.08720021666666666,"median":0.0402421875,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":38,"run_count":24,"total":2.0928052},"codegen_latency_ms":{"attempt_count":38,"max_ms":2128037,"mean_ms":537328.375,"min_ms":33625,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":2128037,"mean_ms":1259891.875,"min_ms":809012,"run_count":8},"medium":{"attempt_count":13,"max_ms":394009,"mean_ms":249918.25,"min_ms":106640,"run_count":8},"none":{"attempt_count":14,"max_ms":139550,"mean_ms":102175.0,"min_ms":33625,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":142524,"output_mean":33293.458333333336,"output_min":2177,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":142524,"output_mean":77872.0,"output_min":45409,"run_count":8},"medium":{"attempt_count":13,"output_max":24263,"output_mean":15845.5,"output_min":6781,"run_count":8},"none":{"attempt_count":14,"output_max":9194,"output_mean":6162.875,"output_min":2177,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"all":41.78045711363341,"highest":45.83843838040298,"medium":30.67291746361237,"none":21.734568154955603},"first_seen_at":"2026-10-12T23:45:50Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[131072],"finish_reason_observations":38,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":41,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"reconciliation_get_attempts":53,"requested_max_output_token_observations":27,"requested_max_output_tokens":[131072],"total_output_tokens":799043,"total_reasoning_output_tokens":636129,"total_visible_output_tokens":162914,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.625,"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":"2026-10-12T23:40:45Z","match_totals_all":{"draws":1943,"losses":3606,"wins":3305},"match_totals_tracks":{"highest":{"draws":457,"losses":1401,"wins":2020},"medium":{"draws":906,"losses":1297,"wins":985},"none":{"draws":580,"losses":908,"wins":300}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":64.61503487712248,"mean":30.1999548739699,"min":6.422509129899948},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":58.45817759552203,"GB2-04":42.6945434889604,"GB2-05":49.31491624237111,"GB2-06":34.03162257519534,"GB2-07":64.61503487712248,"GB2-08":25.916335503246472},"per_game_all":{"GB2-01":41.76378990288987,"GB2-06":41.79712432437695},"per_game_match_totals_all":{"GB2-01":{"draws":248,"losses":637,"wins":667},"GB2-02":{"draws":682,"losses":161,"wins":9},"GB2-03":{"draws":253,"losses":381,"wins":246},"GB2-04":{"draws":467,"losses":230,"wins":359},"GB2-05":{"draws":0,"losses":494,"wins":708},"GB2-06":{"draws":63,"losses":911,"wins":560},"GB2-07":{"draws":0,"losses":537,"wins":567},"GB2-08":{"draws":230,"losses":255,"wins":189}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":173,"wins":432},"GB2-04":{"draws":184,"losses":99,"wins":327},"GB2-05":{"draws":0,"losses":295,"wins":423},"GB2-06":{"draws":28,"losses":422,"wins":172},"GB2-07":{"draws":0,"losses":157,"wins":477},"GB2-08":{"draws":230,"losses":255,"wins":189}},"medium":{"GB2-01":{"draws":102,"losses":173,"wins":191},"GB2-02":{"draws":340,"losses":82,"wins":4},"GB2-03":{"draws":159,"losses":163,"wins":118},"GB2-04":{"draws":283,"losses":131,"wins":32},"GB2-05":{"draws":0,"losses":199,"wins":285},"GB2-06":{"draws":22,"losses":169,"wins":265},"GB2-07":{"draws":0,"losses":380,"wins":90}},"none":{"GB2-01":{"draws":131,"losses":291,"wins":44},"GB2-02":{"draws":342,"losses":79,"wins":5},"GB2-03":{"draws":94,"losses":218,"wins":128},"GB2-06":{"draws":13,"losses":320,"wins":123}}},"per_game_raw_elo_all":{"GB2-01":1490.153095070351,"GB2-06":1321.6340420159822},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1743.0234162973547,"GB2-04":1658.10241867521,"GB2-05":1578.029123842747,"GB2-06":1148.7504679449864,"GB2-07":1840.3546231595963,"GB2-08":1388.6520037493087},"medium":{"GB2-01":1509.9023742579027,"GB2-02":1413.926783730699,"GB2-03":1422.137393882755,"GB2-04":1400.5193195826118,"GB2-05":1582.4687321812207,"GB2-06":1640.7638759330982,"GB2-07":1072.5831926489577},"none":{"GB2-01":1217.533494655795,"GB2-02":1417.6215481577303,"GB2-03":1377.0942225802123,"GB2-06":1175.387782169862}},"per_game_tracks":{"highest":{"GB2-01":58.45817759552203,"GB2-04":42.6945434889604,"GB2-05":49.31491624237111,"GB2-06":34.03162257519534,"GB2-07":64.61503487712248,"GB2-08":25.916335503246472},"medium":{"GB2-01":43.06762865236117,"GB2-02":6.422509129899948,"GB2-03":24.47190608839963,"GB2-04":8.13425235841831,"GB2-05":49.51302481524308,"GB2-06":56.13164567388185,"GB2-07":26.969455527082605},"none":{"GB2-01":23.765563460786414,"GB2-02":6.886739731431823,"GB2-03":21.05786470355051,"GB2-06":35.228104724053665}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.65747349045518,"medium":29.665870682864817,"none":18.276520448589707},"reasoning_agg":{"highest":{"max":64.61503487712248,"mean":42.65747349045518,"min":25.916335503246472},"medium":{"max":56.13164567388185,"mean":29.665870682864817,"min":6.422509129899948},"none":{"max":35.228104724053665,"mean":18.276520448589707,"min":6.886739731431823}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":64.61503487712248,"expected_score":36.13132704197786,"reasoning_variance":24.380953041865475,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.931372168007961},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.61503487712248,"expected_score":38.151024494978955,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.506448995476227},"medium":{"ceiling_score":56.13164567388185,"expected_score":29.291222485852142,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.37464819701267515},"none":{"ceiling_score":35.228104724053665,"expected_score":21.046950510127697,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.77043006153799}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:0486b73521227988","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":1.4205012499999998},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793050000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":1.4205012499999998},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.45591875},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT-5","economics":{"all":32.77041677325984,"highest":32.55698207267731,"medium":30.26978658607256,"none":27.059563776059907},"first_seen_at":"2026-10-13T14:19:04Z","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"first_pass_admitted":4,"first_pass_rate":0.6666666666666666,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"repaired_admitted":2,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":"2026-10-13T14:01:56Z","match_totals_all":{"draws":3233,"losses":4803,"wins":3645},"match_totals_tracks":{"highest":{"draws":1418,"losses":1598,"wins":1538},"medium":{"draws":987,"losses":1814,"wins":1258},"none":{"draws":828,"losses":1391,"wins":849}},"model_slug":"gpt-5","overall":{"max":63.8608311964663,"mean":29.630840387440724,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":43,"overall_ranking_status":"partial","per_game":{"GB2-01":35.15151256986644,"GB2-02":6.643466534467119,"GB2-03":16.622108992942632,"GB2-04":8.904846975053758,"GB2-05":60.17205143737434,"GB2-06":63.8608311964663,"GB2-07":48.477869412075165,"GB2-08":20.623169463172715},"per_game_all":{"GB2-01":36.58555298694389,"GB2-03":9.847011580390346,"GB2-05":51.270234547476946,"GB2-07":47.43865577521685,"GB2-08":18.710628976271177},"per_game_match_totals_all":{"GB2-01":{"draws":226,"losses":836,"wins":592},"GB2-02":{"draws":791,"losses":218,"wins":23},"GB2-03":{"draws":464,"losses":877,"wins":173},"GB2-04":{"draws":726,"losses":301,"wins":125},"GB2-05":{"draws":0,"losses":668,"wins":1019},"GB2-06":{"draws":49,"losses":441,"wins":672},"GB2-07":{"draws":0,"losses":838,"wins":912},"GB2-08":{"draws":977,"losses":624,"wins":129}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":86,"losses":300,"wins":192},"GB2-02":{"draws":419,"losses":105,"wins":18},"GB2-03":{"draws":177,"losses":251,"wins":90},"GB2-04":{"draws":390,"losses":141,"wins":35},"GB2-05":{"draws":0,"losses":161,"wins":419},"GB2-06":{"draws":19,"losses":156,"wins":393},"GB2-07":{"draws":0,"losses":281,"wins":323},"GB2-08":{"draws":327,"losses":203,"wins":68}},"medium":{"GB2-01":{"draws":76,"losses":411,"wins":85},"GB2-03":{"draws":211,"losses":257,"wins":52},"GB2-04":{"draws":336,"losses":160,"wins":90},"GB2-05":{"draws":0,"losses":236,"wins":353},"GB2-06":{"draws":30,"losses":285,"wins":279},"GB2-07":{"draws":0,"losses":230,"wins":376},"GB2-08":{"draws":334,"losses":235,"wins":23}},"none":{"GB2-01":{"draws":64,"losses":125,"wins":315},"GB2-02":{"draws":372,"losses":113,"wins":5},"GB2-03":{"draws":76,"losses":369,"wins":31},"GB2-05":{"draws":0,"losses":271,"wins":247},"GB2-07":{"draws":0,"losses":327,"wins":213},"GB2-08":{"draws":316,"losses":186,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1411.7182068652153,"GB2-03":1229.1837784024929,"GB2-05":1621.8477598859688,"GB2-07":1490.0470071858456,"GB2-08":1276.4428210769922},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1389.9967596582046,"GB2-02":1415.6853613763562,"GB2-03":1318.5710584452313,"GB2-04":1406.2626783045416,"GB2-05":1821.3372616224692,"GB2-06":1812.838940875685,"GB2-07":1511.2414888315645,"GB2-08":1306.2254113142635},"medium":{"GB2-01":1155.812278962286,"GB2-03":1269.713092634796,"GB2-04":1428.1659653088445,"GB2-05":1603.2850901756644,"GB2-06":1453.6656902878449,"GB2-07":1616.0426481529068,"GB2-08":1228.7679082227012},"none":{"GB2-01":1689.3455819751557,"GB2-02":1395.9598793126486,"GB2-03":1099.2671841274512,"GB2-05":1440.9209278597727,"GB2-07":1342.8568845730658,"GB2-08":1294.3351436940122}},"per_game_tracks":{"highest":{"GB2-01":35.15151256986644,"GB2-02":6.643466534467119,"GB2-03":16.622108992942632,"GB2-04":8.904846975053758,"GB2-05":60.17205143737434,"GB2-06":63.8608311964663,"GB2-07":48.477869412075165,"GB2-08":20.623169463172715},"medium":{"GB2-01":19.690755873054457,"GB2-03":12.918925748228403,"GB2-04":11.843642176490484,"GB2-05":50.44191282974045,"GB2-06":47.7276587959829,"GB2-07":53.616508598719264,"GB2-08":15.64910208029194},"none":{"GB2-01":54.91439051791076,"GB2-02":4.165048062927651,"GB2-03":0.0,"GB2-05":43.196739375316035,"GB2-07":40.221589314856125,"GB2-08":19.859615385348874}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.55698207267731,"medium":29.275975313584954,"none":27.059563776059907},"reasoning_agg":{"highest":{"max":63.8608311964663,"mean":32.55698207267731,"min":6.643466534467119},"medium":{"max":53.616508598719264,"mean":29.275975313584954,"min":11.843642176490484},"none":{"max":54.91439051791076,"mean":27.059563776059907,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.8608311964663,"expected_score":30.755942136833387,"reasoning_variance":5.497418296617401,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1251017493926625},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":63.8608311964663,"expected_score":25.10037122876322,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.456610843914088},"medium":{"ceiling_score":53.616508598719264,"expected_score":28.59074250078488,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6852328128000735},"none":{"ceiling_score":54.91439051791076,"expected_score":29.69621442777144,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.636650651711534}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:e81535a3e8cbf684","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626000002},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666666,"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":0.9754123686000001},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.35917138039999996},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"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":3.5146565168000006},"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":29.233886831722366,"highest":29.27131789536578,"medium":32.13445099917024,"none":26.295891600631073},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:42:12Z","match_totals_all":{"draws":8761,"losses":11489,"wins":8031},"match_totals_tracks":{"highest":{"draws":1481,"losses":2096,"wins":1383},"medium":{"draws":3088,"losses":3342,"wins":2986},"none":{"draws":4192,"losses":6051,"wins":3662}},"model_slug":"z-ai-glm-5-2","overall":{"max":70.13957322115257,"mean":29.233886831722362,"min":5.6552402851093095},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.104787766961174,"GB2-02":25.544043760700507,"GB2-03":17.919425479337168,"GB2-04":23.649714240574344,"GB2-05":49.1305179400455,"GB2-06":42.19581892501655,"GB2-07":15.783120823883099,"GB2-08":15.8431142264079},"per_game_all":{"GB2-01":35.28032209076519,"GB2-02":14.713341063912843,"GB2-03":16.307923166452934,"GB2-04":16.429635802673857,"GB2-05":42.4769009565523,"GB2-06":51.970651438838786,"GB2-07":37.28786266726781,"GB2-08":19.404457467315204},"per_game_match_totals_all":{"GB2-01":{"draws":1000,"losses":1721,"wins":870},"GB2-02":{"draws":2454,"losses":535,"wins":309},"GB2-03":{"draws":1361,"losses":1479,"wins":496},"GB2-04":{"draws":1964,"losses":910,"wins":598},"GB2-05":{"draws":0,"losses":2059,"wins":1649},"GB2-06":{"draws":195,"losses":1417,"wins":1908},"GB2-07":{"draws":0,"losses":2093,"wins":1645},"GB2-08":{"draws":1787,"losses":1275,"wins":556}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":252,"losses":198,"wins":235},"GB2-02":{"draws":281,"losses":88,"wins":191},"GB2-03":{"draws":251,"losses":250,"wins":101},"GB2-04":{"draws":260,"losses":157,"wins":186},"GB2-05":{"draws":0,"losses":293,"wins":351},"GB2-06":{"draws":33,"losses":330,"wins":257},"GB2-07":{"draws":0,"losses":560,"wins":56},"GB2-08":{"draws":404,"losses":220,"wins":6}},"medium":{"GB2-01":{"draws":376,"losses":499,"wins":305},"GB2-02":{"draws":829,"losses":154,"wins":107},"GB2-03":{"draws":523,"losses":524,"wins":61},"GB2-04":{"draws":655,"losses":297,"wins":206},"GB2-05":{"draws":0,"losses":607,"wins":673},"GB2-06":{"draws":61,"losses":218,"wins":895},"GB2-07":{"draws":0,"losses":526,"wins":718},"GB2-08":{"draws":644,"losses":517,"wins":21}},"none":{"GB2-01":{"draws":372,"losses":1024,"wins":330},"GB2-02":{"draws":1344,"losses":293,"wins":11},"GB2-03":{"draws":587,"losses":705,"wins":334},"GB2-04":{"draws":1049,"losses":456,"wins":206},"GB2-05":{"draws":0,"losses":1159,"wins":625},"GB2-06":{"draws":101,"losses":869,"wins":756},"GB2-07":{"draws":0,"losses":1007,"wins":871},"GB2-08":{"draws":739,"losses":538,"wins":529}}},"per_game_raw_elo_all":{"GB2-01":1391.9478407955582,"GB2-02":1479.9126769467075,"GB2-03":1314.4258462441696,"GB2-04":1462.3460723626097,"GB2-05":1424.789366262169,"GB2-06":1548.1275494885301,"GB2-07":1283.0243213920803,"GB2-08":1287.2473032750063},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1525.6122501336238,"GB2-02":1566.113144799956,"GB2-03":1335.6872096991694,"GB2-04":1516.1584136042177,"GB2-05":1573.8967623364413,"GB2-06":1330.510190621402,"GB2-07":844.4409155070019,"GB2-08":1231.789117074696},"medium":{"GB2-01":1380.6295956477145,"GB2-02":1465.804717479487,"GB2-03":1262.1270779811862,"GB2-04":1454.0242891772218,"GB2-05":1504.3902794388155,"GB2-06":1952.622743256764,"GB2-07":1584.9883002459344,"GB2-08":1198.1417360844243},"none":{"GB2-01":1269.6016766053367,"GB2-02":1407.8201685606796,"GB2-03":1345.463251052153,"GB2-04":1416.855514306389,"GB2-05":1196.0810570112508,"GB2-06":1361.249714587424,"GB2-07":1419.643748423305,"GB2-08":1431.8110566658984}},"per_game_tracks":{"highest":{"GB2-01":44.104787766961174,"GB2-02":25.544043760700507,"GB2-03":17.919425479337168,"GB2-04":23.649714240574344,"GB2-05":49.1305179400455,"GB2-06":42.19581892501655,"GB2-07":15.783120823883099,"GB2-08":15.8431142264079},"medium":{"GB2-01":34.53309651054879,"GB2-02":12.940739145928717,"GB2-03":12.34394474168381,"GB2-04":15.313090304831,"GB2-05":46.02893124987112,"GB2-06":70.13957322115257,"GB2-07":52.09384329516902,"GB2-08":13.682389524176902},"none":{"GB2-01":27.203081994785613,"GB2-02":5.6552402851093095,"GB2-03":18.660399278337824,"GB2-04":10.326102862616224,"GB2-05":32.27125367974028,"GB2-06":43.57656217034723,"GB2-07":43.9866238827513,"GB2-08":28.68786865136081}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.27131789536578,"medium":32.13445099917024,"none":26.29589160063107},"reasoning_agg":{"highest":{"max":49.1305179400455,"mean":29.27131789536578,"min":15.783120823883099},"medium":{"max":70.13957322115257,"mean":32.13445099917024,"min":12.34394474168381},"none":{"max":43.9866238827513,"mean":26.29589160063107,"min":5.6552402851093095}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":70.13957322115257,"expected_score":26.833913929275315,"reasoning_variance":5.8385593985391715,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.399972902447047},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.1305179400455,"expected_score":20.098830490106714,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.172487405259066},"medium":{"ceiling_score":70.13957322115257,"expected_score":32.288060728100504,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.15360972893026315},"none":{"ceiling_score":43.9866238827513,"expected_score":28.114850569618724,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8189589689876549}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:0f2b44abb61ff1a1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.24666659999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054444999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996}},"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":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054444999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.24666659999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399885},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":27.425598450607183,"highest":37.1143139355281,"medium":28.787814869299062,"none":16.374666546994376},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:07:42Z","match_totals_all":{"draws":5185,"losses":7162,"wins":4383},"match_totals_tracks":{"highest":{"draws":1768,"losses":1612,"wins":2200},"medium":{"draws":1809,"losses":2344,"wins":1565},"none":{"draws":1608,"losses":3206,"wins":618}},"model_slug":"gpt-5-6-luna","overall":{"max":72.44602362696502,"mean":27.42559845060718,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.28837516772396,"GB2-02":8.92542798143972,"GB2-03":20.437499812186967,"GB2-04":5.960904579118896,"GB2-05":45.61621744929189,"GB2-06":72.44602362696502,"GB2-07":60.59554150190553,"GB2-08":17.64452136559285},"per_game_all":{"GB2-01":42.789909400513295,"GB2-02":7.928784074859938,"GB2-03":18.10879106137188,"GB2-04":10.64399957807675,"GB2-05":38.82578891181941,"GB2-06":50.94024150355283,"GB2-07":38.49899151909875,"GB2-08":11.6682815555646},"per_game_match_totals_all":{"GB2-01":{"draws":251,"losses":966,"wins":926},"GB2-02":{"draws":1584,"losses":286,"wins":56},"GB2-03":{"draws":925,"losses":888,"wins":337},"GB2-04":{"draws":1289,"losses":496,"wins":201},"GB2-05":{"draws":0,"losses":1290,"wins":963},"GB2-06":{"draws":142,"losses":953,"wins":1049},"GB2-07":{"draws":0,"losses":1294,"wins":792},"GB2-08":{"draws":994,"losses":989,"wins":59}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":145,"wins":542},"GB2-02":{"draws":497,"losses":89,"wins":36},"GB2-03":{"draws":330,"losses":284,"wins":131},"GB2-04":{"draws":399,"losses":202,"wins":57},"GB2-05":{"draws":0,"losses":384,"wins":422},"GB2-06":{"draws":74,"losses":93,"wins":516},"GB2-07":{"draws":0,"losses":207,"wins":491},"GB2-08":{"draws":467,"losses":208,"wins":5}},"medium":{"GB2-01":{"draws":102,"losses":372,"wins":293},"GB2-02":{"draws":557,"losses":109,"wins":14},"GB2-03":{"draws":257,"losses":296,"wins":178},"GB2-04":{"draws":455,"losses":125,"wins":84},"GB2-05":{"draws":0,"losses":382,"wins":347},"GB2-06":{"draws":30,"losses":321,"wins":420},"GB2-07":{"draws":0,"losses":495,"wins":197},"GB2-08":{"draws":408,"losses":244,"wins":32}},"none":{"GB2-01":{"draws":148,"losses":449,"wins":91},"GB2-02":{"draws":530,"losses":88,"wins":6},"GB2-03":{"draws":338,"losses":308,"wins":28},"GB2-04":{"draws":435,"losses":169,"wins":60},"GB2-05":{"draws":0,"losses":524,"wins":194},"GB2-06":{"draws":38,"losses":539,"wins":113},"GB2-07":{"draws":0,"losses":592,"wins":104},"GB2-08":{"draws":119,"losses":537,"wins":22}}},"per_game_raw_elo_all":{"GB2-01":1505.6957535828187,"GB2-02":1425.915073743469,"GB2-03":1338.185605409382,"GB2-04":1419.224846811442,"GB2-05":1342.9680334267894,"GB2-06":1525.187505416133,"GB2-07":1307.7249674482011,"GB2-08":1166.7775099498008},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1846.4805951963963,"GB2-02":1433.8472618420071,"GB2-03":1368.9094354256752,"GB2-04":1384.3210284778465,"GB2-05":1495.1413731250082,"GB2-06":2003.9713106067586,"GB2-07":1758.3781406110527,"GB2-08":1259.8411091994526},"medium":{"GB2-01":1453.694192788771,"GB2-02":1425.7689691396763,"GB2-03":1386.699902787815,"GB2-04":1468.547798114232,"GB2-05":1395.7919635540643,"GB2-06":1572.8750818206206,"GB2-07":1182.5652115828093,"GB2-08":1255.415501188037},"none":{"GB2-01":1216.9124727632886,"GB2-02":1418.1289902487229,"GB2-03":1258.9474780146559,"GB2-04":1404.8057138422475,"GB2-05":1137.9707636012959,"GB2-06":998.7161238210206,"GB2-07":982.2315501507419,"GB2-08":985.0759194619126}},"per_game_tracks":{"highest":{"GB2-01":65.28837516772396,"GB2-02":8.92542798143972,"GB2-03":20.437499812186967,"GB2-04":5.960904579118896,"GB2-05":45.61621744929189,"GB2-06":72.44602362696502,"GB2-07":60.59554150190553,"GB2-08":17.64452136559285},"medium":{"GB2-01":39.35678916597822,"GB2-02":7.910426685790982,"GB2-03":21.785926001413223,"GB2-04":17.26173017626782,"GB2-05":41.18295031281808,"GB2-06":53.08224926787175,"GB2-07":32.362124043151496,"GB2-08":17.360323301100944},"none":{"GB2-01":23.724563867837713,"GB2-02":6.950497557349113,"GB2-03":12.10294737051545,"GB2-04":8.70936397884353,"GB2-05":29.678198973348277,"GB2-06":27.292451615821726,"GB2-07":22.53930901223923,"GB2-08":0.0}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.1143139355281,"medium":28.787814869299062,"none":16.374666546994376},"reasoning_agg":{"highest":{"max":72.44602362696502,"mean":37.1143139355281,"min":5.960904579118896},"medium":{"max":53.08224926787175,"mean":28.787814869299062,"min":7.910426685790982},"none":{"max":29.678198973348277,"mean":16.374666546994376,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":72.44602362696502,"expected_score":24.45957977643864,"reasoning_variance":20.739647388533726,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.966018674168538},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.44602362696502,"expected_score":30.192276882940448,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.922037052587655},"medium":{"ceiling_score":53.08224926787175,"expected_score":27.433257576265877,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.354557293033185},"none":{"ceiling_score":29.678198973348277,"expected_score":15.753204870109592,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6214616768847847}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:ac228f4ce33a4444","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":29.02036128531404,"highest":35.729398019575285,"medium":27.265246855579484,"none":20.789414581788098},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T10:42:01Z","match_totals_all":{"draws":2473,"losses":3910,"wins":2308},"match_totals_tracks":{"highest":{"draws":624,"losses":1156,"wins":996},"medium":{"draws":831,"losses":1525,"wins":834},"none":{"draws":1018,"losses":1229,"wins":478}},"model_slug":"stealth-space-bunny-alpha","overall":{"max":62.67807618632012,"mean":26.322253879225908,"min":6.189998604271213},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.316561305083034,"GB2-04":6.6935138778335705,"GB2-05":41.91485661334857,"GB2-06":41.49789754464677,"GB2-07":62.67807618632012,"GB2-08":11.27548259021963},"per_game_all":{"GB2-04":9.20939799032129,"GB2-05":34.19863357435732,"GB2-07":43.6530522912635},"per_game_match_totals_all":{"GB2-01":{"draws":223,"losses":303,"wins":406},"GB2-02":{"draws":681,"losses":162,"wins":9},"GB2-03":{"draws":210,"losses":438,"wins":232},"GB2-04":{"draws":873,"losses":370,"wins":100},"GB2-05":{"draws":0,"losses":959,"wins":493},"GB2-06":{"draws":14,"losses":473,"wins":425},"GB2-07":{"draws":0,"losses":788,"wins":622},"GB2-08":{"draws":472,"losses":417,"wins":21}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":141,"losses":102,"wins":223},"GB2-04":{"draws":271,"losses":144,"wins":33},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":8,"losses":279,"wins":169},"GB2-07":{"draws":0,"losses":121,"wins":349},"GB2-08":{"draws":204,"losses":245,"wins":3}},"medium":{"GB2-01":{"draws":82,"losses":201,"wins":183},"GB2-02":{"draws":343,"losses":78,"wins":5},"GB2-03":{"draws":95,"losses":204,"wins":141},"GB2-04":{"draws":305,"losses":115,"wins":28},"GB2-05":{"draws":0,"losses":422,"wins":62},"GB2-06":{"draws":6,"losses":194,"wins":256},"GB2-07":{"draws":0,"losses":311,"wins":159}},"none":{"GB2-02":{"draws":338,"losses":84,"wins":4},"GB2-03":{"draws":115,"losses":234,"wins":91},"GB2-04":{"draws":297,"losses":111,"wins":39},"GB2-05":{"draws":0,"losses":272,"wins":212},"GB2-07":{"draws":0,"losses":356,"wins":114},"GB2-08":{"draws":268,"losses":172,"wins":18}}},"per_game_raw_elo_all":{"GB2-04":1408.532543279003,"GB2-05":1239.2735939494635,"GB2-07":1412.8406458440368},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1619.7021442282432,"GB2-04":1389.7812768557953,"GB2-05":1412.19396609091,"GB2-06":1314.9723481797841,"GB2-07":1800.8508734351078,"GB2-08":1160.6607397634368},"medium":{"GB2-01":1472.7932858092893,"GB2-02":1418.5439964742875,"GB2-03":1404.158263664729,"GB2-04":1411.2595736955545,"GB2-05":911.4148090553031,"GB2-06":1585.3311067422858,"GB2-07":1284.119807730516},"none":{"GB2-02":1412.076255962455,"GB2-03":1322.7958867154848,"GB2-04":1424.5567792856593,"GB2-05":1394.2120067021779,"GB2-07":1153.5512563664865,"GB2-08":1268.3792880423766}},"per_game_tracks":{"highest":{"GB2-01":50.316561305083034,"GB2-04":6.6935138778335705,"GB2-05":41.91485661334857,"GB2-06":41.49789754464677,"GB2-07":62.67807618632012,"GB2-08":11.27548259021963},"medium":{"GB2-01":40.61770290988866,"GB2-02":7.002641230792495,"GB2-03":23.10918022223782,"GB2-04":9.575287543827988,"GB2-05":19.56859618659,"GB2-06":53.641743041857005,"GB2-07":37.34157685386242},"none":{"GB2-02":6.189998604271213,"GB2-03":16.942329309173157,"GB2-04":11.359392549302314,"GB2-05":41.11244792313339,"GB2-07":30.93950383360797,"GB2-08":18.192815271240544}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.2499514098097,"medium":26.370080000167974,"none":19.346730227700046},"reasoning_agg":{"highest":{"max":62.67807618632012,"mean":33.2499514098097,"min":6.6935138778335705},"medium":{"max":53.641743041857005,"mean":26.370080000167974,"min":7.002641230792495},"none":{"max":41.11244792313339,"mean":19.346730227700046,"min":6.189998604271213}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":62.67807618632012,"expected_score":27.455596546093386,"reasoning_variance":13.90322118210965,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1333426668674775},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.67807618632012,"expected_score":27.497563504095464,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.752387905714233},"medium":{"ceiling_score":53.641743041857005,"expected_score":25.226156068622863,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.1439239315451104},"none":{"ceiling_score":41.11244792313339,"expected_score":23.601505326536998,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.2547750988369515}}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:417d288b9594825c","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":0.428104},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.167609}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.428104},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.167609},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40577}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":27.53403224943955,"highest":26.9315568398705,"medium":29.842192213398896,"none":22.244793421272327},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:04:45Z","match_totals_all":{"draws":3930,"losses":6419,"wins":3456},"match_totals_tracks":{"highest":{"draws":1678,"losses":2170,"wins":1293},"medium":{"draws":1087,"losses":1776,"wins":1429},"none":{"draws":1165,"losses":2473,"wins":734}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":68.34708969211397,"mean":25.769477835807407,"min":4.151492380492624},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":34.666336749470865,"GB2-02":5.179319528686556,"GB2-03":21.315924072005465,"GB2-04":7.144911089999672,"GB2-05":44.304502728843794,"GB2-06":28.045407919284656,"GB2-07":42.64670998078369,"GB2-08":32.1493426498893},"per_game_all":{"GB2-01":32.29771899249502,"GB2-03":21.757318396034606,"GB2-04":8.937076092210535,"GB2-05":36.654092160007046,"GB2-06":26.076082105476093,"GB2-08":39.48190575041401},"per_game_match_totals_all":{"GB2-01":{"draws":527,"losses":888,"wins":451},"GB2-02":{"draws":908,"losses":228,"wins":14},"GB2-03":{"draws":500,"losses":907,"wins":538},"GB2-04":{"draws":1251,"losses":431,"wins":126},"GB2-05":{"draws":0,"losses":1205,"wins":803},"GB2-06":{"draws":9,"losses":1491,"wins":316},"GB2-07":{"draws":0,"losses":841,"wins":493},"GB2-08":{"draws":735,"losses":428,"wins":715}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":277,"losses":225,"wins":124},"GB2-02":{"draws":461,"losses":106,"wins":5},"GB2-03":{"draws":204,"losses":294,"wins":171},"GB2-04":{"draws":399,"losses":156,"wins":37},"GB2-05":{"draws":0,"losses":363,"wins":355},"GB2-06":{"draws":2,"losses":482,"wins":122},"GB2-07":{"draws":0,"losses":397,"wins":307},"GB2-08":{"draws":335,"losses":147,"wins":172}},"medium":{"GB2-01":{"draws":93,"losses":265,"wins":268},"GB2-02":{"draws":447,"losses":122,"wins":9},"GB2-03":{"draws":139,"losses":318,"wins":155},"GB2-04":{"draws":405,"losses":156,"wins":51},"GB2-05":{"draws":0,"losses":317,"wins":339},"GB2-06":{"draws":1,"losses":518,"wins":85},"GB2-08":{"draws":2,"losses":80,"wins":522}},"none":{"GB2-01":{"draws":157,"losses":398,"wins":59},"GB2-03":{"draws":157,"losses":295,"wins":212},"GB2-04":{"draws":447,"losses":119,"wins":38},"GB2-05":{"draws":0,"losses":525,"wins":109},"GB2-06":{"draws":6,"losses":491,"wins":109},"GB2-07":{"draws":0,"losses":444,"wins":186},"GB2-08":{"draws":398,"losses":201,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1346.7702746914058,"GB2-03":1386.3224682097389,"GB2-04":1406.50288680993,"GB2-05":1294.3003616132414,"GB2-06":971.6360567330566,"GB2-08":1599.8986794528116},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1382.647788985315,"GB2-02":1404.032363372667,"GB2-03":1380.4989300893617,"GB2-04":1393.1456088399304,"GB2-05":1465.7458778863233,"GB2-06":1015.4792102340365,"GB2-07":1392.3165660280185,"GB2-08":1485.714052404388},"medium":{"GB2-01":1471.3572787711275,"GB2-02":1395.8519910065356,"GB2-03":1365.8264588629809,"GB2-04":1407.8781044381294,"GB2-05":1439.890214684082,"GB2-06":912.0072127114919,"GB2-08":2049.395017620197},"none":{"GB2-01":1186.3057563177756,"GB2-03":1412.6420156768745,"GB2-04":1418.4849471517307,"GB2-05":977.2649922693189,"GB2-06":987.4217472536415,"GB2-07":1184.790842359323,"GB2-08":1264.5869683338494}},"per_game_tracks":{"highest":{"GB2-01":34.666336749470865,"GB2-02":5.179319528686556,"GB2-03":21.315924072005465,"GB2-04":7.144911089999672,"GB2-05":44.304502728843794,"GB2-06":28.045407919284656,"GB2-07":42.64670998078369,"GB2-08":32.1493426498893},"medium":{"GB2-01":40.522898355095144,"GB2-02":4.151492380492624,"GB2-03":20.20382599950487,"GB2-04":9.121590999305948,"GB2-05":43.15074587753226,"GB2-06":23.397702189747463,"GB2-08":68.34708969211397},"none":{"GB2-01":21.703921872919057,"GB2-03":23.752205116593487,"GB2-04":10.544726187325988,"GB2-05":22.507027873645086,"GB2-06":26.78513620739616,"GB2-07":32.47125178178774,"GB2-08":17.949284909238777}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.9315568398705,"medium":28.86241962950287,"none":21.514457038048857},"reasoning_agg":{"highest":{"max":44.304502728843794,"mean":26.9315568398705,"min":5.179319528686556},"medium":{"max":68.34708969211397,"mean":28.86241962950287,"min":4.151492380492624},"none":{"max":32.47125178178774,"mean":21.514457038048857,"min":10.544726187325988}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":68.34708969211397,"expected_score":23.098198702806926,"reasoning_variance":7.347962591454014,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.671279133000482},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":44.304502728843794,"expected_score":17.80230806485562,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.12924877501488},"medium":{"ceiling_score":68.34708969211397,"expected_score":27.031215748311844,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8312038811910263},"none":{"ceiling_score":32.47125178178774,"expected_score":22.14222566811315,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.627768630064292}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:c772c6115b8fc654","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":0.48605810000000005},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713908},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1134224}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713907999999997},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.11342239999999999},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":46},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.11219570000000001,"mean":0.030692482499999996,"median":0.01928415,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":46,"run_count":24,"total":0.73661958},"codegen_latency_ms":{"attempt_count":46,"max_ms":511905,"mean_ms":147013.95833333334,"min_ms":23584,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":20,"max_ms":511905,"mean_ms":284845.75,"min_ms":132388,"run_count":8},"medium":{"attempt_count":13,"max_ms":348782,"mean_ms":92838.875,"min_ms":39705,"run_count":8},"none":{"attempt_count":13,"max_ms":194018,"mean_ms":63357.25,"min_ms":23584,"run_count":8}},"codegen_output_tokens":{"attempt_count":46,"output_max":93362,"output_mean":24067.583333333332,"output_min":4359,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":93362,"output_mean":49316.75,"output_min":16213,"run_count":8},"medium":{"attempt_count":13,"output_max":33638,"output_mean":12726.0,"output_min":7627,"run_count":8},"none":{"attempt_count":13,"output_max":17245,"output_mean":10160.0,"output_min":4359,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":31.685241043150864,"highest":26.059699297957046,"medium":28.32679002383982,"none":25.268427312551555},"first_seen_at":"2026-10-13T14:01:51Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[230400],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":46,"output_token_observations":46,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[230400],"total_output_tokens":577622,"total_visible_output_tokens":183088,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-05","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"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":true,"last_measured_at":"2026-10-13T14:01:51Z","match_totals_all":{"draws":1678,"losses":4589,"wins":1942},"match_totals_tracks":{"highest":{"draws":454,"losses":1880,"wins":633},"medium":{"draws":337,"losses":1504,"wins":697},"none":{"draws":887,"losses":1205,"wins":612}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":47.53375051962658,"mean":24.348894341520094,"min":7.529798998614494},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":48,"overall_ranking_status":"ranked","per_game":{"GB2-01":7.907149345885936,"GB2-05":38.368664996195854,"GB2-06":36.14716551413063,"GB2-07":29.585543398061688,"GB2-08":18.28997323551113},"per_game_all":{"GB2-01":15.634171979899705,"GB2-06":42.75772678117585,"GB2-07":36.66382436837704},"per_game_match_totals_all":{"GB2-01":{"draws":190,"losses":1154,"wins":156},"GB2-02":{"draws":344,"losses":73,"wins":9},"GB2-03":{"draws":266,"losses":459,"wins":155},"GB2-04":{"draws":288,"losses":131,"wins":27},"GB2-05":{"draws":0,"losses":588,"wins":494},"GB2-06":{"draws":57,"losses":867,"wins":574},"GB2-07":{"draws":0,"losses":1032,"wins":511},"GB2-08":{"draws":533,"losses":285,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":492,"wins":40},"GB2-05":{"draws":0,"losses":351,"wins":247},"GB2-06":{"draws":15,"losses":387,"wins":184},"GB2-07":{"draws":0,"losses":454,"wins":149},"GB2-08":{"draws":403,"losses":196,"wins":13}},"medium":{"GB2-01":{"draws":66,"losses":388,"wins":12},"GB2-03":{"draws":129,"losses":240,"wins":71},"GB2-05":{"draws":0,"losses":237,"wins":247},"GB2-06":{"draws":12,"losses":255,"wins":189},"GB2-07":{"draws":0,"losses":295,"wins":175},"GB2-08":{"draws":130,"losses":89,"wins":3}},"none":{"GB2-01":{"draws":88,"losses":274,"wins":104},"GB2-02":{"draws":344,"losses":73,"wins":9},"GB2-03":{"draws":137,"losses":219,"wins":84},"GB2-04":{"draws":288,"losses":131,"wins":27},"GB2-06":{"draws":30,"losses":225,"wins":201},"GB2-07":{"draws":0,"losses":283,"wins":187}}},"per_game_raw_elo_all":{"GB2-01":1094.3670980408526,"GB2-06":1343.0199603193648,"GB2-07":1270.2972287106847},"per_game_raw_elo_tracks":{"highest":{"GB2-01":977.3256867853962,"GB2-05":1332.7238975062814,"GB2-06":1195.8488572309504,"GB2-07":1125.937598709945,"GB2-08":1269.8922577588223},"medium":{"GB2-01":994.4490276936087,"GB2-03":1295.083234671676,"GB2-05":1483.5156176357552,"GB2-06":1383.862318605384,"GB2-07":1326.8216573350821,"GB2-08":1249.122563334752},"none":{"GB2-01":1311.326579643553,"GB2-02":1426.8260664071418,"GB2-03":1331.1488658556495,"GB2-04":1396.0142368827267,"GB2-06":1449.3487051217596,"GB2-07":1358.1324300870274}},"per_game_tracks":{"highest":{"GB2-01":7.907149345885936,"GB2-05":38.368664996195854,"GB2-06":36.14716551413063,"GB2-07":29.585543398061688,"GB2-08":18.28997323551113},"medium":{"GB2-01":9.037624801952548,"GB2-03":14.841852406114926,"GB2-05":45.097441545441335,"GB2-06":44.59226430977032,"GB2-07":39.43534565509667,"GB2-08":16.9562114246631},"none":{"GB2-01":29.957741791860627,"GB2-02":8.043246222745195,"GB2-03":17.575442290489683,"GB2-04":7.529798998614494,"GB2-06":47.53375051962658,"GB2-07":40.97058405197277}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.170713346681392,"medium":26.361048438950217,"none":23.51492123892869},"reasoning_agg":{"highest":{"max":38.368664996195854,"mean":23.170713346681392,"min":7.907149345885936},"medium":{"max":45.097441545441335,"mean":26.361048438950217,"min":9.037624801952548},"none":{"max":47.53375051962658,"mean":23.51492123892869,"min":7.529798998614494}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"ceiling_score":47.53375051962658,"expected_score":25.91717076691032,"reasoning_variance":3.1903350922688247,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.568276425390227},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":38.368664996195854,"expected_score":14.845005144777659,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.325708201903733},"medium":{"ceiling_score":45.097441545441335,"expected_score":25.340424723850816,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0206237150994006},"none":{"ceiling_score":47.53375051962658,"expected_score":27.308638040883423,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7937168019547336}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:bc29f998e211af2f","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":0.050973330659999996},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.010671596920000002},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.058475471099999995}},"codegen_cost_usd":{"admitted_cell_count":36,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749804},"codegen_latency_ms":{"attempt_count":35,"max_ms":2156476,"mean_ms":402937.5,"min_ms":36579,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":2156476,"mean_ms":830597.625,"min_ms":100447,"run_count":8},"medium":{"attempt_count":12,"max_ms":572210,"mean_ms":258473.0,"min_ms":66883,"run_count":8},"none":{"attempt_count":10,"max_ms":286097,"mean_ms":119741.875,"min_ms":36579,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":54472,"output_mean":14159.166666666666,"output_min":1979,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":47250,"output_mean":26393.0,"output_min":7308,"run_count":8},"medium":{"attempt_count":12,"output_max":54472,"output_mean":12951.25,"output_min":5048,"run_count":8},"none":{"attempt_count":10,"output_max":4856,"output_mean":3133.25,"output_min":1979,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":25.241839774220548,"highest":25.561125581933336,"medium":23.83566673376292,"none":25.450508634286614},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:25:31Z","match_totals_all":{"draws":6345,"losses":10617,"wins":4733},"match_totals_tracks":{"highest":{"draws":1570,"losses":1789,"wins":985},"medium":{"draws":3640,"losses":6601,"wins":2716},"none":{"draws":1135,"losses":2227,"wins":1032}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":72.08329545434546,"mean":24.129976697714465,"min":4.824310060026545},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":16.06601269092718,"GB2-02":7.29540922829488,"GB2-03":15.546612097632453,"GB2-04":10.68787306441979,"GB2-06":72.08329545434546,"GB2-07":39.633342532242,"GB2-08":17.615334005671574},"per_game_all":{"GB2-01":22.957823688601426,"GB2-02":6.227638124488646,"GB2-03":17.738732320933213,"GB2-06":53.39732072635021,"GB2-07":32.360764966928556,"GB2-08":18.768758818021215},"per_game_match_totals_all":{"GB2-01":{"draws":512,"losses":1863,"wins":639},"GB2-02":{"draws":2202,"losses":552,"wins":50},"GB2-03":{"draws":789,"losses":1031,"wins":495},"GB2-04":{"draws":1211,"losses":498,"wins":143},"GB2-05":{"draws":0,"losses":1644,"wins":886},"GB2-06":{"draws":83,"losses":1688,"wins":1343},"GB2-07":{"draws":0,"losses":2219,"wins":863},"GB2-08":{"draws":1548,"losses":1122,"wins":314}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":145,"losses":440,"wins":25},"GB2-02":{"draws":438,"losses":97,"wins":25},"GB2-03":{"draws":209,"losses":292,"wins":101},"GB2-04":{"draws":380,"losses":195,"wins":81},"GB2-06":{"draws":42,"losses":102,"wins":458},"GB2-07":{"draws":0,"losses":435,"wins":261},"GB2-08":{"draws":356,"losses":228,"wins":34}},"medium":{"GB2-01":{"draws":219,"losses":1014,"wins":561},"GB2-02":{"draws":1267,"losses":341,"wins":20},"GB2-03":{"draws":377,"losses":448,"wins":284},"GB2-04":{"draws":831,"losses":303,"wins":62},"GB2-05":{"draws":0,"losses":1312,"wins":568},"GB2-06":{"draws":20,"losses":1288,"wins":512},"GB2-07":{"draws":0,"losses":1285,"wins":483},"GB2-08":{"draws":926,"losses":610,"wins":226}},"none":{"GB2-01":{"draws":148,"losses":409,"wins":53},"GB2-02":{"draws":497,"losses":114,"wins":5},"GB2-03":{"draws":203,"losses":291,"wins":110},"GB2-05":{"draws":0,"losses":332,"wins":318},"GB2-06":{"draws":21,"losses":298,"wins":373},"GB2-07":{"draws":0,"losses":499,"wins":119},"GB2-08":{"draws":266,"losses":284,"wins":54}}},"per_game_raw_elo_all":{"GB2-01":1205.2986394804605,"GB2-02":1412.3758250987655,"GB2-03":1333.3032336515134,"GB2-06":1579.8895261654768,"GB2-07":1182.5374935900497,"GB2-08":1277.3480344668553},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1100.9082004356778,"GB2-02":1420.8741073695528,"GB2-03":1304.3814850247702,"GB2-04":1419.5518425690168,"GB2-06":1995.8958835546277,"GB2-07":1330.8597502062003,"GB2-08":1259.3865958510573},"medium":{"GB2-01":1346.7691335829495,"GB2-02":1401.2068789006482,"GB2-03":1383.9911791172683,"GB2-04":1401.9091173348245,"GB2-05":1204.2915784788843,"GB2-06":1179.4544085831778,"GB2-07":1166.732991172376,"GB2-08":1359.2432969577376},"none":{"GB2-01":1168.2185844227538,"GB2-02":1415.046489026096,"GB2-03":1311.5370368125016,"GB2-05":1408.8901220325902,"GB2-06":1564.3182863586242,"GB2-07":1050.0197393915726,"GB2-08":1213.4142105917715}},"per_game_tracks":{"highest":{"GB2-01":16.06601269092718,"GB2-02":7.29540922829488,"GB2-03":15.546612097632453,"GB2-04":10.68787306441979,"GB2-06":72.08329545434546,"GB2-07":39.633342532242,"GB2-08":17.615334005671574},"medium":{"GB2-01":32.29764365701523,"GB2-02":4.824310060026545,"GB2-03":21.580618638633354,"GB2-04":8.320723501510564,"GB2-05":32.637631649704765,"GB2-06":35.41076750561383,"GB2-07":31.585834269837203,"GB2-08":24.0278045877619},"none":{"GB2-01":20.50981471786187,"GB2-02":6.563195085144512,"GB2-03":16.088966226533827,"GB2-05":41.76742923203812,"GB2-06":52.69789921909132,"GB2-07":25.863118098706465,"GB2-08":14.663137860630172}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.721908078084635,"medium":23.05309913224007,"none":24.61492288281869},"reasoning_agg":{"highest":{"max":72.08329545434546,"mean":24.721908078084635,"min":7.29540922829488},"medium":{"max":35.41076750561383,"mean":23.05309913224007,"min":4.824310060026545},"none":{"max":52.69789921909132,"mean":24.61492288281869,"min":6.563195085144512}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":72.08329545434546,"expected_score":21.30908116962478,"reasoning_variance":1.6688089458445639,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.820895528089686},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.08329545434546,"expected_score":18.001511155061827,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.720396923022808},"medium":{"ceiling_score":35.41076750561383,"expected_score":20.781226400308668,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.2718727319314027},"none":{"ceiling_score":52.69789921909132,"expected_score":26.848205141599426,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2332822587807364}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:f78f5f2f111ce853","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093000000001},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"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":24.538057589529092,"highest":25.30703707117162,"medium":20.386243961040606,"none":27.920891736375047},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:58:20Z","match_totals_all":{"draws":9123,"losses":15150,"wins":7409},"match_totals_tracks":{"highest":{"draws":2320,"losses":4743,"wins":2634},"medium":{"draws":3324,"losses":5441,"wins":1638},"none":{"draws":3479,"losses":4966,"wins":3137}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":53.55700279946784,"mean":23.889034035306736,"min":5.327317945856828},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":50,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.271584260722413,"GB2-02":9.72021824724196,"GB2-03":24.496760353872226,"GB2-04":8.025177666342291,"GB2-05":24.730432284854338,"GB2-06":43.57912582239048,"GB2-07":42.722353070744546,"GB2-08":17.910644863204702},"per_game_all":{"GB2-01":33.56486885374162,"GB2-02":7.748573322635207,"GB2-03":23.86986363199023,"GB2-04":11.324530667322955,"GB2-05":21.169120676025045,"GB2-06":39.76604756534346,"GB2-07":40.899281962885894,"GB2-08":17.962174036288303},"per_game_match_totals_all":{"GB2-01":{"draws":757,"losses":2049,"wins":1155},"GB2-02":{"draws":2282,"losses":423,"wins":60},"GB2-03":{"draws":965,"losses":1548,"wins":1192},"GB2-04":{"draws":2682,"losses":1057,"wins":521},"GB2-05":{"draws":0,"losses":3869,"wins":771},"GB2-06":{"draws":88,"losses":2832,"wins":1736},"GB2-07":{"draws":0,"losses":2104,"wins":1815},"GB2-08":{"draws":2349,"losses":1268,"wins":159}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":160,"losses":391,"wins":179},"GB2-02":{"draws":516,"losses":119,"wins":49},"GB2-03":{"draws":254,"losses":647,"wins":563},"GB2-04":{"draws":870,"losses":406,"wins":140},"GB2-05":{"draws":0,"losses":1213,"wins":319},"GB2-06":{"draws":60,"losses":838,"wins":644},"GB2-07":{"draws":0,"losses":880,"wins":709},"GB2-08":{"draws":460,"losses":249,"wins":31}},"medium":{"GB2-01":{"draws":290,"losses":838,"wins":533},"GB2-02":{"draws":633,"losses":93,"wins":5},"GB2-03":{"draws":534,"losses":591,"wins":303},"GB2-04":{"draws":923,"losses":274,"wins":106},"GB2-05":{"draws":0,"losses":1288,"wins":264},"GB2-06":{"draws":10,"losses":1266,"wins":204},"GB2-07":{"draws":0,"losses":591,"wins":159},"GB2-08":{"draws":934,"losses":500,"wins":64}},"none":{"GB2-01":{"draws":307,"losses":820,"wins":443},"GB2-02":{"draws":1133,"losses":211,"wins":6},"GB2-03":{"draws":177,"losses":310,"wins":326},"GB2-04":{"draws":889,"losses":377,"wins":275},"GB2-05":{"draws":0,"losses":1368,"wins":188},"GB2-06":{"draws":18,"losses":728,"wins":888},"GB2-07":{"draws":0,"losses":633,"wins":947},"GB2-08":{"draws":955,"losses":519,"wins":64}}},"per_game_raw_elo_all":{"GB2-01":1365.963826342156,"GB2-02":1424.4807945845953,"GB2-03":1414.1943438612186,"GB2-04":1424.2969483841625,"GB2-05":947.282524249133,"GB2-06":1276.416125562451,"GB2-07":1356.6782432241396,"GB2-08":1264.7876812557777},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1331.2273854268874,"GB2-02":1440.1729172196292,"GB2-03":1422.4653087528704,"GB2-04":1399.7063693354226,"GB2-05":1027.0914314824472,"GB2-06":1361.3067892417382,"GB2-07":1393.859286432119,"GB2-08":1263.9852552377536},"medium":{"GB2-01":1402.165912070213,"GB2-02":1428.059198720866,"GB2-03":1352.228841944519,"GB2-04":1418.4283017649163,"GB2-05":959.8644278111424,"GB2-06":904.7998163532985,"GB2-07":1061.3463998028399,"GB2-08":1265.431442690809},"none":{"GB2-01":1364.498181529368,"GB2-02":1405.2102678132906,"GB2-03":1467.8888808862664,"GB2-04":1454.7561740521485,"GB2-05":854.8917134538092,"GB2-06":1563.1417710923165,"GB2-07":1614.8290434374599,"GB2-08":1264.9463458387704}},"per_game_tracks":{"highest":{"GB2-01":31.271584260722413,"GB2-02":9.72021824724196,"GB2-03":24.496760353872226,"GB2-04":8.025177666342291,"GB2-05":24.730432284854338,"GB2-06":43.57912582239048,"GB2-07":42.722353070744546,"GB2-08":17.910644863204702},"medium":{"GB2-01":35.95491467443538,"GB2-02":8.198183774806834,"GB2-03":19.173196371250153,"GB2-04":10.537125995130154,"GB2-05":21.730562760247082,"GB2-06":23.07396380495672,"GB2-07":26.418490018445294,"GB2-08":18.003514289053232},"none":{"GB2-01":33.46810762606708,"GB2-02":5.327317945856828,"GB2-03":27.93963417084832,"GB2-04":15.411288340496423,"GB2-05":17.046366982973712,"GB2-06":52.6450530686832,"GB2-07":53.55700279946784,"GB2-08":17.972362956606972}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.476161747915658,"medium":19.71692708315134,"none":27.4740132748532},"reasoning_agg":{"highest":{"max":43.57912582239048,"mean":24.476161747915658,"min":8.025177666342291},"medium":{"max":35.95491467443538,"mean":19.71692708315134,"min":8.198183774806834},"none":{"max":53.55700279946784,"mean":27.4740132748532,"min":5.327317945856828}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":53.55700279946784,"expected_score":20.91185444872661,"reasoning_variance":7.757086191701859,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9771795865801245},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":43.57912582239048,"expected_score":16.15222558847901,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.323936159436649},"medium":{"ceiling_score":35.95491467443538,"expected_score":16.055702510175184,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.661224572976156},"none":{"ceiling_score":53.55700279946784,"expected_score":30.527635247525637,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.0536219726724383}}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:7bf75f6ebf97c516","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":0.38919240000000005},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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":31.584743489424355,"highest":21.21496162785461,"medium":27.306870578632083,"none":24.24839399243506},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:11:04Z","match_totals_all":{"draws":4126,"losses":5556,"wins":2307},"match_totals_tracks":{"highest":{"draws":2104,"losses":2254,"wins":757},"medium":{"draws":948,"losses":1288,"wins":680},"none":{"draws":1074,"losses":2014,"wins":870}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":53.043544898222066,"mean":21.573194604061012,"min":5.238006517271569},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":51,"overall_ranking_status":"partial","per_game":{"GB2-01":24.923946358344672,"GB2-02":5.238006517271569,"GB2-04":8.972558745985577,"GB2-05":32.662233762007475,"GB2-06":37.10108826675588,"GB2-08":18.3919361167625},"per_game_all":{"GB2-01":38.03514517518112,"GB2-06":38.21428975287679,"GB2-08":18.504795540215156},"per_game_match_totals_all":{"GB2-01":{"draws":332,"losses":777,"wins":601},"GB2-02":{"draws":1287,"losses":301,"wins":16},"GB2-03":{"draws":223,"losses":248,"wins":47},"GB2-04":{"draws":812,"losses":254,"wins":66},"GB2-05":{"draws":0,"losses":1014,"wins":752},"GB2-06":{"draws":64,"losses":1066,"wins":591},"GB2-07":{"draws":0,"losses":1079,"wins":99},"GB2-08":{"draws":1408,"losses":817,"wins":135}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":123,"losses":352,"wins":93},"GB2-02":{"draws":832,"losses":206,"wins":14},"GB2-04":{"draws":411,"losses":134,"wins":27},"GB2-05":{"draws":0,"losses":785,"wins":389},"GB2-06":{"draws":35,"losses":365,"wins":171},"GB2-08":{"draws":703,"losses":412,"wins":63}},"medium":{"GB2-01":{"draws":117,"losses":204,"wins":257},"GB2-02":{"draws":455,"losses":95,"wins":2},"GB2-06":{"draws":24,"losses":239,"wins":323},"GB2-07":{"draws":0,"losses":537,"wins":63},"GB2-08":{"draws":352,"losses":213,"wins":35}},"none":{"GB2-01":{"draws":92,"losses":221,"wins":251},"GB2-03":{"draws":223,"losses":248,"wins":47},"GB2-04":{"draws":401,"losses":120,"wins":39},"GB2-05":{"draws":0,"losses":229,"wins":363},"GB2-06":{"draws":5,"losses":462,"wins":97},"GB2-07":{"draws":0,"losses":542,"wins":36},"GB2-08":{"draws":353,"losses":192,"wins":37}}},"per_game_raw_elo_all":{"GB2-01":1433.6752171513417,"GB2-06":1241.869299693781,"GB2-08":1273.2375279471628},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1235.0795503005133,"GB2-02":1404.499447181959,"GB2-04":1406.7673444179081,"GB2-05":1204.842911222035,"GB2-06":1217.0860651008575,"GB2-08":1271.4800509232123},"medium":{"GB2-01":1536.1781867257114,"GB2-02":1406.6311246626096,"GB2-06":1572.013405399273,"GB2-07":830.2381807518533,"GB2-08":1266.8699581647113},"none":{"GB2-01":1529.7679144278006,"GB2-03":1267.8325640797739,"GB2-04":1419.8768938990997,"GB2-05":1602.518535901142,"GB2-06":936.5084285812128,"GB2-07":684.059099022533,"GB2-08":1281.3625747535655}},"per_game_tracks":{"highest":{"GB2-01":24.923946358344672,"GB2-02":5.238006517271569,"GB2-04":8.972558745985577,"GB2-05":32.662233762007475,"GB2-06":37.10108826675588,"GB2-08":18.3919361167625},"medium":{"GB2-01":44.8023462663065,"GB2-02":5.505842245004128,"GB2-06":53.043544898222066,"GB2-07":15.086728438121996,"GB2-08":18.09589104550572},"none":{"GB2-01":44.3791429008922,"GB2-03":12.776391327880562,"GB2-04":10.731485664157935,"GB2-05":50.40770689043755,"GB2-06":24.498236093652412,"GB2-07":7.9192356116474665,"GB2-08":19.026559458377253}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":18.372695710034158,"medium":23.57511422891635,"none":22.771773873232526},"reasoning_agg":{"highest":{"max":37.10108826675588,"mean":18.372695710034158,"min":5.238006517271569},"medium":{"max":53.043544898222066,"mean":23.57511422891635,"min":5.505842245004128},"none":{"max":50.40770689043755,"mean":22.771773873232526,"min":7.9192356116474665}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":53.043544898222066,"expected_score":27.192188745492967,"reasoning_variance":5.20241851888219,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.618994141431955},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.10108826675588,"expected_score":12.95908214852153,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.413613561512628},"medium":{"ceiling_score":53.043544898222066,"expected_score":23.664093682841134,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.0889794539247859},"none":{"ceiling_score":50.40770689043755,"expected_score":25.79777427197185,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.026000398739324}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:77cc296015f7d9bb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.058501660000000004},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":23.757216122308165,"highest":25.032915649335685,"medium":20.57237888639679,"none":21.340272680659208},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:14:48Z","match_totals_all":{"draws":4462,"losses":6204,"wins":2418},"match_totals_tracks":{"highest":{"draws":1649,"losses":1758,"wins":1041},"medium":{"draws":1621,"losses":2505,"wins":758},"none":{"draws":1192,"losses":1941,"wins":619}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":43.96158623084151,"mean":21.547593520193768,"min":7.007464160245011},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-01":28.764656186998746,"GB2-02":7.007464160245011,"GB2-03":17.542105899973865,"GB2-04":17.167580682130865,"GB2-05":42.59294266521473,"GB2-07":43.96158623084151,"GB2-08":18.1940737199451},"per_game_all":{"GB2-01":28.040962286193064,"GB2-03":19.0166556743485,"GB2-04":14.103667452786821,"GB2-05":25.50407528270865,"GB2-07":37.76600937974229,"GB2-08":18.111926658069645},"per_game_match_totals_all":{"GB2-01":{"draws":451,"losses":1055,"wins":355},"GB2-02":{"draws":988,"losses":155,"wins":7},"GB2-03":{"draws":612,"losses":803,"wins":420},"GB2-04":{"draws":1256,"losses":423,"wins":231},"GB2-05":{"draws":0,"losses":1507,"wins":481},"GB2-06":{"draws":3,"losses":508,"wins":109},"GB2-07":{"draws":0,"losses":1179,"wins":731},"GB2-08":{"draws":1152,"losses":574,"wins":84}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":182,"losses":324,"wins":107},"GB2-02":{"draws":488,"losses":79,"wins":5},"GB2-03":{"draws":221,"losses":273,"wins":117},"GB2-04":{"draws":380,"losses":156,"wins":122},"GB2-05":{"draws":0,"losses":387,"wins":333},"GB2-07":{"draws":0,"losses":347,"wins":325},"GB2-08":{"draws":378,"losses":192,"wins":32}},"medium":{"GB2-01":{"draws":134,"losses":403,"wins":77},"GB2-02":{"draws":500,"losses":76,"wins":2},"GB2-03":{"draws":176,"losses":288,"wins":148},"GB2-04":{"draws":423,"losses":119,"wins":60},"GB2-05":{"draws":0,"losses":531,"wins":103},"GB2-06":{"draws":3,"losses":508,"wins":109},"GB2-07":{"draws":0,"losses":387,"wins":233},"GB2-08":{"draws":385,"losses":193,"wins":26}},"none":{"GB2-01":{"draws":135,"losses":328,"wins":171},"GB2-03":{"draws":215,"losses":242,"wins":155},"GB2-04":{"draws":453,"losses":148,"wins":49},"GB2-05":{"draws":0,"losses":589,"wins":45},"GB2-07":{"draws":0,"losses":445,"wins":173},"GB2-08":{"draws":389,"losses":189,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1282.2930710031967,"GB2-03":1350.1635215129472,"GB2-04":1445.0102769640073,"GB2-05":1044.428752399376,"GB2-07":1292.7759945438472,"GB2-08":1267.1196689977453},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1293.2548811957035,"GB2-02":1418.5823816822347,"GB2-03":1330.7090420283005,"GB2-04":1467.8460876342422,"GB2-05":1427.3898581536605,"GB2-07":1419.1331122701283,"GB2-08":1268.3988849410352},"medium":{"GB2-01":1197.0815710187753,"GB2-02":1419.0360972585681,"GB2-03":1342.5881951552428,"GB2-04":1438.186562903837,"GB2-05":959.486174943549,"GB2-06":973.265014868969,"GB2-07":1288.1605091502531,"GB2-08":1266.4042044934065},"none":{"GB2-01":1356.5427607951112,"GB2-03":1377.1933273552986,"GB2-04":1428.9981803539433,"GB2-05":746.4102241009186,"GB2-07":1171.0343622111604,"GB2-08":1266.5559175587937}},"per_game_tracks":{"highest":{"GB2-01":28.764656186998746,"GB2-02":7.007464160245011,"GB2-03":17.542105899973865,"GB2-04":17.167580682130865,"GB2-05":42.59294266521473,"GB2-07":43.96158623084151,"GB2-08":18.1940737199451},"medium":{"GB2-01":22.415336432957364,"GB2-02":7.064471490234629,"GB2-03":18.442484785819577,"GB2-04":13.188120022299984,"GB2-05":21.713683988501774,"GB2-06":26.14925086845283,"GB2-07":37.53970163407906,"GB2-08":18.065981868829112},"none":{"GB2-01":32.94289423862308,"GB2-03":21.065376337252058,"GB2-04":11.955301653929615,"GB2-05":12.205599194409452,"GB2-07":31.796740274306313,"GB2-08":18.075724385434732}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.211040222999255,"medium":20.57237888639679,"none":19.859361451185247},"reasoning_agg":{"highest":{"max":43.96158623084151,"mean":24.211040222999255,"min":7.007464160245011},"medium":{"max":37.53970163407906,"mean":20.57237888639679,"min":7.064471490234629},"none":{"max":32.94289423862308,"mean":19.859361451185247,"min":11.955301653929615}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":43.96158623084151,"expected_score":20.948017088039368,"reasoning_variance":4.351678771814008,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.5995764321544002},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":43.96158623084151,"expected_score":17.494561820055505,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.71647840294375},"medium":{"ceiling_score":37.53970163407906,"expected_score":16.55929367447828,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.013085211918511},"none":{"ceiling_score":32.94289423862308,"expected_score":22.67493298436581,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.815571533180563}}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:62cf2f5dff5e8c28","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.05953976200000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085672999999999},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085672999999999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855891},"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":21.12634618168869,"highest":24.53539209377649,"medium":20.29237373927545,"none":21.838094120702237},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T10:32:26Z","match_totals_all":{"draws":4187,"losses":6379,"wins":2370},"match_totals_tracks":{"highest":{"draws":1413,"losses":1891,"wins":957},"medium":{"draws":1623,"losses":2579,"wins":754},"none":{"draws":1151,"losses":1909,"wins":659}},"model_slug":"openai-gpt-oss-120b","overall":{"max":49.483388626900904,"mean":21.4482871659332,"min":6.689787948048205},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":53,"overall_ranking_status":"ranked","per_game":{"GB2-02":9.062531326080022,"GB2-03":22.547043938295452,"GB2-04":11.283686936484148,"GB2-05":49.483388626900904,"GB2-06":29.292687958881917,"GB2-07":35.045335558543144,"GB2-08":15.033070311249858},"per_game_all":{"GB2-02":7.754076094524907,"GB2-03":18.704162620626217,"GB2-05":31.19695829521723,"GB2-07":31.4596389728358,"GB2-08":16.51689492523929},"per_game_match_totals_all":{"GB2-01":{"draws":239,"losses":698,"wins":403},"GB2-02":{"draws":1428,"losses":248,"wins":20},"GB2-03":{"draws":537,"losses":836,"wins":435},"GB2-04":{"draws":850,"losses":326,"wins":90},"GB2-05":{"draws":0,"losses":1346,"wins":566},"GB2-06":{"draws":14,"losses":910,"wins":284},"GB2-07":{"draws":0,"losses":1341,"wins":519},"GB2-08":{"draws":1119,"losses":674,"wins":53}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":454,"losses":96,"wins":16},"GB2-03":{"draws":185,"losses":240,"wins":178},"GB2-04":{"draws":400,"losses":135,"wins":59},"GB2-05":{"draws":0,"losses":289,"wins":355},"GB2-06":{"draws":3,"losses":469,"wins":132},"GB2-07":{"draws":0,"losses":413,"wins":209},"GB2-08":{"draws":371,"losses":249,"wins":8}},"medium":{"GB2-01":{"draws":122,"losses":339,"wins":177},"GB2-02":{"draws":480,"losses":81,"wins":3},"GB2-03":{"draws":189,"losses":295,"wins":120},"GB2-04":{"draws":450,"losses":191,"wins":31},"GB2-05":{"draws":0,"losses":530,"wins":104},"GB2-06":{"draws":11,"losses":441,"wins":152},"GB2-07":{"draws":0,"losses":490,"wins":130},"GB2-08":{"draws":371,"losses":212,"wins":37}},"none":{"GB2-01":{"draws":117,"losses":359,"wins":226},"GB2-02":{"draws":494,"losses":71,"wins":1},"GB2-03":{"draws":163,"losses":301,"wins":137},"GB2-05":{"draws":0,"losses":527,"wins":107},"GB2-07":{"draws":0,"losses":438,"wins":180},"GB2-08":{"draws":377,"losses":213,"wins":8}}},"per_game_raw_elo_all":{"GB2-02":1424.5245905897725,"GB2-03":1346.0406429174702,"GB2-05":1172.0061233626438,"GB2-07":1164.1592721494442,"GB2-08":1242.2814097087658},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1434.9384535017823,"GB2-03":1396.7417159200654,"GB2-04":1423.9925338545445,"GB2-05":1581.8045859154784,"GB2-06":1043.2474392651757,"GB2-07":1237.2885862552907,"GB2-08":1219.1748973159124},"medium":{"GB2-01":1353.502430774998,"GB2-02":1416.0540288242678,"GB2-03":1317.4204310794778,"GB2-04":1393.1213504147013,"GB2-05":962.8343233724171,"GB2-06":1101.2149048374115,"GB2-07":1069.0314992416613,"GB2-08":1275.8979039802978},"none":{"GB2-01":1400.780638423022,"GB2-02":1422.5812894432675,"GB2-03":1323.9597817528675,"GB2-05":971.3794608000364,"GB2-07":1186.1577309513802,"GB2-08":1231.7714278300873}},"per_game_tracks":{"highest":{"GB2-02":9.062531326080022,"GB2-03":22.547043938295452,"GB2-04":11.283686936484148,"GB2-05":49.483388626900904,"GB2-06":29.292687958881917,"GB2-07":35.045335558543144,"GB2-08":15.033070311249858},"medium":{"GB2-01":32.74217298425431,"GB2-02":6.689787948048205,"GB2-03":16.53489733950826,"GB2-04":7.141656302549557,"GB2-05":21.863088363040486,"GB2-06":31.896442871491292,"GB2-07":26.79530792184746,"GB2-08":18.675636183464025},"none":{"GB2-01":35.86345951586091,"GB2-02":7.509909009446497,"GB2-03":17.030546584074948,"GB2-05":22.24439789571029,"GB2-07":32.538273438116796,"GB2-08":15.841978281003987}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.729851256269647,"medium":20.29237373927545,"none":20.322636502254493},"reasoning_agg":{"highest":{"max":49.483388626900904,"mean":23.729851256269647,"min":9.062531326080022},"medium":{"max":32.74217298425431,"mean":20.29237373927545,"min":6.689787948048205},"none":{"max":35.86345951586091,"mean":20.322636502254493,"min":7.509909009446497}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":49.483388626900904,"expected_score":17.758274181224643,"reasoning_variance":3.4374775169941962,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.690012984708556},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.483388626900904,"expected_score":13.698429057186845,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.031422199082803},"medium":{"ceiling_score":32.74217298425431,"expected_score":16.516707094632533,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.775666644642918},"none":{"ceiling_score":35.86345951586091,"expected_score":22.83544429083119,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.5128077885766977}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:bafcffdaa4610350","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.3876148499999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373186},"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":21.69468318345187,"highest":25.682137219270132,"medium":19.83213206288376,"none":19.56978026820172},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":43,"finish_reasons":["stop"],"indexed_attempts":43,"output_token_observations":43,"provider_post_attempt_observations":43,"provider_post_attempts":43,"reasoning_token_observations":43,"reconciliation_get_attempt_observations":43,"reconciliation_get_attempts":203,"total_output_tokens":327143,"total_reasoning_output_tokens":261125,"total_visible_output_tokens":66018,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling-small","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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"],"first_pass_admitted":6,"first_pass_rate":0.6666666666666666,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-13T12:11:51Z","match_totals_all":{"draws":4976,"losses":7653,"wins":2808},"match_totals_tracks":{"highest":{"draws":1678,"losses":2353,"wins":1215},"medium":{"draws":1569,"losses":2738,"wins":879},"none":{"draws":1729,"losses":2562,"wins":714}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":50.72232954600573,"mean":21.065180350726248,"min":6.062797814895173},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":30.208205298744172,"GB2-02":6.484843270599066,"GB2-03":23.79281523328693,"GB2-04":11.379343828501437,"GB2-05":39.251596820673434,"GB2-06":50.72232954600573,"GB2-07":25.087539192135324,"GB2-08":18.530424564214943},"per_game_all":{"GB2-01":20.032915738835502,"GB2-02":6.241274434026039,"GB2-03":23.919568570369602,"GB2-04":13.329911691170219,"GB2-05":20.82282857511193,"GB2-06":34.41417481467365,"GB2-07":36.25165863520496,"GB2-08":18.545133008223043},"per_game_match_totals_all":{"GB2-01":{"draws":355,"losses":1281,"wins":232},"GB2-02":{"draws":1506,"losses":297,"wins":3},"GB2-03":{"draws":625,"losses":698,"wins":562},"GB2-04":{"draws":1252,"losses":487,"wins":241},"GB2-05":{"draws":0,"losses":1585,"wins":384},"GB2-06":{"draws":24,"losses":1345,"wins":587},"GB2-07":{"draws":0,"losses":1275,"wins":708},"GB2-08":{"draws":1214,"losses":685,"wins":91}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":186,"losses":315,"wins":114},"GB2-02":{"draws":520,"losses":110,"wins":0},"GB2-03":{"draws":138,"losses":285,"wins":223},"GB2-04":{"draws":406,"losses":182,"wins":75},"GB2-05":{"draws":0,"losses":385,"wins":292},"GB2-06":{"draws":19,"losses":323,"wins":366},"GB2-07":{"draws":0,"losses":514,"wins":118},"GB2-08":{"draws":409,"losses":239,"wins":27}},"medium":{"GB2-01":{"draws":80,"losses":530,"wins":18},"GB2-02":{"draws":488,"losses":86,"wins":0},"GB2-03":{"draws":192,"losses":279,"wins":152},"GB2-04":{"draws":398,"losses":167,"wins":105},"GB2-05":{"draws":0,"losses":582,"wins":64},"GB2-06":{"draws":3,"losses":507,"wins":113},"GB2-07":{"draws":0,"losses":337,"wins":384},"GB2-08":{"draws":408,"losses":250,"wins":43}},"none":{"GB2-01":{"draws":89,"losses":436,"wins":100},"GB2-02":{"draws":498,"losses":101,"wins":3},"GB2-03":{"draws":295,"losses":134,"wins":187},"GB2-04":{"draws":448,"losses":138,"wins":61},"GB2-05":{"draws":0,"losses":618,"wins":28},"GB2-06":{"draws":2,"losses":515,"wins":108},"GB2-07":{"draws":0,"losses":424,"wins":206},"GB2-08":{"draws":397,"losses":196,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1160.9949832796913,"GB2-02":1412.4843551078357,"GB2-03":1414.850126202915,"GB2-04":1439.2433577483928,"GB2-05":939.522126622347,"GB2-06":1157.2672387301893,"GB2-07":1261.8912198238895,"GB2-08":1273.865673750672},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1315.1203568462495,"GB2-02":1414.422894854965,"GB2-03":1413.1778054452577,"GB2-04":1424.7054791998921,"GB2-05":1352.510378391125,"GB2-06":1520.3361256508115,"GB2-07":1034.2020169165066,"GB2-08":1273.6366299401375},"medium":{"GB2-01":974.4291111280575,"GB2-02":1411.063877738947,"GB2-03":1354.9573563266238,"GB2-04":1451.2773086832922,"GB2-05":822.0981650121406,"GB2-06":984.6304831401424,"GB2-07":1520.133103628421,"GB2-08":1287.1340727211011},"none":{"GB2-01":1193.4354818647666,"GB2-02":1411.9662927295944,"GB2-03":1476.4152168368632,"GB2-04":1441.7472853619945,"GB2-05":643.9578364637752,"GB2-06":966.8351073996147,"GB2-07":1231.3385389267407,"GB2-08":1260.8263185907767}},"per_game_tracks":{"highest":{"GB2-01":30.208205298744172,"GB2-02":6.484843270599066,"GB2-03":23.79281523328693,"GB2-04":11.379343828501437,"GB2-05":39.251596820673434,"GB2-06":50.72232954600573,"GB2-07":25.087539192135324,"GB2-08":18.530424564214943},"medium":{"GB2-01":7.715918691493545,"GB2-02":6.062797814895173,"GB2-03":19.380003768471216,"GB2-04":14.94452402103922,"GB2-05":15.583020988038577,"GB2-06":26.659759540050636,"GB2-07":48.91384550741179,"GB2-08":19.397186171669915},"none":{"GB2-01":22.17462322626879,"GB2-02":6.176182216583879,"GB2-03":28.585886709350667,"GB2-04":13.665867223970006,"GB2-05":7.633867916623776,"GB2-06":25.860435357964583,"GB2-07":34.75359120606777,"GB2-08":17.707788288784272}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.936932599628097,"medium":19.256673863886103,"none":19.001934588664543},"reasoning_agg":{"highest":{"max":50.72232954600573,"mean":24.936932599628097,"min":6.484843270599066},"medium":{"max":48.91384550741179,"mean":19.256673863886103,"min":6.062797814895173},"none":{"max":34.75359120606777,"mean":19.001934588664543,"min":6.176182216583879}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":50.72232954600573,"expected_score":17.310209319964102,"reasoning_variance":5.934998010963554,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.754971030762146},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.72232954600573,"expected_score":16.74422644904615,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.192706150581948},"medium":{"ceiling_score":48.91384550741179,"expected_score":15.854030123188416,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.4026437406976875},"none":{"ceiling_score":34.75359120606777,"expected_score":19.332371387657748,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.33043679899320466}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:05dc2b52c65a627c","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":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"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":105},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.302804525,"mean":0.10924724875000001,"median":0.042993304999999996,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":105,"run_count":40,"total":4.9947863},"codegen_latency_ms":{"attempt_count":105,"max_ms":712912,"mean_ms":229546.025,"min_ms":16322,"run_count":40},"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":13,"max_ms":52676,"mean_ms":32623.625,"min_ms":16322,"run_count":8},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":105,"output_max":80000,"output_mean":26295.425,"output_min":1372,"run_count":40},"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":13,"output_max":9117,"output_mean":4863.875,"output_min":2632,"run_count":8},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":23.89927628830331,"highest":23.583036312439734,"medium":19.981032443743352,"none":24.883526449311585},"first_seen_at":"2026-10-13T14:28:20Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[262144],"finish_reason_observations":105,"finish_reasons":["length","stop"],"indexed_attempts":105,"output_token_observations":105,"provider_post_attempt_observations":13,"provider_post_attempts":16,"reasoning_token_observations":78,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[262144],"total_output_tokens":1051817,"total_reasoning_output_tokens":634907,"total_visible_output_tokens":113426,"visible_token_observations":75},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"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":true,"last_measured_at":"2026-10-13T14:28:20Z","match_totals_all":{"draws":4626,"losses":8739,"wins":3239},"match_totals_tracks":{"highest":{"draws":2062,"losses":3488,"wins":1314},"medium":{"draws":620,"losses":1802,"wins":340},"none":{"draws":1944,"losses":3449,"wins":1585}},"model_slug":"thinkingmachines-inkling","overall":{"max":49.36619009723851,"mean":20.724895017430978,"min":6.640431929777992},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":25.745983804848354,"GB2-02":6.640431929777992,"GB2-03":24.343979947839493,"GB2-04":14.116789488084507,"GB2-05":22.126703531325276,"GB2-06":49.36619009723851,"GB2-07":32.075617485726035,"GB2-08":14.24859421467769},"per_game_all":{"GB2-01":20.403433769456694,"GB2-03":21.869758822574962,"GB2-04":10.592547754252744,"GB2-05":24.400378859327617,"GB2-06":37.717511383979904,"GB2-07":28.412027140227945},"per_game_match_totals_all":{"GB2-01":{"draws":694,"losses":1502,"wins":164},"GB2-02":{"draws":1048,"losses":171,"wins":17},"GB2-03":{"draws":844,"losses":868,"wins":576},"GB2-04":{"draws":1537,"losses":614,"wins":239},"GB2-05":{"draws":0,"losses":2544,"wins":686},"GB2-06":{"draws":47,"losses":1192,"wins":691},"GB2-07":{"draws":0,"losses":1377,"wins":441},"GB2-08":{"draws":456,"losses":471,"wins":425}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":280,"losses":386,"wins":56},"GB2-02":{"draws":577,"losses":94,"wins":9},"GB2-03":{"draws":248,"losses":303,"wins":233},"GB2-04":{"draws":499,"losses":178,"wins":103},"GB2-05":{"draws":0,"losses":1280,"wins":270},"GB2-06":{"draws":25,"losses":403,"wins":422},"GB2-07":{"draws":0,"losses":536,"wins":212},"GB2-08":{"draws":433,"losses":308,"wins":9}},"medium":{"GB2-01":{"draws":54,"losses":363,"wins":49},"GB2-03":{"draws":269,"losses":158,"wins":13},"GB2-04":{"draws":294,"losses":121,"wins":31},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":3,"losses":353,"wins":100},"GB2-07":{"draws":0,"losses":390,"wins":80}},"none":{"GB2-01":{"draws":360,"losses":753,"wins":59},"GB2-02":{"draws":471,"losses":77,"wins":8},"GB2-03":{"draws":327,"losses":407,"wins":330},"GB2-04":{"draws":744,"losses":315,"wins":105},"GB2-05":{"draws":0,"losses":847,"wins":349},"GB2-06":{"draws":19,"losses":436,"wins":169},"GB2-07":{"draws":0,"losses":451,"wins":149},"GB2-08":{"draws":23,"losses":163,"wins":416}}},"per_game_raw_elo_all":{"GB2-01":1166.6072294517942,"GB2-03":1387.805951513856,"GB2-04":1418.8413685535622,"GB2-05":1019.6949421792943,"GB2-06":1230.8095095205183,"GB2-07":1102.0040513569659},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1247.530972717746,"GB2-02":1415.6612092644134,"GB2-03":1420.4495997368215,"GB2-04":1445.108077486162,"GB2-05":968.741932933674,"GB2-06":1490.1443566686905,"GB2-07":1176.7219876706504,"GB2-08":1206.958826443084},"medium":{"GB2-01":1118.6351118859745,"GB2-03":1320.6962014151288,"GB2-04":1408.5875540218995,"GB2-05":933.665117531784,"GB2-06":1080.4652933994737,"GB2-07":1034.945689870342},"none":{"GB2-01":1133.6556037516618,"GB2-02":1427.3278845777968,"GB2-03":1422.272053389618,"GB2-04":1402.8284741526254,"GB2-05":1156.6777760724253,"GB2-06":1121.8188784933911,"GB2-07":1094.3444765299055,"GB2-08":1739.3404505807703}},"per_game_tracks":{"highest":{"GB2-01":25.745983804848354,"GB2-02":6.640431929777992,"GB2-03":24.343979947839493,"GB2-04":14.116789488084507,"GB2-05":22.126703531325276,"GB2-06":49.36619009723851,"GB2-07":32.075617485726035,"GB2-08":14.24859421467769},"medium":{"GB2-01":17.236335609442186,"GB2-03":16.783183931454825,"GB2-04":9.216778860015395,"GB2-05":20.56147135083291,"GB2-06":30.964421742347035,"GB2-07":25.124003168367764},"none":{"GB2-01":18.227981894079534,"GB2-02":8.106297428261428,"GB2-03":24.482112588430567,"GB2-04":8.444074914658326,"GB2-05":30.51296169582467,"GB2-06":32.821922312354175,"GB2-07":28.03646076659003,"GB2-08":48.43639999429394}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.423508544943697,"medium":18.594445882024264,"none":23.15673062532498},"reasoning_agg":{"highest":{"max":49.36619009723851,"mean":20.423508544943697,"min":6.640431929777992},"medium":{"max":30.964421742347035,"mean":18.594445882024264,"min":9.216778860015395},"none":{"max":48.43639999429394,"mean":23.15673062532498,"min":8.106297428261428}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":49.36619009723851,"expected_score":18.726608164820757,"reasoning_variance":4.562284743300715,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9982868526102209},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.36619009723851,"expected_score":14.254372347442823,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.169136197500874},"medium":{"ceiling_score":30.964421742347035,"expected_score":14.79792228810753,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.796523593916733},"none":{"ceiling_score":48.43639999429394,"expected_score":25.972453947284016,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.8157233219590374}}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:8ed9f35f2f7d99b2","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069025},"medium":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"none":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0265788,"mean":0.00468415625,"median":0.001493475,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.03747325}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0265788,"mean":0.00468415625,"median":0.001493475,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.03747325},"historical-provider-setting-intensive":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069025}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":24,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":16,"max":0.0265788,"mean":0.009431849999999999,"median":0.008094299999999999,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":46},"recorded_attempt_count":48,"run_count":24,"total":0.22636439999999997},"codegen_latency_ms":{"attempt_count":46,"max_ms":1854161,"mean_ms":655289.0454545454,"min_ms":24176,"run_count":22},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":1854161,"mean_ms":1241203.5,"min_ms":669527,"run_count":8},"medium":{"attempt_count":14,"max_ms":912503,"mean_ms":578415.5714285715,"min_ms":208280,"run_count":7},"none":{"attempt_count":14,"max_ms":108436,"mean_ms":62546.0,"min_ms":24176,"run_count":7}},"codegen_output_tokens":{"attempt_count":48,"output_max":131072,"output_mean":43410.291666666664,"output_min":1354,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":112315,"output_mean":77461.75,"output_min":52895,"run_count":8},"medium":{"attempt_count":15,"output_max":54994,"output_mean":32804.625,"output_min":3815,"run_count":8},"none":{"attempt_count":15,"output_max":131072,"output_mean":19964.5,"output_min":1354,"run_count":8}},"display_name":"Solar Mini 4","economics":{"highest":37.89484216271055,"medium":23.92590973054105,"none":8.616202522367487},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":48,"effective_max_output_tokens":[131072],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":48,"output_token_observations":48,"provider_post_attempt_observations":48,"provider_post_attempts":49,"reasoning_token_observations":48,"reconciliation_get_attempt_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[131072],"total_output_tokens":1041847,"total_reasoning_output_tokens":808441,"total_visible_output_tokens":233406,"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":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":2,"evaluated_cells":7,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.7142857142857143,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.14285714285714285},"baseline":{"admitted_plugins":1,"evaluated_cells":7,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"infra_excluded_game_aliases":["GB2-07"],"infra_failures_excluded":1,"model_code_failure_rate":0.8571428571428571,"model_code_failures":6,"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":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.375}},"id":"upstage/solar-mini4","is_recent_addition":false,"last_measured_at":"2026-10-12T22:38:55Z","match_totals_all":{"draws":404,"losses":1726,"wins":648},"match_totals_tracks":{"highest":{"draws":7,"losses":904,"wins":499},"medium":{"draws":84,"losses":708,"wins":130},"none":{"draws":313,"losses":114,"wins":19}},"model_slug":"upstage-solar-mini4","overall":{"max":42.712804978206314,"mean":17.48131277595159,"min":5.2971392341803325},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete","below_generation_quality_threshold"],"overall_official_rank":56,"overall_ranking_status":"partial","per_game":{"GB2-05":42.712804978206314,"GB2-06":35.52355029842168,"GB2-07":35.448171211503684},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":339,"wins":48},"GB2-04":{"draws":313,"losses":114,"wins":19},"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":12,"losses":690,"wins":210},"GB2-07":{"draws":0,"losses":325,"wins":145}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":7,"losses":321,"wins":128},"GB2-07":{"draws":0,"losses":325,"wins":145}},"medium":{"GB2-01":{"draws":79,"losses":339,"wins":48},"GB2-06":{"draws":5,"losses":369,"wins":82}},"none":{"GB2-04":{"draws":313,"losses":114,"wins":19}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1430.0759696959922,"GB2-06":1181.965294929496,"GB2-07":1245.5043106743087},"medium":{"GB2-01":1155.2901000855504,"GB2-06":1018.8215515368822},"none":{"GB2-04":1404.1113673570158}},"per_game_tracks":{"highest":{"GB2-05":42.712804978206314,"GB2-06":35.52355029842168,"GB2-07":35.448171211503684},"medium":{"GB2-01":19.656281852652114,"GB2-06":28.195537608429984},"none":{"GB2-04":8.616202522367487}},"provider_color":"#805CFB","provider_company":"Upstage","provider_key":"upstage","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.65431656658468,"medium":17.49248252708976,"none":5.2971392341803325},"reasoning_agg":{"highest":{"max":42.712804978206314,"mean":29.65431656658468,"min":35.448171211503684},"medium":{"max":28.195537608429984,"mean":17.49248252708976,"min":19.656281852652114},"none":{"max":8.616202522367487,"mean":5.2971392341803325,"min":8.616202522367487}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":42.712804978206314,"reasoning_variance":24.357177332404348},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.712804978206314,"expected_score":23.42243292758614,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.231883638998539},"medium":{"ceiling_score":28.195537608429984,"expected_score":10.624262802376208,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.868219724713551},"none":{"ceiling_score":8.616202522367487,"expected_score":12.48983116822177,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.192691934041437}}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:5306429c9898abc6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.00761251}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612510000000001},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.028312969999999993},"codegen_latency_ms":{"attempt_count":37,"max_ms":49328,"mean_ms":21505.916666666668,"min_ms":9355,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":47445,"mean_ms":22491.5,"min_ms":13295,"run_count":8},"medium":{"attempt_count":12,"max_ms":49328,"mean_ms":23044.25,"min_ms":13295,"run_count":8},"none":{"attempt_count":14,"max_ms":24913,"mean_ms":18982.0,"min_ms":9355,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":11394,"output_mean":4854.291666666667,"output_min":1030,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":11185,"output_mean":6150.25,"output_min":2902,"run_count":8},"medium":{"attempt_count":12,"output_max":11394,"output_mean":5469.5,"output_min":3022,"run_count":8},"none":{"attempt_count":14,"output_max":4416,"output_mean":2943.125,"output_min":1030,"run_count":8}},"display_name":"Mercury 2.5 Preview","economics":{"all":14.400639758686856,"highest":16.689377723471292,"medium":16.67865267598542,"none":21.906520673550666},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:49:07Z","match_totals_all":{"draws":3941,"losses":5273,"wins":1315},"match_totals_tracks":{"highest":{"draws":1466,"losses":1937,"wins":313},"medium":{"draws":1326,"losses":1982,"wins":344},"none":{"draws":1149,"losses":1354,"wins":658}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":38.632780449491484,"mean":16.84346951936152,"min":6.536763319627209},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":26.320376209057503,"GB2-02":6.801316719710105,"GB2-04":8.140232080424047,"GB2-06":24.01221173972966,"GB2-07":20.553208180343518,"GB2-08":14.30892141156291},"per_game_all":{"GB2-02":6.820578529979876,"GB2-04":9.277530548446604,"GB2-06":27.10381019763408},"per_game_match_totals_all":{"GB2-01":{"draws":155,"losses":367,"wins":102},"GB2-02":{"draws":1487,"losses":275,"wins":2},"GB2-03":{"draws":185,"losses":307,"wins":201},"GB2-04":{"draws":1326,"losses":397,"wins":87},"GB2-05":{"draws":0,"losses":910,"wins":402},"GB2-06":{"draws":14,"losses":1459,"wins":339},"GB2-07":{"draws":0,"losses":1123,"wins":149},"GB2-08":{"draws":774,"losses":435,"wins":33}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":155,"losses":367,"wins":102},"GB2-02":{"draws":499,"losses":91,"wins":2},"GB2-04":{"draws":452,"losses":150,"wins":22},"GB2-06":{"draws":4,"losses":512,"wins":88},"GB2-07":{"draws":0,"losses":559,"wins":87},"GB2-08":{"draws":356,"losses":258,"wins":12}},"medium":{"GB2-02":{"draws":487,"losses":75,"wins":0},"GB2-04":{"draws":415,"losses":146,"wins":31},"GB2-05":{"draws":0,"losses":535,"wins":117},"GB2-06":{"draws":6,"losses":485,"wins":113},"GB2-07":{"draws":0,"losses":564,"wins":62},"GB2-08":{"draws":418,"losses":177,"wins":21}},"none":{"GB2-02":{"draws":501,"losses":109,"wins":0},"GB2-03":{"draws":185,"losses":307,"wins":201},"GB2-04":{"draws":459,"losses":101,"wins":34},"GB2-05":{"draws":0,"losses":375,"wins":285},"GB2-06":{"draws":4,"losses":462,"wins":138}}},"per_game_raw_elo_all":{"GB2-02":1417.0949778438226,"GB2-04":1409.0403455832354,"GB2-06":994.5163948598444},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1256.2313092881504,"GB2-02":1416.9416750431235,"GB2-04":1400.5638873589692,"GB2-06":925.6880553322379,"GB2-07":941.7255597218465,"GB2-08":1207.898257632803},"medium":{"GB2-02":1419.507137211928,"GB2-04":1398.3129604987623,"GB2-05":980.5258205338487,"GB2-06":998.4693941319449,"GB2-07":862.0063053092281,"GB2-08":1273.6571416765216},"none":{"GB2-02":1414.8361212764157,"GB2-03":1396.0032542261154,"GB2-04":1428.2441888919743,"GB2-05":1338.6427184425615,"GB2-06":1059.3917351153505}},"per_game_tracks":{"highest":{"GB2-01":26.320376209057503,"GB2-02":6.801316719710105,"GB2-04":8.140232080424047,"GB2-06":24.01221173972966,"GB2-07":20.553208180343518,"GB2-08":14.30892141156291},"medium":{"GB2-02":7.123655550602316,"GB2-04":7.83822201890856,"GB2-05":22.652535761867632,"GB2-06":27.281369129574045,"GB2-07":16.64439183415537,"GB2-08":18.53174176080459},"none":{"GB2-02":6.536763319627209,"GB2-03":22.49107232902892,"GB2-04":11.854137546007205,"GB2-05":38.632780449491484,"GB2-06":30.017849723598527}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":15.531216004852721,"medium":15.521235223548265,"none":19.477957329683573},"reasoning_agg":{"highest":{"max":26.320376209057503,"mean":15.531216004852721,"min":6.801316719710105},"medium":{"max":27.281369129574045,"mean":15.521235223548265,"min":7.123655550602316},"none":{"max":38.632780449491484,"mean":19.477957329683573,"min":6.536763319627209}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":38.632780449491484,"expected_score":8.603642430603587,"reasoning_variance":3.9567221061353077,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.239827088757933},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":26.320376209057503,"expected_score":7.350894603933887,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.180321400918835},"medium":{"ceiling_score":27.281369129574045,"expected_score":12.423648099010776,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.0975871245374886},"none":{"ceiling_score":38.632780449491484,"expected_score":23.265944260573768,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7879869308901952}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:f8b6c8a1e8419df3","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875}},"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":0.04706874999999999},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025000000003}},"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":20.376261088686725,"highest":21.492766114227486,"medium":21.00961564242354,"none":12.669992670848227},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:11:57Z","match_totals_all":{"draws":2231,"losses":5855,"wins":1274},"match_totals_tracks":{"highest":{"draws":779,"losses":1722,"wins":452},"medium":{"draws":883,"losses":2133,"wins":579},"none":{"draws":569,"losses":2000,"wins":243}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":35.652653691385346,"mean":16.642371891173354,"min":0.5334167171991303},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":58,"overall_ranking_status":"partial","per_game":{"GB2-04":10.749428321092305,"GB2-05":16.204370671007073,"GB2-06":27.11944718268541,"GB2-07":35.652653691385346,"GB2-08":17.7379307049673},"per_game_all":{"GB2-05":16.761957646231494,"GB2-06":29.362698253076527,"GB2-07":15.004127366752153},"per_game_match_totals_all":{"GB2-01":{"draws":398,"losses":660,"wins":102},"GB2-02":{"draws":448,"losses":82,"wins":6},"GB2-04":{"draws":802,"losses":243,"wins":96},"GB2-05":{"draws":0,"losses":1529,"wins":245},"GB2-06":{"draws":10,"losses":1318,"wins":411},"GB2-07":{"draws":0,"losses":1519,"wins":253},"GB2-08":{"draws":573,"losses":504,"wins":161}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":419,"losses":120,"wins":33},"GB2-05":{"draws":0,"losses":522,"wins":76},"GB2-06":{"draws":0,"losses":450,"wins":119},"GB2-07":{"draws":0,"losses":411,"wins":199},"GB2-08":{"draws":360,"losses":219,"wins":25}},"medium":{"GB2-01":{"draws":284,"losses":231,"wins":73},"GB2-04":{"draws":383,"losses":123,"wins":63},"GB2-05":{"draws":0,"losses":482,"wins":120},"GB2-06":{"draws":3,"losses":457,"wins":148},"GB2-07":{"draws":0,"losses":555,"wins":39},"GB2-08":{"draws":213,"losses":285,"wins":136}},"none":{"GB2-01":{"draws":114,"losses":429,"wins":29},"GB2-02":{"draws":448,"losses":82,"wins":6},"GB2-05":{"draws":0,"losses":525,"wins":49},"GB2-06":{"draws":7,"losses":411,"wins":144},"GB2-07":{"draws":0,"losses":553,"wins":15}}},"per_game_raw_elo_all":{"GB2-05":848.5181070791033,"GB2-06":1044.8060803257358,"GB2-07":828.5535541948371},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1420.0106232465075,"GB2-05":836.0225964167217,"GB2-06":994.8645214781476,"GB2-07":1249.674675662806,"GB2-08":1261.295704329844},"medium":{"GB2-01":1332.4433741270702,"GB2-04":1432.8497017623772,"GB2-05":979.4701610402885,"GB2-06":1065.139573401513,"GB2-07":702.5586708598214,"GB2-08":1304.7121945655322},"none":{"GB2-01":1061.9653677040328,"GB2-02":1419.7393360854528,"GB2-05":730.0615637802999,"GB2-06":1074.4141460975468,"GB2-07":533.4273160618839}},"per_game_tracks":{"highest":{"GB2-04":10.749428321092305,"GB2-05":16.204370671007073,"GB2-06":27.11944718268541,"GB2-07":35.652653691385346,"GB2-08":17.7379307049673},"medium":{"GB2-01":31.351863301347702,"GB2-04":12.472065764773467,"GB2-05":22.605429084934993,"GB2-06":30.276028376516,"GB2-07":8.826311691671979,"GB2-08":20.525995635297114},"none":{"GB2-01":13.495023955211602,"GB2-02":7.152830299049825,"GB2-05":11.476073182752414,"GB2-06":30.692619200028165,"GB2-07":0.5334167171991303}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.110071722856503,"medium":19.551650404706827,"none":11.26539354595673},"reasoning_agg":{"highest":{"max":35.652653691385346,"mean":19.110071722856503,"min":10.749428321092305},"medium":{"max":31.351863301347702,"mean":19.551650404706827,"min":8.826311691671979},"none":{"max":30.692619200028165,"mean":11.26539354595673,"min":0.5334167171991303}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":35.652653691385346,"expected_score":10.732756983564228,"reasoning_variance":8.286256858750097,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.909614907609127},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":35.652653691385346,"expected_score":8.437796972960626,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.672274749895877},"medium":{"ceiling_score":31.351863301347702,"expected_score":16.362566053783087,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.189084350923739},"none":{"ceiling_score":30.692619200028165,"expected_score":8.472557525163207,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.7928360207935228}}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:279ed8e1938a92c1","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998},"codegen_latency_ms":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8}},"codegen_output_tokens":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8}},"display_name":"Pareto 26.10 Preview","economics":{"none":78.159162742147},"first_seen_at":"2026-10-13T13:25:45Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[131072],"finish_reason_observations":9,"finish_reasons":["stop"],"indexed_attempts":9,"output_token_observations":9,"provider_post_attempt_observations":9,"provider_post_attempts":9,"reasoning_token_observations":9,"reconciliation_get_attempt_observations":9,"requested_max_output_token_observations":9,"requested_max_output_tokens":[131072],"total_output_tokens":57710,"total_visible_output_tokens":57710,"visible_token_observations":9},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-10-13T12:58:04Z","match_totals_all":{"draws":127,"losses":293,"wins":3000},"match_totals_tracks":{"none":{"draws":127,"losses":293,"wins":3000}},"model_slug":"unbiased-pareto-26-10-preview","overall":{"max":92.66060584281914,"mean":78.159162742147,"min":58.183904306409666},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":117,"wins":337},"GB2-02":{"draws":35,"losses":19,"wins":372},"GB2-03":{"draws":4,"losses":24,"wins":412},"GB2-04":{"draws":39,"losses":45,"wins":362},"GB2-05":{"draws":0,"losses":23,"wins":461},"GB2-06":{"draws":37,"losses":37,"wins":382},"GB2-07":{"draws":0,"losses":17,"wins":453},"GB2-08":{"draws":0,"losses":11,"wins":221}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":12,"losses":117,"wins":337},"GB2-02":{"draws":35,"losses":19,"wins":372},"GB2-03":{"draws":4,"losses":24,"wins":412},"GB2-04":{"draws":39,"losses":45,"wins":362},"GB2-05":{"draws":0,"losses":23,"wins":461},"GB2-06":{"draws":37,"losses":37,"wins":382},"GB2-07":{"draws":0,"losses":17,"wins":453},"GB2-08":{"draws":0,"losses":11,"wins":221}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1738.8689917087584,"GB2-02":1977.7405770086382,"GB2-03":2160.2964002469625,"GB2-04":1854.0547035431944,"GB2-05":2408.971076260453,"GB2-06":2115.4149048995496,"GB2-07":2412.336473660663,"GB2-08":2291.7988643504477}},"per_game_tracks":{"none":{"GB2-01":58.183904306409666,"GB2-02":77.26318695240818,"GB2-03":80.42057318822805,"GB2-04":68.98574053018375,"GB2-05":86.39402588056443,"GB2-06":77.45179373014652,"GB2-07":92.66060584281914,"GB2-08":83.91347150641641}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":78.159162742147},"reasoning_agg":{"none":{"max":92.66060584281914,"mean":78.159162742147,"min":58.183904306409666}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"score_diagnostics":{"ceiling_score":92.66060584281914},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":92.66060584281914,"expected_score":95.36901270870237,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":17.209849966555367}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:ba0e7b91d293d49e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.455327115},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.455327115},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.032052512812499996,"median":0.0201057,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":19,"run_count":16,"total":0.5128402049999999},"codegen_latency_ms":{"attempt_count":19,"max_ms":3172586,"mean_ms":488857.125,"min_ms":33029,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":9,"max_ms":3172586,"mean_ms":924271.75,"min_ms":388744,"run_count":8},"none":{"attempt_count":10,"max_ms":84396,"mean_ms":53442.5,"min_ms":33029,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":171951,"output_mean":32110.125,"output_min":2214,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":9,"output_max":171951,"output_mean":60792.125,"output_min":28781,"run_count":8},"none":{"attempt_count":10,"output_max":6088,"output_mean":3428.125,"output_min":2214,"run_count":8}},"display_name":"MiMo-V2.6-Pro","economics":{"medium":54.65187336912323,"none":35.127897713386815},"first_seen_at":"2026-10-13T14:27:56Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":19,"effective_max_output_tokens":[131072],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"provider_post_attempt_observations":19,"provider_post_attempts":20,"reasoning_token_observations":19,"reconciliation_get_attempt_observations":19,"requested_max_output_token_observations":19,"requested_max_output_tokens":[131072],"total_output_tokens":513762,"total_reasoning_output_tokens":447944,"total_visible_output_tokens":65818,"visible_token_observations":19},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-13T14:14:45Z","match_totals_all":{"draws":1289,"losses":2165,"wins":3592},"match_totals_tracks":{"medium":{"draws":341,"losses":800,"wins":2257},"none":{"draws":948,"losses":1365,"wins":1335}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":80.02000432869326,"mean":44.889885541255026,"min":5.25704450460231},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":280,"losses":363,"wins":289},"GB2-02":{"draws":402,"losses":142,"wins":308},"GB2-03":{"draws":95,"losses":276,"wins":509},"GB2-04":{"draws":459,"losses":223,"wins":212},"GB2-05":{"draws":0,"losses":339,"wins":629},"GB2-06":{"draws":53,"losses":381,"wins":478},"GB2-07":{"draws":0,"losses":324,"wins":616},"GB2-08":{"draws":0,"losses":117,"wins":551}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":71,"losses":183,"wins":212},"GB2-02":{"draws":76,"losses":48,"wins":302},"GB2-03":{"draws":2,"losses":68,"wins":370},"GB2-04":{"draws":163,"losses":163,"wins":120},"GB2-05":{"draws":0,"losses":74,"wins":410},"GB2-06":{"draws":29,"losses":186,"wins":241},"GB2-07":{"draws":0,"losses":46,"wins":424},"GB2-08":{"draws":0,"losses":32,"wins":178}},"none":{"GB2-01":{"draws":209,"losses":180,"wins":77},"GB2-02":{"draws":326,"losses":94,"wins":6},"GB2-03":{"draws":93,"losses":208,"wins":139},"GB2-04":{"draws":296,"losses":60,"wins":92},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":24,"losses":195,"wins":237},"GB2-07":{"draws":0,"losses":278,"wins":192},"GB2-08":{"draws":0,"losses":85,"wins":373}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1521.3034070878234,"GB2-02":1766.0720710378064,"GB2-03":1882.5241069151016,"GB2-04":1450.1445381575693,"GB2-05":2046.520392320189,"GB2-06":1574.067171512035,"GB2-07":2154.5348174084243,"GB2-08":2000.2489394086185},"none":{"GB2-01":1384.5305631849233,"GB2-02":1404.6509685985134,"GB2-03":1398.1596692773574,"GB2-04":1515.812008513884,"GB2-05":1412.19396609091,"GB2-06":1553.265336984433,"GB2-07":1371.0463641993088,"GB2-08":1903.803487853197}},"per_game_tracks":{"medium":{"GB2-01":43.820319839035704,"GB2-02":50.6679872332351,"GB2-03":59.3668578840863,"GB2-04":14.79253858685898,"GB2-05":70.22039472720152,"GB2-06":53.13579498286292,"GB2-07":80.02000432869326,"GB2-08":65.1910893710121},"none":{"GB2-01":34.79063667630067,"GB2-02":5.25704450460231,"GB2-03":22.65451753093095,"GB2-04":23.60323657642165,"GB2-05":41.91485661334857,"GB2-06":52.20142812193752,"GB2-07":41.60378361114592,"GB2-08":58.9976780724069}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":54.65187336912323,"none":35.127897713386815},"reasoning_agg":{"medium":{"max":80.02000432869326,"mean":54.65187336912323,"min":14.79253858685898},"none":{"max":58.9976780724069,"mean":35.127897713386815,"min":5.25704450460231}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":80.02000432869326,"reasoning_variance":19.523975655736415},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":80.02000432869326,"expected_score":56.42738227145206,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7755089023288306},"none":{"ceiling_score":58.9976780724069,"expected_score":39.770927054811835,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.64302934142502}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:d6acf4ab074f64d1","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419},"medium":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419}},"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":3,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1851245,"median":0.183419,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":5,"run_count":3,"total":0.5553735},"codegen_latency_ms":{"attempt_count":4,"max_ms":724394,"mean_ms":700552.5,"min_ms":676711,"run_count":2},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":2,"max_ms":724394,"mean_ms":724394.0,"min_ms":724394,"run_count":1},"none":{"attempt_count":2,"max_ms":676711,"mean_ms":676711.0,"min_ms":676711,"run_count":1}},"codegen_output_tokens":{"attempt_count":5,"output_max":64000,"output_mean":62025.0,"output_min":59586,"run_count":3},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":1,"output_max":64000,"output_mean":64000.0,"output_min":64000,"run_count":1},"medium":{"attempt_count":2,"output_max":59586,"output_mean":59586.0,"output_min":59586,"run_count":1},"none":{"attempt_count":2,"output_max":62489,"output_mean":62489.0,"output_min":62489,"run_count":1}},"display_name":"Step 5 Preview","economics":{"medium":59.079643019305514,"none":19.592172852253892},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":5,"effective_max_output_tokens":[64000],"finish_reason_observations":4,"finish_reasons":["stop"],"indexed_attempts":5,"output_token_observations":5,"provider_post_attempt_observations":5,"provider_post_attempts":5,"reasoning_token_observations":5,"reconciliation_get_attempt_observations":5,"requested_max_output_token_observations":5,"requested_max_output_tokens":[64000],"total_output_tokens":186075,"total_reasoning_output_tokens":53683,"total_visible_output_tokens":132392,"visible_token_observations":5},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":64000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"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":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-10-13T14:18:58Z","match_totals_all":{"draws":128,"losses":109,"wins":197},"match_totals_tracks":{"medium":{"draws":2,"losses":36,"wins":180},"none":{"draws":126,"losses":73,"wins":17}},"model_slug":"stepfun-step-5-preview","overall":{"max":59.079643019305514,"mean":39.3359079357797,"min":19.592172852253892},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":128,"losses":109,"wins":197}},"per_game_match_totals_tracks":{"medium":{"GB2-08":{"draws":2,"losses":36,"wins":180}},"none":{"GB2-08":{"draws":126,"losses":73,"wins":17}}},"per_game_raw_elo_tracks":{"medium":{"GB2-08":1905.0798678535264},"none":{"GB2-08":1290.1704572835877}},"per_game_tracks":{"medium":{"GB2-08":59.079643019305514},"none":{"GB2-08":19.592172852253892}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":59.079643019305514,"none":19.592172852253892},"reasoning_agg":{"medium":{"max":59.079643019305514,"mean":59.079643019305514,"min":59.079643019305514},"none":{"max":19.592172852253892,"mean":19.592172852253892,"min":19.592172852253892}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"ceiling_score":59.079643019305514,"reasoning_variance":39.487470167051626},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.079643019305514,"expected_score":64.12090595655994,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.041262937254423},"none":{"ceiling_score":19.592172852253892,"expected_score":23.348066169275082,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.75589331702119}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:1634fd786aeaa347","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":0.16601802},"codegen_latency_ms":{"attempt_count":23,"max_ms":1374551,"mean_ms":491530.125,"min_ms":35032,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1374551,"mean_ms":925316.625,"min_ms":428464,"run_count":8},"none":{"attempt_count":12,"max_ms":114099,"mean_ms":57743.625,"min_ms":35032,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":78655,"output_mean":31302.375,"output_min":3072,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":78655,"output_mean":57997.125,"output_min":33074,"run_count":8},"none":{"attempt_count":12,"output_max":6869,"output_mean":4607.625,"output_min":3072,"run_count":8}},"display_name":"MiMo-V2.6-Flash","economics":{"medium":41.6533837290742,"none":32.4982308349348},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T10:58:47Z","match_totals_all":{"draws":1382,"losses":2563,"wins":2892},"match_totals_tracks":{"medium":{"draws":536,"losses":1220,"wins":1883},"none":{"draws":846,"losses":1343,"wins":1009}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":71.22231590768303,"mean":36.54231973910714,"min":6.306288027954118},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":164,"losses":291,"wins":476},"GB2-02":{"draws":507,"losses":145,"wins":200},"GB2-03":{"draws":168,"losses":360,"wins":350},"GB2-04":{"draws":51,"losses":167,"wins":230},"GB2-05":{"draws":0,"losses":420,"wins":548},"GB2-06":{"draws":46,"losses":357,"wins":509},"GB2-07":{"draws":0,"losses":366,"wins":574},"GB2-08":{"draws":446,"losses":457,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":19,"losses":211,"wins":235},"GB2-02":{"draws":186,"losses":53,"wins":187},"GB2-03":{"draws":30,"losses":157,"wins":251},"GB2-04":{"draws":51,"losses":167,"wins":230},"GB2-05":{"draws":0,"losses":193,"wins":291},"GB2-06":{"draws":16,"losses":147,"wins":293},"GB2-07":{"draws":0,"losses":77,"wins":393},"GB2-08":{"draws":234,"losses":215,"wins":3}},"none":{"GB2-01":{"draws":145,"losses":80,"wins":241},"GB2-02":{"draws":321,"losses":92,"wins":13},"GB2-03":{"draws":138,"losses":203,"wins":99},"GB2-05":{"draws":0,"losses":227,"wins":257},"GB2-06":{"draws":30,"losses":210,"wins":216},"GB2-07":{"draws":0,"losses":289,"wins":181},"GB2-08":{"draws":212,"losses":242,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1515.42553362099,"GB2-02":1615.3280748440895,"GB2-03":1567.9141401314894,"GB2-04":1543.7506143686119,"GB2-05":1598.7491794341688,"GB2-06":1724.8554623609489,"GB2-07":1975.1083365093125,"GB2-08":1200.341266291111},"none":{"GB2-01":1665.467286264515,"GB2-02":1413.0017917294763,"GB2-03":1362.9500206175062,"GB2-05":1509.0878982416848,"GB2-06":1496.3126621915842,"GB2-07":1342.5395035229426,"GB2-08":1168.3572868653796}},"per_game_tracks":{"medium":{"GB2-01":43.432265210926694,"GB2-02":31.727679288742777,"GB2-03":35.521035851022106,"GB2-04":27.35179910060246,"GB2-05":50.23950695625721,"GB2-06":59.90883136087353,"GB2-07":71.22231590768303,"GB2-08":13.823636156485824},"none":{"GB2-01":53.33795590866734,"GB2-02":6.306288027954118,"GB2-03":19.985806732054687,"GB2-05":46.23855301962679,"GB2-06":49.643255096530154,"GB2-07":40.20602740016145,"GB2-08":11.769729659549048}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.6533837290742,"none":31.43125574914009},"reasoning_agg":{"medium":{"max":71.22231590768303,"mean":41.6533837290742,"min":13.823636156485824},"none":{"max":53.33795590866734,"mean":31.43125574914009,"min":6.306288027954118}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":71.22231590768303,"reasoning_variance":10.222127979934111},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":71.22231590768303,"expected_score":42.32426726703507,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6708835379608686},"none":{"ceiling_score":53.33795590866734,"expected_score":36.03260589860627,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.601350149466182}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:a78fcb9a5f009aff","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.30150960000000004},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899822999999995},"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":41.048358281729215,"none":22.270203697563115},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:12:29Z","match_totals_all":{"draws":3229,"losses":3798,"wins":3126},"match_totals_tracks":{"medium":{"draws":1575,"losses":1317,"wins":2199},"none":{"draws":1654,"losses":2481,"wins":927}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":69.94800357960156,"mean":31.659280989646163,"min":7.542746189139425},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":414,"losses":555,"wins":371},"GB2-02":{"draws":825,"losses":183,"wins":172},"GB2-03":{"draws":325,"losses":420,"wins":468},"GB2-04":{"draws":785,"losses":288,"wins":139},"GB2-05":{"draws":0,"losses":718,"wins":582},"GB2-06":{"draws":90,"losses":422,"wins":794},"GB2-07":{"draws":0,"losses":748,"wins":512},"GB2-08":{"draws":790,"losses":464,"wins":88}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":253,"losses":232,"wins":221},"GB2-02":{"draws":335,"losses":92,"wins":159},"GB2-03":{"draws":142,"losses":154,"wins":299},"GB2-04":{"draws":364,"losses":141,"wins":99},"GB2-05":{"draws":0,"losses":191,"wins":463},"GB2-06":{"draws":74,"losses":106,"wins":436},"GB2-07":{"draws":0,"losses":177,"wins":457},"GB2-08":{"draws":407,"losses":224,"wins":65}},"none":{"GB2-01":{"draws":161,"losses":323,"wins":150},"GB2-02":{"draws":490,"losses":91,"wins":13},"GB2-03":{"draws":183,"losses":266,"wins":169},"GB2-04":{"draws":421,"losses":147,"wins":40},"GB2-05":{"draws":0,"losses":527,"wins":119},"GB2-06":{"draws":16,"losses":316,"wins":358},"GB2-07":{"draws":0,"losses":571,"wins":55},"GB2-08":{"draws":383,"losses":240,"wins":23}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1493.74080651504,"GB2-02":1533.2779131430957,"GB2-03":1604.3688793530537,"GB2-04":1443.5419714823981,"GB2-05":1778.3630762995344,"GB2-06":1948.3578231801791,"GB2-07":1801.6806711669074,"GB2-08":1325.4204279573514},"none":{"GB2-01":1330.5452149853716,"GB2-02":1422.8426372368276,"GB2-03":1412.4834791379046,"GB2-04":1403.513842814035,"GB2-05":997.1439597701535,"GB2-06":1530.4158613461168,"GB2-07":838.4533530853411,"GB2-08":1250.6983769111907}},"per_game_tracks":{"medium":{"GB2-01":42.00064903881499,"GB2-02":21.418443970905372,"GB2-03":38.28411812914041,"GB2-04":13.906662815868664,"GB2-05":58.25441504344231,"GB2-06":69.94800357960156,"GB2-07":62.7187630562863,"GB2-08":21.855810619774083},"none":{"GB2-01":31.22654766738928,"GB2-02":7.542746189139425,"GB2-03":23.74018885998006,"GB2-04":8.536031803730241,"GB2-05":23.39408672692946,"GB2-06":51.17508629628576,"GB2-07":15.489537021073405,"GB2-08":17.057405015977285}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.048358281729215,"none":22.270203697563115},"reasoning_agg":{"medium":{"max":69.94800357960156,"mean":41.048358281729215,"min":13.906662815868664},"none":{"max":51.17508629628576,"mean":22.270203697563115,"min":7.542746189139425}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":69.94800357960156,"reasoning_variance":18.7781545841661},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":69.94800357960156,"expected_score":42.33808649900901,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2897282172797944},"none":{"ceiling_score":51.17508629628576,"expected_score":24.052458381383175,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7822546838200601}}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:8588f7e459b09704","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414000000001}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.33846634,"mean":0.10613685812499998,"median":0.05239252,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.6981897300000002},"codegen_latency_ms":{"attempt_count":23,"max_ms":2372746,"mean_ms":755436.1875,"min_ms":27078,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2372746,"mean_ms":1420193.375,"min_ms":412995,"run_count":8},"none":{"attempt_count":13,"max_ms":165291,"mean_ms":90679.0,"min_ms":27078,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":159550,"output_mean":46908.8125,"output_min":3069,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":159550,"output_mean":88125.0,"output_min":32501,"run_count":8},"none":{"attempt_count":13,"output_max":9287,"output_mean":5692.625,"output_min":3069,"run_count":8}},"display_name":"Mistral Large 4","economics":{"highest":40.61128707201597,"none":23.33169035767272},"first_seen_at":"2026-10-13T14:28:18Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[262144],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[262144],"total_output_tokens":750541,"total_reasoning_output_tokens":655796,"total_visible_output_tokens":94745,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-10-13T14:19:04Z","match_totals_all":{"draws":1757,"losses":2326,"wins":2253},"match_totals_tracks":{"highest":{"draws":762,"losses":1055,"wins":1579},"none":{"draws":995,"losses":1271,"wins":674}},"model_slug":"mistralai-mistral-large-4-0","overall":{"max":70.61946008343504,"mean":31.588478137321573,"min":6.435567230555157},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":30.997791051059803,"GB2-02":30.273208474333003,"GB2-03":21.515176740555418,"GB2-04":35.90075537847797,"GB2-05":44.41580087238249,"GB2-06":70.61946008343504,"GB2-07":66.96557789705346,"GB2-08":24.202526078830584},"per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":442,"wins":372},"GB2-02":{"draws":583,"losses":107,"wins":162},"GB2-03":{"draws":318,"losses":420,"wins":142},"GB2-04":{"draws":474,"losses":201,"wins":217},"GB2-05":{"draws":0,"losses":421,"wins":547},"GB2-06":{"draws":34,"losses":73,"wins":349},"GB2-07":{"draws":0,"losses":527,"wins":413},"GB2-08":{"draws":230,"losses":135,"wins":51}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":301,"wins":145},"GB2-02":{"draws":231,"losses":36,"wins":159},"GB2-03":{"draws":166,"losses":179,"wins":95},"GB2-04":{"draws":205,"losses":56,"wins":185},"GB2-05":{"draws":0,"losses":243,"wins":241},"GB2-06":{"draws":34,"losses":73,"wins":349},"GB2-07":{"draws":0,"losses":97,"wins":373},"GB2-08":{"draws":106,"losses":70,"wins":32}},"none":{"GB2-01":{"draws":98,"losses":141,"wins":227},"GB2-02":{"draws":352,"losses":71,"wins":3},"GB2-03":{"draws":152,"losses":241,"wins":47},"GB2-04":{"draws":269,"losses":145,"wins":32},"GB2-05":{"draws":0,"losses":178,"wins":306},"GB2-07":{"draws":0,"losses":430,"wins":40},"GB2-08":{"draws":124,"losses":65,"wins":19}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1327.0802326141063,"GB2-02":1603.7520886693233,"GB2-03":1383.1277711226935,"GB2-04":1607.467283992273,"GB2-05":1468.2400665978357,"GB2-06":1963.3064773644605,"GB2-07":1888.2933136525423,"GB2-08":1361.9641065875376},"none":{"GB2-01":1581.4159159150036,"GB2-02":1423.1493561343837,"GB2-03":1267.3862281213924,"GB2-04":1387.8587613146053,"GB2-05":1640.7287012252261,"GB2-07":840.9459627921094,"GB2-08":1312.8563201957027}},"per_game_tracks":{"highest":{"GB2-01":30.997791051059803,"GB2-02":30.273208474333003,"GB2-03":21.515176740555418,"GB2-04":35.90075537847797,"GB2-05":44.41580087238249,"GB2-06":70.61946008343504,"GB2-07":66.96557789705346,"GB2-08":24.202526078830584},"none":{"GB2-01":47.78892130506868,"GB2-02":7.581284044833798,"GB2-03":12.74256135122937,"GB2-04":6.435567230555157,"GB2-05":52.11275849509283,"GB2-07":15.61175534383962,"GB2-08":21.048984733089593}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.61128707201597,"none":22.565669202627173},"reasoning_agg":{"highest":{"max":70.61946008343504,"mean":40.61128707201597,"min":21.515176740555418},"none":{"max":52.11275849509283,"mean":22.565669202627173,"min":6.435567230555157}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":70.61946008343504,"reasoning_variance":18.045617869388796},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.61946008343504,"expected_score":33.83740006839637,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.773887003619599},"none":{"ceiling_score":52.11275849509283,"expected_score":26.26763209269407,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.701962890066895}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:023fe3dc3324481d","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":1.0777302952},"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":36.31229037611408,"none":25.47055520208233},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:28:07Z","match_totals_all":{"draws":1851,"losses":3623,"wins":2334},"match_totals_tracks":{"medium":{"draws":756,"losses":1606,"wins":1432},"none":{"draws":1095,"losses":2017,"wins":902}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":61.393153892856006,"mean":29.213352577525583,"min":4.175884811179403},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":251,"losses":511,"wins":594},"GB2-02":{"draws":391,"losses":134,"wins":27},"GB2-03":{"draws":220,"losses":245,"wins":71},"GB2-04":{"draws":294,"losses":148,"wins":130},"GB2-05":{"draws":0,"losses":904,"wins":314},"GB2-06":{"draws":22,"losses":552,"wins":624},"GB2-07":{"draws":0,"losses":678,"wins":558},"GB2-08":{"draws":673,"losses":451,"wins":16}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":93,"losses":207,"wins":456},"GB2-04":{"draws":294,"losses":148,"wins":130},"GB2-05":{"draws":0,"losses":445,"wins":171},"GB2-06":{"draws":16,"losses":189,"wins":405},"GB2-07":{"draws":0,"losses":362,"wins":266},"GB2-08":{"draws":353,"losses":255,"wins":4}},"none":{"GB2-01":{"draws":158,"losses":304,"wins":138},"GB2-02":{"draws":391,"losses":134,"wins":27},"GB2-03":{"draws":220,"losses":245,"wins":71},"GB2-05":{"draws":0,"losses":459,"wins":143},"GB2-06":{"draws":6,"losses":363,"wins":219},"GB2-07":{"draws":0,"losses":316,"wins":292},"GB2-08":{"draws":320,"losses":196,"wins":12}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1701.704765865496,"GB2-04":1464.5364139161593,"GB2-05":1124.291456111921,"GB2-06":1757.9009747684743,"GB2-07":1346.3864660552604,"GB2-08":1211.874967809796},"none":{"GB2-01":1337.3654488226853,"GB2-02":1396.0461278964626,"GB2-03":1296.9016806495238,"GB2-05":1061.6033914378504,"GB2-06":1267.032207057016,"GB2-07":1442.7394900781846,"GB2-08":1245.560058994304}},"per_game_tracks":{"medium":{"GB2-01":55.73033841732697,"GB2-04":16.72351704733886,"GB2-05":29.067787450982248,"GB2-06":61.393153892856006,"GB2-07":40.394652722115254,"GB2-08":14.56429272606512},"none":{"GB2-01":31.67681651381634,"GB2-02":4.175884811179403,"GB2-03":14.97968128549789,"GB2-05":26.270458929666294,"GB2-06":39.34454519902722,"GB2-07":45.11906062181898,"GB2-08":16.727439053570187}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.79239386913817,"none":24.634311285913004},"reasoning_agg":{"medium":{"max":61.393153892856006,"mean":33.79239386913817,"min":14.56429272606512},"none":{"max":45.11906062181898,"mean":24.634311285913004,"min":4.175884811179403}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":61.393153892856006,"reasoning_variance":9.158082583225163},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":61.393153892856006,"expected_score":36.138462113986904,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3460682448487375},"none":{"ceiling_score":45.11906062181898,"expected_score":26.110745765140262,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4764344792272581}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:7528e8434c2eda2e","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":0.18239874999999997}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999999},"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":30.55633205528103,"none":29.607859475793585},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:36:37Z","match_totals_all":{"draws":2484,"losses":3391,"wins":2363},"match_totals_tracks":{"medium":{"draws":1315,"losses":1611,"wins":1260},"none":{"draws":1169,"losses":1780,"wins":1103}},"model_slug":"qwen-qwen3-7-max","overall":{"max":64.55895488159145,"mean":29.094446718629325,"min":8.322182507255533},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":276,"losses":525,"wins":354},"GB2-02":{"draws":841,"losses":193,"wins":84},"GB2-03":{"draws":246,"losses":246,"wins":38},"GB2-04":{"draws":333,"losses":162,"wins":96},"GB2-05":{"draws":0,"losses":750,"wins":506},"GB2-06":{"draws":64,"losses":686,"wins":428},"GB2-07":{"draws":0,"losses":366,"wins":808},"GB2-08":{"draws":724,"losses":463,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":108,"losses":413,"wins":60},"GB2-02":{"draws":447,"losses":95,"wins":26},"GB2-04":{"draws":333,"losses":162,"wins":96},"GB2-05":{"draws":0,"losses":364,"wins":266},"GB2-06":{"draws":60,"losses":214,"wins":322},"GB2-07":{"draws":0,"losses":134,"wins":458},"GB2-08":{"draws":367,"losses":229,"wins":32}},"none":{"GB2-01":{"draws":168,"losses":112,"wins":294},"GB2-02":{"draws":394,"losses":98,"wins":58},"GB2-03":{"draws":246,"losses":246,"wins":38},"GB2-05":{"draws":0,"losses":386,"wins":240},"GB2-06":{"draws":4,"losses":472,"wins":106},"GB2-07":{"draws":0,"losses":232,"wins":350},"GB2-08":{"draws":357,"losses":234,"wins":17}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1126.4033952551288,"GB2-02":1429.0460920969956,"GB2-04":1427.7592120350578,"GB2-05":1352.18275398759,"GB2-06":1594.985386310222,"GB2-07":1839.2108867864213,"GB2-08":1267.9081233751303},"none":{"GB2-01":1663.980000823702,"GB2-02":1446.2697908779405,"GB2-03":1267.114862561006,"GB2-05":1295.6458590327245,"GB2-06":947.7907570970301,"GB2-07":1595.083052964228,"GB2-08":1242.0033590772198}},"per_game_tracks":{"medium":{"GB2-01":17.749194270124892,"GB2-02":8.322182507255533,"GB2-04":11.789067510645198,"GB2-05":39.236977242081366,"GB2-06":54.075389357157675,"GB2-07":64.55895488159145,"GB2-08":18.16255861811108},"none":{"GB2-01":53.23976597622268,"GB2-02":10.486263114718366,"GB2-03":12.721993233426138,"GB2-05":36.7141322701372,"GB2-06":25.00501033345638,"GB2-07":52.58881197904256,"GB2-08":16.499039423551768}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":29.55311298216127,"none":28.63578045509738},"reasoning_agg":{"medium":{"max":64.55895488159145,"mean":29.55311298216127,"min":8.322182507255533},"none":{"max":53.23976597622268,"mean":28.63578045509738,"min":10.486263114718366}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":64.55895488159145,"reasoning_variance":0.9173325270638912},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":64.55895488159145,"expected_score":29.726229825662877,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.1731168435016066},"none":{"ceiling_score":53.23976597622268,"expected_score":31.19423498205029,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.558454526952911}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:ca5706e1289410bb","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":1.2830031539999998}},"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":29.70290685227238},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T10:29:25Z","match_totals_all":{"draws":891,"losses":1423,"wins":1253},"match_totals_tracks":{"medium":{"draws":891,"losses":1423,"wins":1253}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":45.59169591946391,"mean":27.641669446181726,"min":6.593094713947105},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":13,"losses":344,"wins":236},"GB2-02":{"draws":445,"losses":115,"wins":20},"GB2-04":{"draws":371,"losses":164,"wins":47},"GB2-05":{"draws":0,"losses":293,"wins":315},"GB2-07":{"draws":0,"losses":338,"wins":272},"GB2-08":{"draws":62,"losses":169,"wins":363}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":13,"losses":344,"wins":236},"GB2-02":{"draws":445,"losses":115,"wins":20},"GB2-04":{"draws":371,"losses":164,"wins":47},"GB2-05":{"draws":0,"losses":293,"wins":315},"GB2-07":{"draws":0,"losses":338,"wins":272},"GB2-08":{"draws":62,"losses":169,"wins":363}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1371.4273304365654,"GB2-02":1415.2844571490864,"GB2-04":1394.802612026873,"GB2-05":1494.591846233172,"GB2-07":1375.2520948093754,"GB2-08":1653.5909827218904}},"per_game_tracks":{"medium":{"GB2-01":33.925566997635194,"GB2-02":6.593094713947105,"GB2-04":7.367233566694406,"GB2-05":45.59169591946391,"GB2-07":41.810000147883756,"GB2-08":42.92984976800992}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.641669446181726},"reasoning_agg":{"medium":{"max":45.59169591946391,"mean":27.641669446181726,"min":6.593094713947105}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":45.59169591946391},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.59169591946391,"expected_score":29.515004842059273,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8733353958775467}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:8e6f19a50c9cfbcd","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.45756399999999997}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.45756399999999997},"codegen_latency_ms":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8}},"codegen_output_tokens":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8}},"display_name":"GPT-4.1","economics":{"none":26.96122026007302},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:11:21Z","match_totals_all":{"draws":1441,"losses":1973,"wins":1252},"match_totals_tracks":{"none":{"draws":1441,"losses":1973,"wins":1252}},"model_slug":"gpt-4-1","overall":{"max":48.327513299125975,"mean":26.96122026007302,"min":5.3942450203985866},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":213,"wins":332},"GB2-02":{"draws":476,"losses":91,"wins":5},"GB2-03":{"draws":137,"losses":255,"wins":150},"GB2-04":{"draws":382,"losses":167,"wins":29},"GB2-05":{"draws":0,"losses":498,"wins":100},"GB2-06":{"draws":35,"losses":269,"wins":286},"GB2-07":{"draws":0,"losses":311,"wins":283},"GB2-08":{"draws":367,"losses":169,"wins":67}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":44,"losses":213,"wins":332},"GB2-02":{"draws":476,"losses":91,"wins":5},"GB2-03":{"draws":137,"losses":255,"wins":150},"GB2-04":{"draws":382,"losses":167,"wins":29},"GB2-05":{"draws":0,"losses":498,"wins":100},"GB2-06":{"draws":35,"losses":269,"wins":286},"GB2-07":{"draws":0,"losses":311,"wins":283},"GB2-08":{"draws":367,"losses":169,"wins":67}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1589.5739827489053,"GB2-02":1416.7228523950228,"GB2-03":1363.3250595834531,"GB2-04":1380.097628717865,"GB2-05":917.5808955203736,"GB2-06":1463.3430154818905,"GB2-07":1429.1711680035642,"GB2-08":1338.8791826170477}},"per_game_tracks":{"none":{"GB2-01":48.327513299125975,"GB2-02":6.773822634075469,"GB2-03":20.014232762319605,"GB2-04":5.3942450203985866,"GB2-05":19.843745365677297,"GB2-06":48.16234026370232,"GB2-07":44.453774932603764,"GB2-08":22.720087802681135}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":26.96122026007302},"reasoning_agg":{"none":{"max":48.327513299125975,"mean":26.96122026007302,"min":5.3942450203985866}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":48.327513299125975},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":48.327513299125975,"expected_score":29.438340823867104,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.4771205637940845}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:2b64bf35e39106cc","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"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-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.14705250000000003},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.1688104},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":32.13861995969974,"none":18.73221494785713},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T13:12:08Z","match_totals_all":{"draws":3126,"losses":3971,"wins":2132},"match_totals_tracks":{"medium":{"draws":1317,"losses":1729,"wins":1623},"none":{"draws":1809,"losses":2242,"wins":509}},"model_slug":"gpt-5-4-mini","overall":{"max":54.67351609505018,"mean":25.435417453778435,"min":5.972433063334616},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":224,"losses":446,"wins":472},"GB2-02":{"draws":901,"losses":186,"wins":11},"GB2-03":{"draws":634,"losses":291,"wins":146},"GB2-04":{"draws":713,"losses":271,"wins":162},"GB2-05":{"draws":0,"losses":810,"wins":382},"GB2-06":{"draws":75,"losses":650,"wins":439},"GB2-07":{"draws":0,"losses":884,"wins":334},"GB2-08":{"draws":579,"losses":433,"wins":186}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":34,"losses":161,"wins":373},"GB2-02":{"draws":447,"losses":97,"wins":10},"GB2-03":{"draws":212,"losses":199,"wins":132},"GB2-04":{"draws":363,"losses":122,"wins":83},"GB2-05":{"draws":0,"losses":308,"wins":296},"GB2-06":{"draws":53,"losses":273,"wins":266},"GB2-07":{"draws":0,"losses":327,"wins":295},"GB2-08":{"draws":208,"losses":242,"wins":168}},"none":{"GB2-01":{"draws":190,"losses":285,"wins":99},"GB2-02":{"draws":454,"losses":89,"wins":1},"GB2-03":{"draws":422,"losses":92,"wins":14},"GB2-04":{"draws":350,"losses":149,"wins":79},"GB2-05":{"draws":0,"losses":502,"wins":86},"GB2-06":{"draws":22,"losses":377,"wins":173},"GB2-07":{"draws":0,"losses":557,"wins":39},"GB2-08":{"draws":371,"losses":191,"wins":18}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1685.697050875629,"GB2-02":1411.2319132956325,"GB2-03":1403.8961541743147,"GB2-04":1448.5085363007697,"GB2-05":1437.882153190438,"GB2-06":1428.4899201989886,"GB2-07":1426.3499753684273,"GB2-08":1369.9565413606592},"none":{"GB2-01":1311.790325476346,"GB2-02":1410.3446738165392,"GB2-03":1382.6143322432222,"GB2-04":1426.8576544347288,"GB2-05":874.7907369166833,"GB2-06":1167.108282301218,"GB2-07":720.3455517782488,"GB2-08":1269.481405786555}},"per_game_tracks":{"medium":{"GB2-01":54.67351609505018,"GB2-02":6.083910729967143,"GB2-03":23.08931366706954,"GB2-04":14.573033888529471,"GB2-05":43.06114018116994,"GB2-06":46.59682558807083,"GB2-07":44.31544544157652,"GB2-08":24.715774086164263},"none":{"GB2-01":29.988358088331964,"GB2-02":5.972433063334616,"GB2-03":21.47626070661696,"GB2-04":11.668104243846702,"GB2-05":17.934320793135875,"GB2-06":34.856210106200024,"GB2-07":9.698442915100058,"GB2-08":18.263589666290834}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.13861995969974,"none":18.73221494785713},"reasoning_agg":{"medium":{"max":54.67351609505018,"mean":32.13861995969974,"min":6.083910729967143},"none":{"max":34.856210106200024,"mean":18.73221494785713,"min":5.972433063334616}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.67351609505018,"reasoning_variance":13.406405011842608},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":54.67351609505018,"expected_score":30.755195040828195,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.383424918871544},"none":{"ceiling_score":34.856210106200024,"expected_score":19.25015272711497,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5179377792578386}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:264b96442a17a515","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999},"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821378999999998},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":29.14988996947043,"none":25.016436547944473},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:25:09Z","match_totals_all":{"draws":2947,"losses":6902,"wins":4089},"match_totals_tracks":{"medium":{"draws":1230,"losses":3360,"wins":2432},"none":{"draws":1717,"losses":3542,"wins":1657}},"model_slug":"gpt-5-4-nano","overall":{"max":54.12235391803877,"mean":25.203723328408607,"min":4.802393017105402},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":440,"losses":1322,"wins":506},"GB2-02":{"draws":1317,"losses":326,"wins":15},"GB2-03":{"draws":171,"losses":269,"wins":100},"GB2-04":{"draws":288,"losses":125,"wins":163},"GB2-05":{"draws":0,"losses":1641,"wins":743},"GB2-06":{"draws":58,"losses":1111,"wins":1143},"GB2-07":{"draws":0,"losses":1277,"wins":561},"GB2-08":{"draws":673,"losses":831,"wins":858}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":179,"losses":845,"wins":104},"GB2-02":{"draws":436,"losses":102,"wins":2},"GB2-04":{"draws":288,"losses":125,"wins":163},"GB2-05":{"draws":0,"losses":587,"wins":619},"GB2-06":{"draws":54,"losses":456,"wins":658},"GB2-07":{"draws":0,"losses":789,"wins":431},"GB2-08":{"draws":273,"losses":456,"wins":455}},"none":{"GB2-01":{"draws":261,"losses":477,"wins":402},"GB2-02":{"draws":881,"losses":224,"wins":13},"GB2-03":{"draws":171,"losses":269,"wins":100},"GB2-05":{"draws":0,"losses":1054,"wins":124},"GB2-06":{"draws":4,"losses":655,"wins":485},"GB2-07":{"draws":0,"losses":488,"wins":130},"GB2-08":{"draws":400,"losses":375,"wins":403}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1049.424984730046,"GB2-02":1402.1526428170014,"GB2-04":1500.9849018646128,"GB2-05":1505.361332696807,"GB2-06":1596.0309595908739,"GB2-07":1193.290573579564,"GB2-08":1479.3783315716669},"none":{"GB2-01":1458.205254382964,"GB2-02":1401.032443371703,"GB2-03":1310.659011820162,"GB2-05":790.702911357472,"GB2-06":1340.0455383308272,"GB2-07":1043.3769655127883,"GB2-08":1487.9361257131081}},"per_game_tracks":{"medium":{"GB2-01":12.667113371771164,"GB2-02":4.943141060071801,"GB2-04":21.61386256769371,"GB2-05":46.072262544088275,"GB2-06":54.12235391803877,"GB2-07":32.88801293411764,"GB2-08":31.742483390511637},"none":{"GB2-01":39.65460747377084,"GB2-02":4.802393017105402,"GB2-03":16.022416434987296,"GB2-05":14.182071079331639,"GB2-06":42.624123115940954,"GB2-07":25.537407788032592,"GB2-08":32.29203692644258}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.12702924788074,"none":23.280417408936483},"reasoning_agg":{"medium":{"max":54.12235391803877,"mean":27.12702924788074,"min":4.943141060071801},"none":{"max":42.624123115940954,"mean":23.280417408936483,"min":4.802393017105402}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.12235391803877,"reasoning_variance":3.8466118389442556},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":54.12235391803877,"expected_score":28.09129260243595,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9642633545552108},"none":{"ceiling_score":42.624123115940954,"expected_score":26.18122917562269,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.900811766686207}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:1e3168587010809f","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":0.010139173999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725613},"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":27.948876021330474,"none":22.564891750085376},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:13:13Z","match_totals_all":{"draws":2480,"losses":3145,"wins":1891},"match_totals_tracks":{"highest":{"draws":1101,"losses":1809,"wins":1142},"none":{"draws":1379,"losses":1336,"wins":749}},"model_slug":"tencent-hy3-preview","overall":{"max":62.4191883896819,"mean":23.622955397363974,"min":1.5434388218765318},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":50.84250511417906,"GB2-02":3.377757460965938,"GB2-04":10.7755394598517,"GB2-05":50.752870481013716,"GB2-06":25.300994686544374,"GB2-07":30.654752048438247,"GB2-08":23.93771289832029},"per_game_match_totals_all":{"GB2-01":{"draws":194,"losses":251,"wins":709},"GB2-02":{"draws":816,"losses":257,"wins":7},"GB2-03":{"draws":147,"losses":302,"wins":105},"GB2-04":{"draws":764,"losses":228,"wins":132},"GB2-05":{"draws":0,"losses":731,"wins":467},"GB2-06":{"draws":2,"losses":467,"wins":103},"GB2-07":{"draws":0,"losses":446,"wins":164},"GB2-08":{"draws":557,"losses":463,"wins":204}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":99,"losses":168,"wins":309},"GB2-02":{"draws":408,"losses":125,"wins":7},"GB2-04":{"draws":423,"losses":112,"wins":33},"GB2-05":{"draws":0,"losses":239,"wins":353},"GB2-06":{"draws":2,"losses":467,"wins":103},"GB2-07":{"draws":0,"losses":446,"wins":164},"GB2-08":{"draws":169,"losses":252,"wins":173}},"none":{"GB2-01":{"draws":95,"losses":83,"wins":400},"GB2-02":{"draws":408,"losses":132,"wins":0},"GB2-03":{"draws":147,"losses":302,"wins":105},"GB2-04":{"draws":341,"losses":116,"wins":99},"GB2-05":{"draws":0,"losses":492,"wins":114},"GB2-08":{"draws":388,"losses":211,"wins":31}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.668628678114,"GB2-02":1389.6939130013682,"GB2-04":1420.2052335296523,"GB2-05":1610.2536436385037,"GB2-06":954.3802647017818,"GB2-07":1147.7438205608803,"GB2-08":1357.8403651563985},"none":{"GB2-01":1803.0209490217737,"GB2-02":1375.094756390012,"GB2-03":1283.2033052366983,"GB2-04":1468.0481009856967,"GB2-05":957.6525585350922,"GB2-08":1275.635118429697}},"per_game_tracks":{"highest":{"GB2-01":50.84250511417906,"GB2-02":3.377757460965938,"GB2-04":10.7755394598517,"GB2-05":50.752870481013716,"GB2-06":25.300994686544374,"GB2-07":30.654752048438247,"GB2-08":23.93771289832029},"none":{"GB2-01":62.4191883896819,"GB2-02":1.5434388218765318,"GB2-03":13.94141468010135,"GB2-04":17.194685101105243,"GB2-05":21.631862552424636,"GB2-08":18.6587609553226}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.246912886985616,"none":20.99899790774233},"reasoning_agg":{"highest":{"max":50.84250511417906,"mean":26.246912886985616,"min":3.377757460965938},"none":{"max":62.4191883896819,"mean":20.99899790774233,"min":1.5434388218765318}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":62.4191883896819,"reasoning_variance":5.247914979243287},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.84250511417906,"expected_score":19.330093240632316,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.9168196463533},"none":{"ceiling_score":62.4191883896819,"expected_score":25.91345333334637,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.914455425604043}}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:c6ab2531e1444a25","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":0.09094181999999998},"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":20.392244441647097,"none":28.425609598992487},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":0.5384615384615384,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.15384615384615385,"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},"performance_rejected_game_aliases":["GB2-07"],"performance_rejections":1,"repaired_admitted":4,"repaired_rate":0.3076923076923077},"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":"2026-10-13T14:18:47Z","match_totals_all":{"draws":5217,"losses":7101,"wins":3425},"match_totals_tracks":{"medium":{"draws":3301,"losses":3764,"wins":1346},"none":{"draws":1916,"losses":3337,"wins":2079}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":44.21925657528032,"mean":23.45456197152452,"min":5.288115024538477},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":327,"losses":919,"wins":744},"GB2-02":{"draws":1679,"losses":322,"wins":23},"GB2-03":{"draws":1049,"losses":1246,"wins":579},"GB2-04":{"draws":443,"losses":223,"wins":66},"GB2-05":{"draws":0,"losses":1716,"wins":1083},"GB2-06":{"draws":32,"losses":1050,"wins":284},"GB2-07":{"draws":0,"losses":692,"wins":528},"GB2-08":{"draws":1687,"losses":933,"wins":118}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":132,"losses":421,"wins":263},"GB2-02":{"draws":1228,"losses":208,"wins":2},"GB2-03":{"draws":547,"losses":682,"wins":307},"GB2-04":{"draws":443,"losses":223,"wins":66},"GB2-05":{"draws":0,"losses":1122,"wins":485},"GB2-06":{"draws":15,"losses":603,"wins":156},"GB2-08":{"draws":936,"losses":505,"wins":67}},"none":{"GB2-01":{"draws":195,"losses":498,"wins":481},"GB2-02":{"draws":451,"losses":114,"wins":21},"GB2-03":{"draws":502,"losses":564,"wins":272},"GB2-05":{"draws":0,"losses":594,"wins":598},"GB2-06":{"draws":17,"losses":447,"wins":128},"GB2-07":{"draws":0,"losses":692,"wins":528},"GB2-08":{"draws":751,"losses":428,"wins":51}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1399.3028887814037,"GB2-02":1420.5113284222136,"GB2-03":1340.1121138718772,"GB2-04":1382.4333343784006,"GB2-05":1142.9160569478663,"GB2-06":1012.4635885615988,"GB2-08":1264.7338535402394},"none":{"GB2-01":1487.5947660055717,"GB2-02":1404.8982557256668,"GB2-03":1352.8754833205253,"GB2-05":1463.835513641623,"GB2-06":1020.1572669259306,"GB2-07":1390.502367321661,"GB2-08":1262.908616639548}},"per_game_tracks":{"medium":{"GB2-01":35.765899132696454,"GB2-02":7.249827678436319,"GB2-03":18.25481052290231,"GB2-04":5.7076299742551395,"GB2-05":29.898872720361517,"GB2-06":27.909953666340027,"GB2-08":17.958717396537885},"none":{"GB2-01":41.59489014017548,"GB2-02":5.288115024538477,"GB2-03":19.222208471308843,"GB2-05":44.21925657528032,"GB2-06":28.25553463386054,"GB2-07":42.557755692250836,"GB2-08":17.841506655532882}},"provider_color":"#4137FF","provider_company":"Poolside","provider_key":"poolside","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":19.55813149045263,"none":27.35099245259641},"reasoning_agg":{"medium":{"max":35.765899132696454,"mean":19.55813149045263,"min":5.7076299742551395},"none":{"max":44.21925657528032,"mean":27.35099245259641,"min":5.288115024538477}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":44.21925657528032,"reasoning_variance":7.792860962143781},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":35.765899132696454,"expected_score":16.820978216699075,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.737153273753556},"none":{"ceiling_score":44.21925657528032,"expected_score":29.747907583672706,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3969151310762946}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:c142af8439c129ad","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":33.40550021902565,"none":17.421878397670852},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:42:13Z","match_totals_all":{"draws":2011,"losses":3542,"wins":1554},"match_totals_tracks":{"medium":{"draws":1020,"losses":1488,"wins":1100},"none":{"draws":991,"losses":2054,"wins":454}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":63.03588202454918,"mean":23.414882525671988,"min":3.789205243077069},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":235,"losses":650,"wins":297},"GB2-02":{"draws":914,"losses":185,"wins":9},"GB2-04":{"draws":403,"losses":114,"wins":50},"GB2-05":{"draws":0,"losses":732,"wins":496},"GB2-06":{"draws":28,"losses":659,"wins":475},"GB2-07":{"draws":0,"losses":1005,"wins":227},"GB2-08":{"draws":431,"losses":197,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":103,"losses":255,"wins":238},"GB2-02":{"draws":462,"losses":74,"wins":8},"GB2-05":{"draws":0,"losses":336,"wins":290},"GB2-06":{"draws":24,"losses":159,"wins":397},"GB2-07":{"draws":0,"losses":467,"wins":167},"GB2-08":{"draws":431,"losses":197,"wins":0}},"none":{"GB2-01":{"draws":132,"losses":395,"wins":59},"GB2-02":{"draws":452,"losses":111,"wins":1},"GB2-04":{"draws":403,"losses":114,"wins":50},"GB2-05":{"draws":0,"losses":396,"wins":206},"GB2-06":{"draws":4,"losses":500,"wins":78},"GB2-07":{"draws":0,"losses":538,"wins":60}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1471.5168083575763,"GB2-02":1424.920898390236,"GB2-05":1412.4120214732918,"GB2-06":1794.473075298104,"GB2-07":1124.688586913406,"GB2-08":1259.3180164701685},"none":{"GB2-01":1160.830422449215,"GB2-02":1392.9685843046143,"GB2-04":1429.0686996110637,"GB2-05":1218.7537718271722,"GB2-06":870.910063656209,"GB2-07":806.4543341451955}},"per_game_tracks":{"medium":{"GB2-01":40.53343042841912,"GB2-02":7.80387039460395,"GB2-05":41.92458689523771,"GB2-06":63.03588202454918,"GB2-07":29.52430150909941,"GB2-08":17.6109300622445},"none":{"GB2-01":20.022051504987644,"GB2-02":3.789205243077069,"GB2-04":11.964763323056882,"GB2-05":33.28297787540641,"GB2-06":21.551720091158273,"GB2-07":13.920552348338846}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.08732082456152,"none":15.742444226782455},"reasoning_agg":{"medium":{"max":63.03588202454918,"mean":31.08732082456152,"min":7.80387039460395},"none":{"max":33.28297787540641,"mean":15.742444226782455,"min":3.789205243077069}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.03588202454918,"reasoning_variance":15.344876597779065},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.03588202454918,"expected_score":32.73360079871608,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.646279974154563},"none":{"ceiling_score":33.28297787540641,"expected_score":15.48249049791315,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.2599537288693057}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:996839815f24af4e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":22.592889144277127},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T11:42:16Z","match_totals_all":{"draws":1561,"losses":2245,"wins":921},"match_totals_tracks":{"medium":{"draws":1561,"losses":2245,"wins":921}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":44.36986043634203,"mean":22.592889144277127,"min":8.099159062043583},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":114,"losses":301,"wins":173},"GB2-02":{"draws":462,"losses":80,"wins":12},"GB2-03":{"draws":163,"losses":289,"wins":79},"GB2-04":{"draws":427,"losses":128,"wins":31},"GB2-05":{"draws":0,"losses":305,"wins":307},"GB2-06":{"draws":4,"losses":405,"wins":205},"GB2-07":{"draws":0,"losses":526,"wins":88},"GB2-08":{"draws":391,"losses":211,"wins":26}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":114,"losses":301,"wins":173},"GB2-02":{"draws":462,"losses":80,"wins":12},"GB2-03":{"draws":163,"losses":289,"wins":79},"GB2-04":{"draws":427,"losses":128,"wins":31},"GB2-05":{"draws":0,"losses":305,"wins":307},"GB2-06":{"draws":4,"losses":405,"wins":205},"GB2-07":{"draws":0,"losses":526,"wins":88},"GB2-08":{"draws":391,"losses":211,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1367.9381757286806,"GB2-02":1427.2710710427093,"GB2-03":1266.2990675811275,"GB2-04":1407.314380018841,"GB2-05":1467.2105425345324,"GB2-06":1191.2282686578137,"GB2-07":909.6809488175392,"GB2-08":1264.6160979451245}},"per_game_tracks":{"medium":{"GB2-01":33.69521453424464,"GB2-02":8.099159062043583,"GB2-03":12.660160157683084,"GB2-04":9.045955291386294,"GB2-05":44.36986043634203,"GB2-06":35.93962012504579,"GB2-07":18.981988029918114,"GB2-08":17.95115551755348}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.592889144277127},"reasoning_agg":{"medium":{"max":44.36986043634203,"mean":22.592889144277127,"min":8.099159062043583}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":44.36986043634203},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":44.36986043634203,"expected_score":19.36767514987345,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.2252139944036777}}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:6b5ca8216d334a6a","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.214047204}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.214047204}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.60040646},"codegen_latency_ms":{"attempt_count":87,"max_ms":1635062,"mean_ms":598630.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":49,"max_ms":1635062,"mean_ms":1021590.9375,"min_ms":525940,"run_count":16},"none":{"attempt_count":38,"max_ms":457140,"mean_ms":175670.5625,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":110598,"output_mean":38325.9375,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":59,"output_max":110598,"output_mean":68392.8125,"output_min":16796,"run_count":16},"none":{"attempt_count":38,"output_max":22812,"output_mean":8259.0625,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":22.003282241337747,"none":22.854597770238378},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:19:08Z","match_totals_all":{"draws":4480,"losses":8812,"wins":3739},"match_totals_tracks":{"medium":{"draws":2184,"losses":4603,"wins":2024},"none":{"draws":2296,"losses":4209,"wins":1715}},"model_slug":"meituan-longcat-2-0","overall":{"max":39.85175191442988,"mean":21.290300894377012,"min":4.732430760608853},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":314,"losses":537,"wins":365},"GB2-02":{"draws":1057,"losses":198,"wins":5},"GB2-03":{"draws":626,"losses":826,"wins":351},"GB2-04":{"draws":1082,"losses":528,"wins":206},"GB2-05":{"draws":0,"losses":2043,"wins":745},"GB2-06":{"draws":144,"losses":1789,"wins":769},"GB2-07":{"draws":0,"losses":1781,"wins":965},"GB2-08":{"draws":1257,"losses":1110,"wins":333}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":587,"losses":93,"wins":4},"GB2-03":{"draws":274,"losses":300,"wins":161},"GB2-04":{"draws":753,"losses":388,"wins":110},"GB2-05":{"draws":0,"losses":1025,"wins":569},"GB2-06":{"draws":68,"losses":1085,"wins":361},"GB2-07":{"draws":0,"losses":983,"wins":547},"GB2-08":{"draws":502,"losses":729,"wins":272}},"none":{"GB2-01":{"draws":314,"losses":537,"wins":365},"GB2-02":{"draws":470,"losses":105,"wins":1},"GB2-03":{"draws":352,"losses":526,"wins":190},"GB2-04":{"draws":329,"losses":140,"wins":96},"GB2-05":{"draws":0,"losses":1018,"wins":176},"GB2-06":{"draws":76,"losses":704,"wins":408},"GB2-07":{"draws":0,"losses":798,"wins":418},"GB2-08":{"draws":755,"losses":381,"wins":61}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1428.096049176631,"GB2-03":1365.8836886128688,"GB2-04":1381.3509063191132,"GB2-05":1242.0506280630593,"GB2-06":1082.3589675700996,"GB2-07":1259.5013980088456,"GB2-08":1273.833778262218},"none":{"GB2-01":1402.3086540340619,"GB2-02":1400.475620844956,"GB2-03":1302.0965038660077,"GB2-04":1448.888823555516,"GB2-05":870.4805668520918,"GB2-06":1278.3241637887058,"GB2-07":1252.8834673634572,"GB2-08":1276.8815863626387}},"per_game_tracks":{"medium":{"GB2-02":8.20281386952174,"GB2-03":20.20816372104871,"GB2-04":5.562399060469946,"GB2-05":34.322553123812504,"GB2-06":31.04948089364811,"GB2-07":36.134480236536426,"GB2-08":18.54308478432675},"none":{"GB2-01":35.96433843627875,"GB2-02":4.732430760608853,"GB2-03":15.373422244120174,"GB2-04":14.624057570919984,"GB2-05":17.741988142318036,"GB2-06":39.85175191442988,"GB2-07":35.809988046095924,"GB2-08":18.73880504713541}},"provider_color":"#29E154","provider_company":"Meituan","provider_key":"meituan","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":20.47636136998384,"none":22.104240418770182},"reasoning_agg":{"medium":{"max":36.134480236536426,"mean":20.47636136998384,"min":5.562399060469946},"none":{"max":39.85175191442988,"mean":22.104240418770182,"min":4.732430760608853}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":39.85175191442988,"reasoning_variance":1.6278790487863404},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.134480236536426,"expected_score":18.935425401289184,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.540935968694658},"none":{"ceiling_score":39.85175191442988,"expected_score":24.19911429297961,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.0948738742094264}}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:eb4b745f99eebdb9","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"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":16.78500328769267,"none":26.79023176578742},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:28:18Z","match_totals_all":{"draws":1959,"losses":4054,"wins":1671},"match_totals_tracks":{"medium":{"draws":1243,"losses":2321,"wins":588},"none":{"draws":716,"losses":1733,"wins":1083}},"model_slug":"minimax-minimax-m3","overall":{"max":46.122480040625916,"mean":20.582520722280723,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":136,"losses":650,"wins":410},"GB2-02":{"draws":879,"losses":224,"wins":5},"GB2-03":{"draws":136,"losses":265,"wins":153},"GB2-04":{"draws":392,"losses":143,"wins":45},"GB2-05":{"draws":0,"losses":1013,"wins":213},"GB2-06":{"draws":5,"losses":474,"wins":117},"GB2-07":{"draws":0,"losses":805,"wins":417},"GB2-08":{"draws":411,"losses":480,"wins":311}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":32,"losses":446,"wins":112},"GB2-02":{"draws":431,"losses":114,"wins":1},"GB2-04":{"draws":392,"losses":143,"wins":45},"GB2-05":{"draws":0,"losses":597,"wins":11},"GB2-06":{"draws":5,"losses":474,"wins":117},"GB2-07":{"draws":0,"losses":350,"wins":268},"GB2-08":{"draws":383,"losses":197,"wins":34}},"none":{"GB2-01":{"draws":104,"losses":204,"wins":298},"GB2-02":{"draws":448,"losses":110,"wins":4},"GB2-03":{"draws":136,"losses":265,"wins":153},"GB2-05":{"draws":0,"losses":416,"wins":202},"GB2-07":{"draws":0,"losses":455,"wins":149},"GB2-08":{"draws":28,"losses":283,"wins":277}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1157.9897544261548,"GB2-02":1390.4040725493655,"GB2-04":1407.2829408571204,"GB2-05":472.8830406276762,"GB2-06":973.020792504509,"GB2-07":1351.5396354632683,"GB2-08":1271.0790156093108},"none":{"GB2-01":1556.1742870751777,"GB2-02":1399.3838762450507,"GB2-03":1356.1877600003431,"GB2-05":1195.8660142975625,"GB2-07":1108.9392631798787,"GB2-08":1445.0286053396878}},"per_game_tracks":{"medium":{"GB2-01":19.834511848087953,"GB2-02":3.466985827391268,"GB2-04":9.0417370542978,"GB2-05":0.0,"GB2-06":26.13828100501384,"GB2-07":40.64732433783861,"GB2-08":18.366182941219233},"none":{"GB2-01":46.122480040625916,"GB2-02":4.595257941517805,"GB2-03":19.473262056923726,"GB2-05":32.26165783211875,"GB2-07":28.75207634838245,"GB2-08":29.536656375155864}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":16.23392158684825,"none":24.931119857713195},"reasoning_agg":{"medium":{"max":40.64732433783861,"mean":16.23392158684825,"min":0.0},"none":{"max":46.122480040625916,"mean":24.931119857713195,"min":4.595257941517805}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":46.122480040625916,"reasoning_variance":8.697198270864945},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.64732433783861,"expected_score":12.087912218810771,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.146009368037479},"none":{"ceiling_score":46.122480040625916,"expected_score":29.290483185972423,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.359363328259228}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:b01aa117506268d3","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.030739789999999996},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.01492467}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.030739789999999996},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.01492467}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0061656,"mean":0.0028540287500000002,"median":0.00232709,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"recorded_attempt_count":25,"run_count":16,"total":0.04566446},"codegen_latency_ms":{"attempt_count":25,"max_ms":425398,"mean_ms":137358.0,"min_ms":22859,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":14,"max_ms":425398,"mean_ms":207893.5,"min_ms":65353,"run_count":8},"none":{"attempt_count":11,"max_ms":256957,"mean_ms":66822.5,"min_ms":22859,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":12120,"output_mean":4888.4375,"output_min":1108,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":14,"output_max":12120,"output_mean":7438.375,"output_min":3314,"run_count":8},"none":{"attempt_count":11,"output_max":4877,"output_mean":2338.5,"output_min":1108,"run_count":8}},"display_name":"Gemma 4 31B","economics":{"medium":24.684820527186126,"none":17.1223174546531},"first_seen_at":"2026-10-13T14:28:27Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[16384],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":26,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[16384],"total_output_tokens":78215,"total_reasoning_output_tokens":27437,"total_visible_output_tokens":50778,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":16384,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-10-13T14:28:20Z","match_totals_all":{"draws":1747,"losses":3125,"wins":1024},"match_totals_tracks":{"medium":{"draws":1019,"losses":1627,"wins":758},"none":{"draws":728,"losses":1498,"wins":266}},"model_slug":"google-gemma-4-31b-it","overall":{"max":58.182750378102355,"mean":20.309466174787495,"min":4.905877337510499},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":312,"wins":36},"GB2-02":{"draws":669,"losses":170,"wins":13},"GB2-03":{"draws":100,"losses":209,"wins":131},"GB2-04":{"draws":570,"losses":218,"wins":104},"GB2-05":{"draws":0,"losses":542,"wins":426},"GB2-06":{"draws":37,"losses":705,"wins":170},"GB2-07":{"draws":0,"losses":819,"wins":121},"GB2-08":{"draws":253,"losses":150,"wins":23}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":118,"losses":312,"wins":36},"GB2-02":{"draws":340,"losses":76,"wins":10},"GB2-03":{"draws":100,"losses":209,"wins":131},"GB2-04":{"draws":291,"losses":113,"wins":42},"GB2-05":{"draws":0,"losses":135,"wins":349},"GB2-06":{"draws":35,"losses":320,"wins":101},"GB2-07":{"draws":0,"losses":393,"wins":77},"GB2-08":{"draws":135,"losses":69,"wins":12}},"none":{"GB2-02":{"draws":329,"losses":94,"wins":3},"GB2-04":{"draws":279,"losses":105,"wins":62},"GB2-05":{"draws":0,"losses":407,"wins":77},"GB2-06":{"draws":2,"losses":385,"wins":69},"GB2-07":{"draws":0,"losses":426,"wins":44},"GB2-08":{"draws":118,"losses":81,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1177.5054953735162,"GB2-02":1424.9885006319419,"GB2-03":1389.1481646397112,"GB2-04":1425.478927950996,"GB2-05":1776.7570728782548,"GB2-06":1138.7998521362242,"GB2-07":1023.0698740643306,"GB2-08":1277.5158642398824},"none":{"GB2-02":1401.8560646162452,"GB2-04":1450.1445381575693,"GB2-05":975.6406385885106,"GB2-06":962.0276616684064,"GB2-07":865.190145016685,"GB2-08":1267.8051327055664}},"per_game_tracks":{"medium":{"GB2-01":21.122932505377147,"GB2-02":7.812364313486135,"GB2-03":21.97149169409457,"GB2-04":11.483118548608727,"GB2-05":58.182750378102355,"GB2-06":33.58466557026528,"GB2-07":24.54170491070231,"GB2-08":18.77953629685244},"none":{"GB2-02":4.905877337510499,"GB2-04":14.79253858685898,"GB2-05":22.434544364963582,"GB2-06":25.644496808363208,"GB2-07":16.800502735892316,"GB2-08":18.155944894330013}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.684820527186126,"none":15.934111822388866},"reasoning_agg":{"medium":{"max":58.182750378102355,"mean":24.684820527186126,"min":7.812364313486135},"none":{"max":25.644496808363208,"mean":15.934111822388866,"min":4.905877337510499}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":58.182750378102355,"reasoning_variance":8.75070870479726},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":58.182750378102355,"expected_score":21.72224892745966,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9625715997264663},"none":{"ceiling_score":25.644496808363208,"expected_score":17.186406189031967,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2522943666431008}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:2aacde13c82c4c44","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":0.19736108440000003},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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":0.0689052158}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.0306854728},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"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":0.7524538072},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":19.25308623397644,"highest":20.25817767495714,"medium":21.55313139477439,"none":22.718979101984687},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:14:45Z","match_totals_all":{"draws":6970,"losses":10300,"wins":3969},"match_totals_tracks":{"highest":{"draws":1468,"losses":1027,"wins":327},"medium":{"draws":3144,"losses":4146,"wins":1444},"none":{"draws":2358,"losses":5127,"wins":2198}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":46.75035131768862,"mean":19.391751361181544,"min":5.347473149952944},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":21.73154556568388,"GB2-02":8.20688185813198,"GB2-04":7.671885925214851,"GB2-06":46.75035131768862,"GB2-08":16.930223708066364},"per_game_all":{"GB2-01":28.183345433279545,"GB2-02":6.8929504166139415,"GB2-04":8.154578275470172,"GB2-06":36.84626240299095,"GB2-08":16.1882946415276},"per_game_match_totals_all":{"GB2-01":{"draws":721,"losses":1841,"wins":874},"GB2-02":{"draws":2194,"losses":450,"wins":64},"GB2-03":{"draws":203,"losses":204,"wins":123},"GB2-04":{"draws":2205,"losses":935,"wins":261},"GB2-05":{"draws":0,"losses":2058,"wins":892},"GB2-06":{"draws":85,"losses":1840,"wins":959},"GB2-07":{"draws":0,"losses":1743,"wins":645},"GB2-08":{"draws":1562,"losses":1229,"wins":151}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":257,"losses":293,"wins":6},"GB2-02":{"draws":436,"losses":85,"wins":15},"GB2-04":{"draws":365,"losses":155,"wins":44},"GB2-06":{"draws":36,"losses":297,"wins":253},"GB2-08":{"draws":374,"losses":197,"wins":9}},"medium":{"GB2-01":{"draws":146,"losses":719,"wins":291},"GB2-02":{"draws":1335,"losses":266,"wins":43},"GB2-04":{"draws":1104,"losses":497,"wins":109},"GB2-05":{"draws":0,"losses":859,"wins":363},"GB2-06":{"draws":29,"losses":443,"wins":128},"GB2-07":{"draws":0,"losses":826,"wins":376},"GB2-08":{"draws":530,"losses":536,"wins":134}},"none":{"GB2-01":{"draws":318,"losses":829,"wins":577},"GB2-02":{"draws":423,"losses":99,"wins":6},"GB2-03":{"draws":203,"losses":204,"wins":123},"GB2-04":{"draws":736,"losses":283,"wins":108},"GB2-05":{"draws":0,"losses":1199,"wins":529},"GB2-06":{"draws":20,"losses":1100,"wins":578},"GB2-07":{"draws":0,"losses":917,"wins":269},"GB2-08":{"draws":658,"losses":496,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1284.4497522067225,"GB2-02":1417.6709783732367,"GB2-04":1400.6708117296641,"GB2-06":1211.4128700496747,"GB2-08":1237.1643585045367},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1186.7241731049933,"GB2-02":1428.1284258867338,"GB2-04":1397.0732323279913,"GB2-06":1431.9078676421113,"GB2-08":1248.7178756850506},"medium":{"GB2-01":1272.9678024323887,"GB2-02":1419.5138281878392,"GB2-04":1389.9454245082015,"GB2-05":1135.4205980312813,"GB2-06":1043.7326433402666,"GB2-07":1208.476026223043,"GB2-08":1251.2853461902057},"none":{"GB2-01":1393.6572810827852,"GB2-02":1405.3706810451372,"GB2-03":1385.2901372033016,"GB2-04":1414.9937783527998,"GB2-05":1230.7011571522062,"GB2-06":1158.5980991666459,"GB2-07":1061.5031409608189,"GB2-08":1211.4898536383541}},"per_game_tracks":{"highest":{"GB2-01":21.73154556568388,"GB2-02":8.20688185813198,"GB2-04":7.671885925214851,"GB2-06":46.75035131768862,"GB2-08":16.930223708066364},"medium":{"GB2-01":27.425312145426915,"GB2-02":7.1244962417569,"GB2-04":6.715537802056596,"GB2-05":29.564402975335433,"GB2-06":29.3144821236201,"GB2-07":33.63259021289988,"GB2-08":17.0950982623249},"none":{"GB2-01":35.393178588727835,"GB2-02":5.347473149952944,"GB2-03":21.679072999964074,"GB2-04":10.076311099139069,"GB2-05":33.81610586234669,"GB2-06":34.47395376766414,"GB2-07":26.426175393891203,"GB2-08":14.539561954191537}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":18.01235012214323,"medium":19.475452712384385,"none":20.687451249017023},"reasoning_agg":{"highest":{"max":46.75035131768862,"mean":18.01235012214323,"min":7.671885925214851},"medium":{"max":33.63259021289988,"mean":19.475452712384385,"min":6.715537802056596},"none":{"max":35.393178588727835,"mean":20.687451249017023,"min":5.347473149952944}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":46.75035131768862,"expected_score":15.477510539561749,"reasoning_variance":2.6751011268737948,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.9142408216197957},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":46.75035131768862,"expected_score":13.481975311675802,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.530374810467427},"medium":{"ceiling_score":33.63259021289988,"expected_score":17.67535303255053,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8000996798338562},"none":{"ceiling_score":35.393178588727835,"expected_score":23.998426793188543,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.3109755441715194}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:b57bb69ec0ce5eaa","codegen_cost_by_reasoning":{"medium":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":2,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":3,"run_count":2,"total":0.0},"codegen_latency_ms":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1}},"codegen_output_tokens":{"attempt_count":3,"output_max":32768,"output_mean":19502.5,"output_min":6237,"run_count":2},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":1,"output_max":32768,"output_mean":32768.0,"output_min":32768,"run_count":1},"none":{"attempt_count":2,"output_max":6237,"output_mean":6237.0,"output_min":6237,"run_count":1}},"display_name":"Ling 3.1 Flash","economics":{"none":18.847645778583264},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":3,"effective_max_output_tokens":[32768],"finish_reason_observations":2,"finish_reasons":["stop"],"indexed_attempts":3,"output_token_observations":3,"provider_post_attempt_observations":3,"provider_post_attempts":4,"reasoning_token_observations":3,"reconciliation_get_attempt_observations":3,"requested_max_output_token_observations":3,"requested_max_output_tokens":[32768],"total_output_tokens":39005,"total_reasoning_output_tokens":30791,"total_visible_output_tokens":8214,"visible_token_observations":3},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-13T14:11:08Z","match_totals_all":{"draws":153,"losses":98,"wins":13},"match_totals_tracks":{"none":{"draws":153,"losses":98,"wins":13}},"model_slug":"inclusionai-ling-3-1-flash","overall":{"max":18.847645778583264,"mean":18.847645778583264,"min":18.847645778583264},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":153,"losses":98,"wins":13}},"per_game_match_totals_tracks":{"none":{"GB2-08":{"draws":153,"losses":98,"wins":13}}},"per_game_raw_elo_tracks":{"none":{"GB2-08":1278.5764832435345}},"per_game_tracks":{"none":{"GB2-08":18.847645778583264}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":18.847645778583264},"reasoning_agg":{"none":{"max":18.847645778583264,"mean":18.847645778583264,"min":18.847645778583264}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":18.847645778583264},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":18.847645778583264,"expected_score":22.46081045180223,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.613164673218968}}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:58ee641433c53262","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.3975426639832813},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167188}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281}},"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":20.38127979647842,"none":13.699314705094716},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T14:07:27Z","match_totals_all":{"draws":2871,"losses":4606,"wins":1207},"match_totals_tracks":{"highest":{"draws":1515,"losses":2171,"wins":748},"none":{"draws":1356,"losses":2435,"wins":459}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":38.09790942240539,"mean":16.48083379219175,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-02":9.033622214802557,"GB2-03":17.919796666483563,"GB2-04":7.086798755689644,"GB2-05":38.09790942240539,"GB2-06":32.692014457333855,"GB2-07":19.1605833745525,"GB2-08":18.678233684081423},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":507,"wins":40},"GB2-02":{"draws":970,"losses":216,"wins":28},"GB2-03":{"draws":350,"losses":603,"wins":275},"GB2-04":{"draws":698,"losses":410,"wins":90},"GB2-05":{"draws":0,"losses":938,"wins":358},"GB2-06":{"draws":27,"losses":919,"wins":264},"GB2-07":{"draws":0,"losses":572,"wins":78},"GB2-08":{"draws":761,"losses":441,"wins":74}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":499,"losses":104,"wins":27},"GB2-03":{"draws":186,"losses":285,"wins":135},"GB2-04":{"draws":413,"losses":159,"wins":36},"GB2-05":{"draws":0,"losses":385,"wins":277},"GB2-06":{"draws":24,"losses":427,"wins":155},"GB2-07":{"draws":0,"losses":572,"wins":78},"GB2-08":{"draws":393,"losses":239,"wins":40}},"none":{"GB2-01":{"draws":65,"losses":507,"wins":40},"GB2-02":{"draws":471,"losses":112,"wins":1},"GB2-03":{"draws":164,"losses":318,"wins":140},"GB2-04":{"draws":285,"losses":251,"wins":54},"GB2-05":{"draws":0,"losses":553,"wins":81},"GB2-06":{"draws":3,"losses":492,"wins":109},"GB2-08":{"draws":368,"losses":202,"wins":34}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1434.7083688076398,"GB2-03":1335.6921069585567,"GB2-04":1392.7124887857462,"GB2-05":1326.6562716299125,"GB2-06":1118.9267364269526,"GB2-07":913.3233526694628,"GB2-08":1275.9383529522588},"none":{"GB2-01":1027.7116609776708,"GB2-02":1401.5765864283835,"GB2-03":1313.4156507052207,"GB2-04":1339.8935012592522,"GB2-05":890.4940551397212,"GB2-06":983.834860967506,"GB2-08":1270.0546902047308}},"per_game_tracks":{"highest":{"GB2-02":9.033622214802557,"GB2-03":17.919796666483563,"GB2-04":7.086798755689644,"GB2-05":38.09790942240539,"GB2-06":32.692014457333855,"GB2-07":19.1605833745525,"GB2-08":18.678233684081423},"none":{"GB2-01":11.233609261605627,"GB2-02":4.8707621549789994,"GB2-03":16.231355525298273,"GB2-04":0.0,"GB2-05":18.635049714550068,"GB2-06":26.62402216357345,"GB2-08":18.300404115656598}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.71212590099692,"none":13.249541683386578},"reasoning_agg":{"highest":{"max":38.09790942240539,"mean":19.71212590099692,"min":7.086798755689644},"none":{"max":26.62402216357345,"mean":13.249541683386578,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":38.09790942240539,"reasoning_variance":6.462584217610342},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":38.09790942240539,"expected_score":8.870439711951205,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.841686189045715},"none":{"ceiling_score":26.62402216357345,"expected_score":11.501598206601463,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.7479434767851156}}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:ffc7b0980fa12b22","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":3.40579925},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":17.286559468493763,"none":21.60733265459172},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":"2026-10-13T12:05:12Z","match_totals_all":{"draws":1833,"losses":4002,"wins":1163},"match_totals_tracks":{"medium":{"draws":306,"losses":2214,"wins":438},"none":{"draws":1527,"losses":1788,"wins":725}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":55.53781781902651,"mean":16.47157840750048,"min":1.0584933657452227},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":400,"losses":149,"wins":9},"GB2-03":{"draws":457,"losses":494,"wins":111},"GB2-04":{"draws":449,"losses":114,"wins":29},"GB2-05":{"draws":0,"losses":926,"wins":290},"GB2-06":{"draws":53,"losses":981,"wins":128},"GB2-07":{"draws":0,"losses":654,"wins":548},"GB2-08":{"draws":474,"losses":684,"wins":48}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":191,"losses":273,"wins":70},"GB2-05":{"draws":0,"losses":519,"wins":93},"GB2-06":{"draws":45,"losses":484,"wins":67},"GB2-07":{"draws":0,"losses":451,"wins":163},"GB2-08":{"draws":70,"losses":487,"wins":45}},"none":{"GB2-02":{"draws":400,"losses":149,"wins":9},"GB2-03":{"draws":266,"losses":221,"wins":41},"GB2-04":{"draws":449,"losses":114,"wins":29},"GB2-05":{"draws":0,"losses":407,"wins":197},"GB2-06":{"draws":8,"losses":497,"wins":61},"GB2-07":{"draws":0,"losses":203,"wins":385},"GB2-08":{"draws":404,"losses":197,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1275.9224395956064,"GB2-05":897.4054488162127,"GB2-06":910.5788334363277,"GB2-07":1128.42980448626,"GB2-08":1001.5590602878265},"none":{"GB2-02":1372.4013560884616,"GB2-03":1289.4315878774444,"GB2-04":1417.4664894835046,"GB2-05":1210.7511647384863,"GB2-06":826.5517546850401,"GB2-07":1655.227231150353,"GB2-08":1252.9467527471552}},"per_game_tracks":{"medium":{"GB2-03":13.389562403776162,"GB2-05":18.943456725578585,"GB2-06":23.333542932169717,"GB2-07":29.70774191519914,"GB2-08":1.0584933657452227},"none":{"GB2-02":1.2050251376353645,"GB2-03":14.413486563078298,"GB2-04":10.408078271985183,"GB2-05":32.925877665494745,"GB2-06":19.559254770161996,"GB2-07":55.53781781902651,"GB2-08":17.201788354759948}},"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":15.370166386617921,"none":17.572990428383044},"reasoning_agg":{"medium":{"max":29.70774191519914,"mean":15.370166386617921,"min":1.0584933657452227},"none":{"max":55.53781781902651,"mean":17.572990428383044,"min":1.2050251376353645}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.53781781902651,"reasoning_variance":2.2028240417651226},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":29.70774191519914,"expected_score":11.153134175820586,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.217032210797335},"none":{"ceiling_score":55.53781781902651,"expected_score":22.089197863849538,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.5162074354664945}}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:305083fd896b3511","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":30,"run_count":16,"total":0.0},"codegen_latency_ms":{"attempt_count":30,"max_ms":905283,"mean_ms":265606.6875,"min_ms":7507,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":905283,"mean_ms":509118.375,"min_ms":288605,"run_count":8},"none":{"attempt_count":15,"max_ms":59126,"mean_ms":22095.0,"min_ms":7507,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":52275,"output_mean":16877.75,"output_min":1148,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":52275,"output_mean":30105.875,"output_min":9014,"run_count":8},"none":{"attempt_count":15,"output_max":7281,"output_mean":3649.625,"output_min":1148,"run_count":8}},"display_name":"North Mini Code","economics":{"medium":21.760195242565842,"none":14.120274020673733},"first_seen_at":"2026-10-13T12:13:36Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[64000],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":15,"provider_post_attempts":15,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[64000],"total_output_tokens":270044,"total_visible_output_tokens":29197,"visible_token_observations":15},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":1011,"losses":2889,"wins":820},"match_totals_tracks":{"medium":{"draws":906,"losses":1954,"wins":710},"none":{"draws":105,"losses":935,"wins":110}},"model_slug":"cohere-north-mini-code","overall":{"max":42.57619175998257,"mean":15.649927497912557,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-03":{"draws":135,"losses":347,"wins":40},"GB2-04":{"draws":402,"losses":148,"wins":48},"GB2-05":{"draws":0,"losses":707,"wins":405},"GB2-06":{"draws":7,"losses":462,"wins":119},"GB2-07":{"draws":0,"losses":903,"wins":201},"GB2-08":{"draws":467,"losses":322,"wins":7}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":135,"losses":347,"wins":40},"GB2-04":{"draws":402,"losses":148,"wins":48},"GB2-05":{"draws":0,"losses":319,"wins":309},"GB2-06":{"draws":7,"losses":462,"wins":119},"GB2-07":{"draws":0,"losses":440,"wins":194},"GB2-08":{"draws":362,"losses":238,"wins":0}},"none":{"GB2-05":{"draws":0,"losses":388,"wins":96},"GB2-07":{"draws":0,"losses":463,"wins":7},"GB2-08":{"draws":105,"losses":84,"wins":7}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1164.7133965702178,"GB2-04":1409.2039920301818,"GB2-05":1427.014470771542,"GB2-06":989.04309255965,"GB2-07":1188.4002626011963,"GB2-08":1206.495054781262},"none":{"GB2-05":1048.4492481836437,"GB2-07":522.5484260808261,"GB2-08":1244.7799072170003}},"per_game_tracks":{"medium":{"GB2-03":4.96048726810271,"GB2-04":9.299487225219552,"GB2-05":42.57619175998257,"GB2-06":26.857963020917882,"GB2-07":32.64822986500804,"GB2-08":14.218812316164305},"none":{"GB2-05":25.683481802683964,"GB2-07":0.0,"GB2-08":16.67734025933723}},"provider_color":"#FF7759","provider_company":"Cohere","provider_key":"cohere","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":20.250143427742163,"none":11.04971156808295},"reasoning_agg":{"medium":{"max":42.57619175998257,"mean":20.250143427742163,"min":4.96048726810271},"none":{"max":25.683481802683964,"mean":11.04971156808295,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":42.57619175998257,"reasoning_variance":9.200431859659213},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":42.57619175998257,"expected_score":17.775002298265665,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.475141129476498},"none":{"ceiling_score":25.683481802683964,"expected_score":14.253786501101459,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.204074933018509}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:34309b55f784132e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.00217964,"mean":0.000272455,"median":0.0,"min":0.0,"recorded_attempt_count":53,"run_count":17,"total":0.00653892},"none":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0010891599999999998,"mean":0.00013614499999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":43,"run_count":17,"total":0.0032674799999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00653892,"mean":0.00653892,"median":0.00653892,"min":0.00653892,"recorded_attempt_count":1,"run_count":1,"total":0.00653892},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","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-variant-1":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0032674799999999997,"mean":0.0032674799999999997,"median":0.0032674799999999997,"min":0.0032674799999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":3,"run_count":1,"total":0.0032674799999999997},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"provider_reported":96},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":15,"max":0.00217964,"mean":0.00020429999999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":96,"run_count":34,"total":0.0098064},"codegen_latency_ms":{"attempt_count":96,"max_ms":410978,"mean_ms":155707.0,"min_ms":18717,"run_count":33},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":53,"max_ms":410978,"mean_ms":269539.1875,"min_ms":161500,"run_count":16},"none":{"attempt_count":43,"max_ms":90441,"mean_ms":48570.82352941176,"min_ms":18717,"run_count":17}},"codegen_output_tokens":{"attempt_count":96,"output_max":92074,"output_mean":32817.64705882353,"output_min":2036,"run_count":34},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":53,"output_max":92074,"output_mean":58883.76470588235,"output_min":20000,"run_count":17},"none":{"attempt_count":43,"output_max":17378,"output_mean":6751.529411764706,"output_min":2036,"run_count":17}},"display_name":"Ling 3.0 Flash","economics":{"medium":18.727134898683186,"none":14.966814186806156},"first_seen_at":"2026-10-13T14:22:46Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[32768],"finish_reason_observations":96,"finish_reasons":["length","stop","unknown"],"indexed_attempts":98,"output_token_observations":97,"provider_post_attempt_observations":4,"provider_post_attempts":5,"reasoning_token_observations":69,"reconciliation_get_attempt_observations":4,"requested_max_output_token_observations":4,"requested_max_output_tokens":[32768],"total_output_tokens":1115800,"total_reasoning_output_tokens":656294,"total_visible_output_tokens":120852,"visible_token_observations":59},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":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":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":"2026-10-13T14:25:09Z","match_totals_all":{"draws":3761,"losses":5588,"wins":1531},"match_totals_tracks":{"medium":{"draws":1279,"losses":2498,"wins":838},"none":{"draws":2482,"losses":3090,"wins":693}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":37.3796790234279,"mean":14.10036548486628,"min":2.226634589182131},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":472,"losses":1144,"wins":373},"GB2-02":{"draws":1008,"losses":269,"wins":11},"GB2-03":{"draws":378,"losses":624,"wins":126},"GB2-04":{"draws":1009,"losses":264,"wins":87},"GB2-06":{"draws":14,"losses":1684,"wins":288},"GB2-07":{"draws":0,"losses":1047,"wins":597},"GB2-08":{"draws":880,"losses":556,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":198,"losses":511,"wins":36},"GB2-02":{"draws":535,"losses":157,"wins":6},"GB2-04":{"draws":543,"losses":163,"wins":42},"GB2-06":{"draws":3,"losses":620,"wins":157},"GB2-07":{"draws":0,"losses":1047,"wins":597}},"none":{"GB2-01":{"draws":274,"losses":633,"wins":337},"GB2-02":{"draws":473,"losses":112,"wins":5},"GB2-03":{"draws":378,"losses":624,"wins":126},"GB2-04":{"draws":466,"losses":101,"wins":45},"GB2-06":{"draws":11,"losses":1064,"wins":131},"GB2-08":{"draws":880,"losses":556,"wins":49}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1136.0935064605237,"GB2-02":1380.5322424355452,"GB2-04":1402.0523129460369,"GB2-06":998.8951595844269,"GB2-07":1284.8968911952393},"none":{"GB2-01":1357.6407282118535,"GB2-02":1395.6653926719048,"GB2-03":1236.1554889096835,"GB2-04":1432.9773535943987,"GB2-06":691.9457099533657,"GB2-08":1238.5884814166502}},"per_game_tracks":{"medium":{"GB2-01":18.38893116159805,"GB2-02":2.226634589182131,"GB2-04":8.339936260536872,"GB2-06":27.30049345867099,"GB2-07":37.3796790234279},"none":{"GB2-01":33.015381565882485,"GB2-02":4.128047135513873,"GB2-03":10.375431483040334,"GB2-04":12.489192992815795,"GB2-06":13.513084788825406,"GB2-08":16.279747154759043}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":14.893142218594642,"none":13.307588751137915},"reasoning_agg":{"medium":{"max":37.3796790234279,"mean":14.893142218594642,"min":2.226634589182131},"none":{"max":33.015381565882485,"mean":13.307588751137915,"min":4.128047135513873}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":37.3796790234279,"reasoning_variance":1.5855534674567267},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":37.3796790234279,"expected_score":11.989861600109801,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9032806184848408},"none":{"ceiling_score":33.015381565882485,"expected_score":14.204114200367227,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.896525449229312}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:b9eef861e1de91ea","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507},"codegen_latency_ms":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8}},"codegen_output_tokens":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8}},"display_name":"GPT-4.1 Nano","economics":{"none":16.06135001609366},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[32768],"finish_reason_observations":13,"finish_reasons":["stop"],"indexed_attempts":13,"output_token_observations":13,"provider_post_attempt_observations":13,"provider_post_attempts":13,"reasoning_token_observations":13,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[32768],"total_output_tokens":20448,"total_visible_output_tokens":20448,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-10-12T23:41:16Z","match_totals_all":{"draws":615,"losses":627,"wins":80},"match_totals_tracks":{"none":{"draws":615,"losses":627,"wins":80}},"model_slug":"gpt-4-1-nano","overall":{"max":26.37106409679643,"mean":12.568685622674016,"min":6.073639377510463},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":339,"losses":84,"wins":3},"GB2-03":{"draws":270,"losses":164,"wins":6},"GB2-06":{"draws":6,"losses":379,"wins":71}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":339,"losses":84,"wins":3},"GB2-03":{"draws":270,"losses":164,"wins":6},"GB2-06":{"draws":6,"losses":379,"wins":71}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1411.1501646397937,"GB2-03":1306.9243282580971,"GB2-06":978.2032487308453}},"per_game_tracks":{"none":{"GB2-02":6.073639377510463,"GB2-03":15.739346573974078,"GB2-06":26.37106409679643}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":12.568685622674016},"reasoning_agg":{"none":{"max":26.37106409679643,"mean":12.568685622674016,"min":6.073639377510463}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":26.37106409679643},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":26.37106409679643,"expected_score":15.113900312633154,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.5452146899591384}}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:cad88ef1dc140c69","codegen_cost_by_reasoning":{"highest":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538000000001},"medium":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.018105180000000002},"none":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.01810518},"historical-provider-setting-baseline":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998},"historical-provider-setting-intensive":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":24,"cost_basis_counts":{"provider_reported":56},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":23,"max":0.01113168,"mean":0.00448752,"median":0.002935335,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":37},"recorded_attempt_count":56,"run_count":24,"total":0.10770048000000002},"codegen_latency_ms":{"attempt_count":56,"max_ms":643052,"mean_ms":207186.875,"min_ms":45308,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":643052,"mean_ms":466285.75,"min_ms":257629,"run_count":8},"medium":{"attempt_count":19,"max_ms":129121,"mean_ms":76432.5,"min_ms":45308,"run_count":8},"none":{"attempt_count":19,"max_ms":136274,"mean_ms":78842.375,"min_ms":49515,"run_count":8}},"codegen_output_tokens":{"attempt_count":56,"output_max":39360,"output_mean":13818.666666666666,"output_min":3954,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":39360,"output_mean":29587.25,"output_min":21705,"run_count":8},"medium":{"attempt_count":19,"output_max":7321,"output_mean":5310.0,"output_min":3954,"run_count":8},"none":{"attempt_count":19,"output_max":9484,"output_mean":6558.75,"output_min":4755,"run_count":8}},"display_name":"Granite 4.2 8B","economics":{"medium":6.679463751037211},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":37,"effective_max_output_tokens":[117964],"finish_reason_observations":56,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":56,"provider_post_attempt_observations":56,"provider_post_attempts":56,"reasoning_token_observations":56,"reconciliation_get_attempt_observations":56,"reconciliation_get_attempts":88,"requested_max_output_token_observations":37,"requested_max_output_tokens":[117964],"total_output_tokens":331648,"total_reasoning_output_tokens":194609,"total_visible_output_tokens":137039,"visible_token_observations":56},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"ibm","provider_model":"ibm-granite/granite-4.2-8b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"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":"2026-10-12T23:18:50Z","match_totals_all":{"draws":285,"losses":136,"wins":25},"match_totals_tracks":{"medium":{"draws":285,"losses":136,"wins":25}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":6.679463751037211,"mean":3.9716329085681075,"min":3.9716329085681075},"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":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-04":{"draws":285,"losses":136,"wins":25}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":285,"losses":136,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1389.6765591267351}},"per_game_tracks":{"medium":{"GB2-04":6.679463751037211}},"provider_color":"#0F62FE","provider_company":"IBM","provider_key":"ibm","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":3.9716329085681075},"reasoning_agg":{"medium":{"max":6.679463751037211,"mean":3.9716329085681075,"min":6.679463751037211}},"reasoning_labels":{"highest":"Setting not tested","medium":"Low","none":"Setting not tested"},"reasoning_settings":{"balanced":"low"},"score_diagnostics":{"ceiling_score":6.679463751037211},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":6.679463751037211,"expected_score":6.955704521138169,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.9840716125700615}}}],"public_release_id":"gb2-20261013-0ba6ea7997f6","rating_method":{"bootstrap_iterations":0,"first_player_advantage":false,"method":"glicko2_style"},"results_cut_id":"gb2-20261013-0ba6ea7997f6","schema_version":2,"snapshot_id":"20261013_143125","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-13 14:31 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":51,"wins":51},"claude-fable-5":{"draws":35,"losses":131,"wins":30},"claude-fable-5-1":{"draws":8,"losses":196,"wins":6},"claude-haiku-5-5":{"draws":25,"losses":73,"wins":22},"claude-opus-4-5":{"draws":95,"losses":135,"wins":64},"claude-opus-4-8":{"draws":32,"losses":70,"wins":22},"claude-opus-5":{"draws":30,"losses":182,"wins":24},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":77,"losses":118,"wins":45},"claude-sonnet-5-5":{"draws":28,"losses":79,"wins":25},"cohere/north-mini-code":{"draws":11,"losses":14,"wins":23},"deepseek/deepseek-v4-flash":{"draws":102,"losses":101,"wins":97},"deepseek/deepseek-v4-pro":{"draws":63,"losses":107,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":68,"losses":93,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":60,"wins":32},"fireworks/ember-1":{"draws":40,"losses":68,"wins":24},"gemini-3.1-pro-preview":{"draws":36,"losses":57,"wins":39},"google/gemini-3.1-flash-lite":{"draws":30,"losses":20,"wins":48},"google/gemini-3.5-flash":{"draws":75,"losses":120,"wins":61},"google/gemini-3.5-flash-lite":{"draws":157,"losses":138,"wins":145},"google/gemini-3.6-flash":{"draws":108,"losses":192,"wins":86},"google/gemini-3.8-flash":{"draws":57,"losses":111,"wins":38},"google/gemma-4-31b-it":{"draws":23,"losses":24,"wins":21},"gpt-4.1":{"draws":18,"losses":17,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":40,"losses":44,"wins":38},"gpt-5.4":{"draws":54,"losses":91,"wins":47},"gpt-5.4-mini":{"draws":35,"losses":25,"wins":32},"gpt-5.4-nano":{"draws":31,"losses":49,"wins":58},"gpt-5.5":{"draws":54,"losses":56,"wins":24},"gpt-5.6-luna":{"draws":77,"losses":71,"wins":86},"gpt-5.6-sol":{"draws":33,"losses":147,"wins":28},"gpt-5.6-terra":{"draws":68,"losses":107,"wins":43},"gpt-6-astra":{"draws":10,"losses":153,"wins":15},"gpt-6-luna":{"draws":39,"losses":54,"wins":35},"gpt-6-sol":{"draws":15,"losses":102,"wins":15},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":72,"losses":47,"wins":57},"inclusionai/ling-3.0-flash":{"draws":52,"losses":22,"wins":52},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":63,"losses":54,"wins":81},"meta/muse-glimmer-30b":{"draws":92,"losses":64,"wins":68},"meta/muse-spark-1.2":{"draws":52,"losses":81,"wins":51},"meta/muse-spark-1.3":{"draws":46,"losses":104,"wins":31},"meta/muse-wonder":{"draws":29,"losses":83,"wins":16},"minimax/minimax-m3":{"draws":20,"losses":17,"wins":41},"mistralai/mistral-large-4-0":{"draws":22,"losses":32,"wins":22},"mistralai/mistral-medium-3-5":{"draws":58,"losses":35,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":16,"wins":9},"moonshotai/kimi-k3":{"draws":56,"losses":95,"wins":47},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":39},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":37,"wins":42},"o3":{"draws":52,"losses":135,"wins":83},"openai/gpt-oss-120b":{"draws":75,"losses":59,"wins":76},"poolside/laguna-s-2.1":{"draws":81,"losses":52,"wins":61},"qwen/qwen3.7-max":{"draws":28,"losses":30,"wins":26},"qwen/qwen3.7-plus":{"draws":22,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":73,"losses":100,"wins":49},"qwen/qwen3.8-27b":{"draws":25,"losses":60,"wins":29},"qwen/qwen3.8-flash":{"draws":57,"losses":65,"wins":36},"qwen/qwen3.8-max":{"draws":84,"losses":87,"wins":67},"qwen/qwen3.8-max-0902":{"draws":35,"losses":73,"wins":18},"stealth/ox-alpha":{"draws":176,"losses":400,"wins":154},"stealth/space-bunny-alpha":{"draws":35,"losses":38,"wins":31},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":42},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":27,"losses":23,"wins":24},"tencent/hy4-preview":{"draws":78,"losses":122,"wins":30},"thinkingmachines/inkling":{"draws":69,"losses":51,"wins":82},"thinkingmachines/inkling-small":{"draws":96,"losses":56,"wins":100},"unbiased/pareto-26.10-preview":{"draws":0,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":15,"wins":14},"x-ai/grok-4.5":{"draws":49,"losses":120,"wins":29},"x-ai/grok-4.6":{"draws":62,"losses":121,"wins":31},"x-ai/grok-4.7":{"draws":6,"losses":91,"wins":17},"x-ai/grok-build-0.1":{"draws":18,"losses":10,"wins":22},"xiaomi/mimo-v2.5":{"draws":82,"losses":52,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":27,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":49,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":55,"wins":18},"z-ai/glm-5.2":{"draws":143,"losses":128,"wins":103},"z-ai/glm-5.3":{"draws":41,"losses":108,"wins":29},"z-ai/glm-5.3-flash":{"draws":66,"losses":111,"wins":37},"z-ai/glm-5.3-flashx":{"draws":24,"losses":83,"wins":25}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":30,"wins":131},"claude-fable-5":{"draws":24,"losses":76,"wins":76},"claude-fable-5-1":{"draws":15,"losses":242,"wins":45},"claude-haiku-5-5":{"draws":22,"losses":41,"wins":71},"claude-opus-4-5":{"draws":57,"losses":46,"wins":219},"claude-opus-4-8":{"draws":28,"losses":38,"wins":74},"claude-opus-5":{"draws":41,"losses":178,"wins":75},"claude-opus-5-5":{"draws":13,"losses":122,"wins":21},"claude-sonnet-5":{"draws":55,"losses":42,"wins":159},"claude-sonnet-5-5":{"draws":24,"losses":58,"wins":62},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":59,"losses":21,"wins":220},"deepseek/deepseek-v4-pro":{"draws":50,"losses":54,"wins":124},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":44,"wins":135},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":36,"wins":74},"fireworks/ember-1":{"draws":31,"losses":22,"wins":91},"gemini-3.1-pro-preview":{"draws":27,"losses":30,"wins":87},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":83},"google/gemini-3.5-flash":{"draws":59,"losses":54,"wins":171},"google/gemini-3.5-flash-lite":{"draws":84,"losses":55,"wins":257},"google/gemini-3.6-flash":{"draws":73,"losses":124,"wins":213},"google/gemini-3.8-flash":{"draws":41,"losses":97,"wins":126},"google/gemma-4-31b-it":{"draws":16,"losses":8,"wins":50},"gpt-4.1":{"draws":7,"losses":12,"wins":29},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":28,"losses":27,"wins":81},"gpt-5.4":{"draws":65,"losses":83,"wins":112},"gpt-5.4-mini":{"draws":22,"losses":11,"wins":63},"gpt-5.4-nano":{"draws":19,"losses":15,"wins":112},"gpt-5.5":{"draws":31,"losses":41,"wins":66},"gpt-5.6-luna":{"draws":61,"losses":34,"wins":133},"gpt-5.6-sol":{"draws":35,"losses":111,"wins":124},"gpt-5.6-terra":{"draws":68,"losses":40,"wins":150},"gpt-6-astra":{"draws":19,"losses":204,"wins":53},"gpt-6-luna":{"draws":31,"losses":28,"wins":79},"gpt-6-sol":{"draws":19,"losses":82,"wins":43},"gpt-6.1-sol":{"draws":11,"losses":101,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":45,"losses":7,"wins":88},"inclusionai/ling-3.0-flash":{"draws":22,"losses":5,"wins":85},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":34,"losses":30,"wins":128},"meta/muse-glimmer-30b":{"draws":48,"losses":14,"wins":120},"meta/muse-spark-1.2":{"draws":34,"losses":48,"wins":118},"meta/muse-spark-1.3":{"draws":39,"losses":58,"wins":107},"meta/muse-wonder":{"draws":25,"losses":55,"wins":56},"minimax/minimax-m3":{"draws":20,"losses":6,"wins":54},"mistralai/mistral-large-4-0":{"draws":14,"losses":23,"wins":45},"mistralai/mistral-medium-3-5":{"draws":37,"losses":11,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":40,"losses":36,"wins":134},"nex-agi/nex-n2-pro":{"draws":15,"losses":1,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":12,"wins":89},"o3":{"draws":27,"losses":44,"wins":205},"openai/gpt-oss-120b":{"draws":50,"losses":20,"wins":114},"poolside/laguna-s-2.1":{"draws":43,"losses":29,"wins":108},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":58},"qwen/qwen3.7-plus":{"draws":13,"losses":8,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":68,"losses":64,"wins":123},"qwen/qwen3.8-27b":{"draws":23,"losses":26,"wins":83},"qwen/qwen3.8-flash":{"draws":45,"losses":28,"wins":85},"qwen/qwen3.8-max":{"draws":41,"losses":70,"wins":131},"qwen/qwen3.8-max-0902":{"draws":28,"losses":34,"wins":80},"stealth/ox-alpha":{"draws":172,"losses":185,"wins":469},"stealth/space-bunny-alpha":{"draws":31,"losses":15,"wins":68},"stepfun/step-3.7-flash":{"draws":15,"losses":8,"wins":79},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":47},"tencent/hy4-preview":{"draws":42,"losses":57,"wins":141},"thinkingmachines/inkling":{"draws":45,"losses":6,"wins":141},"thinkingmachines/inkling-small":{"draws":51,"losses":26,"wins":141},"unbiased/pareto-26.10-preview":{"draws":5,"losses":33,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":28},"x-ai/grok-4.5":{"draws":31,"losses":77,"wins":114},"x-ai/grok-4.6":{"draws":64,"losses":90,"wins":116},"x-ai/grok-4.7":{"draws":7,"losses":76,"wins":43},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":31},"xiaomi/mimo-v2.5":{"draws":45,"losses":5,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":71},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":39,"wins":45},"z-ai/glm-5.2":{"draws":88,"losses":61,"wins":221},"z-ai/glm-5.3":{"draws":35,"losses":94,"wins":87},"z-ai/glm-5.3-flash":{"draws":44,"losses":80,"wins":124},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":73}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":6,"wins":196},"claude-fable-5":{"draws":15,"losses":45,"wins":242},"claude-fable-5-1":{"draws":20,"losses":122,"wins":122},"claude-haiku-5-5":{"draws":8,"losses":8,"wins":134},"claude-opus-4-5":{"draws":15,"losses":11,"wins":332},"claude-opus-4-8":{"draws":8,"losses":11,"wins":127},"claude-opus-5":{"draws":32,"losses":86,"wins":174},"claude-opus-5-5":{"draws":16,"losses":95,"wins":63},"claude-sonnet-5":{"draws":15,"losses":9,"wins":265},"claude-sonnet-5-5":{"draws":9,"losses":34,"wins":119},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":13,"losses":2,"wins":299},"deepseek/deepseek-v4-pro":{"draws":16,"losses":6,"wins":224},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":6,"wins":237},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":133},"fireworks/ember-1":{"draws":4,"losses":8,"wins":150},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":150},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":104},"google/gemini-3.5-flash":{"draws":23,"losses":14,"wins":279},"google/gemini-3.5-flash-lite":{"draws":28,"losses":3,"wins":375},"google/gemini-3.6-flash":{"draws":34,"losses":32,"wins":382},"google/gemini-3.8-flash":{"draws":22,"losses":27,"wins":257},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":79},"gpt-4.1":{"draws":1,"losses":2,"wins":51},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":7,"losses":1,"wins":134},"gpt-5.4":{"draws":19,"losses":33,"wins":230},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":104},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":155},"gpt-5.5":{"draws":5,"losses":18,"wins":131},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":206},"gpt-5.6-sol":{"draws":25,"losses":44,"wins":249},"gpt-5.6-terra":{"draws":22,"losses":6,"wins":244},"gpt-6-astra":{"draws":27,"losses":186,"wins":111},"gpt-6-luna":{"draws":10,"losses":6,"wins":142},"gpt-6-sol":{"draws":14,"losses":38,"wins":110},"gpt-6.1-sol":{"draws":13,"losses":77,"wins":72},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":129},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":113},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":188},"meta/muse-glimmer-30b":{"draws":13,"losses":1,"wins":161},"meta/muse-spark-1.2":{"draws":13,"losses":11,"wins":200},"meta/muse-spark-1.3":{"draws":13,"losses":18,"wins":199},"meta/muse-wonder":{"draws":13,"losses":31,"wins":112},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":84},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":97},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":36},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":207},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":78},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":129},"o3":{"draws":5,"losses":14,"wins":275},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":170},"poolside/laguna-s-2.1":{"draws":10,"losses":2,"wins":178},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":90},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":72},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":13,"wins":250},"qwen/qwen3.8-27b":{"draws":7,"losses":2,"wins":139},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":157},"qwen/qwen3.8-max":{"draws":14,"losses":8,"wins":246},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":139},"stealth/ox-alpha":{"draws":78,"losses":49,"wins":849},"stealth/space-bunny-alpha":{"draws":6,"losses":3,"wins":121},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":109},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":74},"tencent/hy4-preview":{"draws":12,"losses":25,"wins":229},"thinkingmachines/inkling":{"draws":13,"losses":0,"wins":195},"thinkingmachines/inkling-small":{"draws":14,"losses":1,"wins":221},"unbiased/pareto-26.10-preview":{"draws":3,"losses":27,"wins":20},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":37},"x-ai/grok-4.5":{"draws":8,"losses":19,"wins":213},"x-ai/grok-4.6":{"draws":18,"losses":44,"wins":246},"x-ai/grok-4.7":{"draws":6,"losses":39,"wins":95},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":53},"xiaomi/mimo-v2.5":{"draws":12,"losses":3,"wins":229},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":90},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":85},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":10,"wins":80},"z-ai/glm-5.2":{"draws":29,"losses":10,"wins":359},"z-ai/glm-5.3":{"draws":16,"losses":38,"wins":192},"z-ai/glm-5.3-flash":{"draws":24,"losses":30,"wins":238},"z-ai/glm-5.3-flashx":{"draws":15,"losses":13,"wins":134}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":22,"wins":73},"claude-fable-5":{"draws":22,"losses":71,"wins":41},"claude-fable-5-1":{"draws":8,"losses":134,"wins":8},"claude-haiku-5-5":{"draws":14,"losses":33,"wins":33},"claude-opus-4-5":{"draws":61,"losses":53,"wins":98},"claude-opus-4-8":{"draws":28,"losses":55,"wins":41},"claude-opus-5":{"draws":35,"losses":151,"wins":38},"claude-opus-5-5":{"draws":16,"losses":114,"wins":6},"claude-sonnet-5":{"draws":34,"losses":37,"wins":61},"claude-sonnet-5-5":{"draws":25,"losses":62,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":31},"deepseek/deepseek-v4-flash":{"draws":55,"losses":30,"wins":111},"deepseek/deepseek-v4-pro":{"draws":33,"losses":39,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":28,"wins":62},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":39,"wins":52},"fireworks/ember-1":{"draws":33,"losses":35,"wins":62},"gemini-3.1-pro-preview":{"draws":28,"losses":43,"wins":57},"google/gemini-3.1-flash-lite":{"draws":20,"losses":7,"wins":61},"google/gemini-3.5-flash":{"draws":35,"losses":58,"wins":71},"google/gemini-3.5-flash-lite":{"draws":43,"losses":40,"wins":145},"google/gemini-3.6-flash":{"draws":54,"losses":92,"wins":86},"google/gemini-3.8-flash":{"draws":32,"losses":59,"wins":39},"google/gemma-4-31b-it":{"draws":21,"losses":9,"wins":50},"gpt-4.1":{"draws":13,"losses":8,"wins":21},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":27,"losses":27,"wins":56},"gpt-5.4":{"draws":26,"losses":49,"wins":47},"gpt-5.4-mini":{"draws":26,"losses":11,"wins":49},"gpt-5.4-nano":{"draws":27,"losses":37,"wins":70},"gpt-5.5":{"draws":43,"losses":34,"wins":43},"gpt-5.6-luna":{"draws":37,"losses":24,"wins":69},"gpt-5.6-sol":{"draws":21,"losses":71,"wins":38},"gpt-5.6-terra":{"draws":36,"losses":36,"wins":54},"gpt-6-astra":{"draws":10,"losses":113,"wins":7},"gpt-6-luna":{"draws":35,"losses":39,"wins":60},"gpt-6-sol":{"draws":27,"losses":77,"wins":24},"gpt-6.1-sol":{"draws":15,"losses":105,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":4,"wins":64},"inclusionai/ling-3.0-flash":{"draws":26,"losses":5,"wins":57},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":25,"losses":18,"wins":89},"meta/muse-glimmer-30b":{"draws":33,"losses":15,"wins":62},"meta/muse-spark-1.2":{"draws":26,"losses":39,"wins":65},"meta/muse-spark-1.3":{"draws":22,"losses":51,"wins":59},"meta/muse-wonder":{"draws":28,"losses":75,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":49},"mistralai/mistral-large-4-0":{"draws":30,"losses":28,"wins":28},"mistralai/mistral-medium-3-5":{"draws":20,"losses":4,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":36,"wins":56},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":26,"wins":60},"o3":{"draws":27,"losses":60,"wins":97},"openai/gpt-oss-120b":{"draws":26,"losses":12,"wins":74},"poolside/laguna-s-2.1":{"draws":30,"losses":35,"wins":55},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":33},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":43,"wins":55},"qwen/qwen3.8-27b":{"draws":21,"losses":28,"wins":45},"qwen/qwen3.8-flash":{"draws":24,"losses":19,"wins":45},"qwen/qwen3.8-max":{"draws":32,"losses":35,"wins":63},"qwen/qwen3.8-max-0902":{"draws":39,"losses":47,"wins":48},"stealth/ox-alpha":{"draws":94,"losses":153,"wins":165},"stealth/space-bunny-alpha":{"draws":30,"losses":23,"wins":49},"stepfun/step-3.7-flash":{"draws":14,"losses":16,"wins":66},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":29},"tencent/hy4-preview":{"draws":28,"losses":52,"wins":46},"thinkingmachines/inkling":{"draws":36,"losses":17,"wins":93},"thinkingmachines/inkling-small":{"draws":27,"losses":13,"wins":86},"unbiased/pareto-26.10-preview":{"draws":2,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":30,"losses":51,"wins":45},"x-ai/grok-4.6":{"draws":36,"losses":57,"wins":37},"x-ai/grok-4.7":{"draws":12,"losses":83,"wins":19},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":27},"xiaomi/mimo-v2.5":{"draws":52,"losses":31,"wins":121},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":18,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":27,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":39,"wins":32},"z-ai/glm-5.2":{"draws":58,"losses":61,"wins":139},"z-ai/glm-5.3":{"draws":23,"losses":74,"wins":29},"z-ai/glm-5.3-flash":{"draws":22,"losses":57,"wins":53},"z-ai/glm-5.3-flashx":{"draws":24,"losses":51,"wins":55}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":43,"wins":107},"claude-fable-5":{"draws":40,"losses":154,"wins":36},"claude-fable-5-1":{"draws":13,"losses":237,"wins":8},"claude-haiku-5-5":{"draws":38,"losses":50,"wins":40},"claude-opus-4-5":{"draws":110,"losses":93,"wins":121},"claude-opus-4-8":{"draws":56,"losses":103,"wins":63},"claude-opus-5":{"draws":69,"losses":343,"wins":46},"claude-opus-5-5":{"draws":12,"losses":136,"wins":8},"claude-sonnet-5":{"draws":109,"losses":76,"wins":137},"claude-sonnet-5-5":{"draws":30,"losses":75,"wins":39},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":51},"deepseek/deepseek-v4-flash":{"draws":82,"losses":67,"wins":157},"deepseek/deepseek-v4-pro":{"draws":52,"losses":75,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":77,"wins":72},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":62,"wins":44},"fireworks/ember-1":{"draws":50,"losses":56,"wins":38},"gemini-3.1-pro-preview":{"draws":36,"losses":46,"wins":62},"google/gemini-3.1-flash-lite":{"draws":34,"losses":8,"wins":98},"google/gemini-3.5-flash":{"draws":68,"losses":110,"wins":88},"google/gemini-3.5-flash-lite":{"draws":217,"losses":137,"wins":302},"google/gemini-3.6-flash":{"draws":167,"losses":271,"wins":198},"google/gemini-3.8-flash":{"draws":67,"losses":125,"wins":46},"google/gemma-4-31b-it":{"draws":26,"losses":10,"wins":38},"gpt-4.1":{"draws":34,"losses":21,"wins":19},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":58,"losses":51,"wins":63},"gpt-5.4":{"draws":83,"losses":153,"wins":64},"gpt-5.4-mini":{"draws":62,"losses":33,"wins":55},"gpt-5.4-nano":{"draws":61,"losses":56,"wins":109},"gpt-5.5":{"draws":95,"losses":84,"wins":39},"gpt-5.6-luna":{"draws":111,"losses":78,"wins":127},"gpt-5.6-sol":{"draws":51,"losses":211,"wins":66},"gpt-5.6-terra":{"draws":78,"losses":57,"wins":75},"gpt-6-astra":{"draws":17,"losses":200,"wins":15},"gpt-6-luna":{"draws":44,"losses":47,"wins":49},"gpt-6-sol":{"draws":24,"losses":103,"wins":17},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":61,"losses":10,"wins":85},"inclusionai/ling-3.0-flash":{"draws":61,"losses":25,"wins":86},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":83,"losses":54,"wins":169},"meta/muse-glimmer-30b":{"draws":65,"losses":27,"wins":96},"meta/muse-spark-1.2":{"draws":60,"losses":112,"wins":70},"meta/muse-spark-1.3":{"draws":39,"losses":104,"wins":51},"meta/muse-wonder":{"draws":27,"losses":84,"wins":25},"minimax/minimax-m3":{"draws":34,"losses":15,"wins":67},"mistralai/mistral-large-4-0":{"draws":28,"losses":27,"wins":29},"mistralai/mistral-medium-3-5":{"draws":34,"losses":11,"wins":79},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":15,"wins":30},"moonshotai/kimi-k3":{"draws":106,"losses":107,"wins":89},"nex-agi/nex-n2-pro":{"draws":27,"losses":14,"wins":67},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":63,"losses":26,"wins":91},"o3":{"draws":59,"losses":119,"wins":262},"openai/gpt-oss-120b":{"draws":55,"losses":28,"wins":105},"poolside/laguna-s-2.1":{"draws":111,"losses":32,"wins":139},"qwen/qwen3.7-max":{"draws":34,"losses":34,"wins":64},"qwen/qwen3.7-plus":{"draws":32,"losses":24,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":81,"losses":85,"wins":58},"qwen/qwen3.8-27b":{"draws":34,"losses":48,"wins":42},"qwen/qwen3.8-flash":{"draws":49,"losses":46,"wins":51},"qwen/qwen3.8-max":{"draws":65,"losses":102,"wins":64},"qwen/qwen3.8-max-0902":{"draws":35,"losses":57,"wins":50},"stealth/ox-alpha":{"draws":218,"losses":302,"wins":229},"stealth/space-bunny-alpha":{"draws":36,"losses":27,"wins":51},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":71},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":43,"losses":28,"wins":51},"tencent/hy4-preview":{"draws":55,"losses":99,"wins":66},"thinkingmachines/inkling":{"draws":81,"losses":45,"wins":152},"thinkingmachines/inkling-small":{"draws":76,"losses":31,"wins":122},"unbiased/pareto-26.10-preview":{"draws":1,"losses":44,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":110,"losses":149,"wins":99},"x-ai/grok-4.6":{"draws":61,"losses":118,"wins":49},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":27,"losses":8,"wins":41},"xiaomi/mimo-v2.5":{"draws":114,"losses":51,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":50,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":49,"wins":21},"z-ai/glm-5.2":{"draws":127,"losses":114,"wins":183},"z-ai/glm-5.3":{"draws":51,"losses":104,"wins":35},"z-ai/glm-5.3-flash":{"draws":54,"losses":112,"wins":60},"z-ai/glm-5.3-flashx":{"draws":37,"losses":74,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":22,"wins":70},"claude-fable-5":{"draws":28,"losses":74,"wins":38},"claude-fable-5-1":{"draws":8,"losses":127,"wins":11},"claude-haiku-5-5":{"draws":28,"losses":41,"wins":55},"claude-opus-4-5":{"draws":96,"losses":92,"wins":186},"claude-opus-4-8":{"draws":32,"losses":64,"wins":64},"claude-opus-5":{"draws":79,"losses":273,"wins":82},"claude-opus-5-5":{"draws":13,"losses":114,"wins":17},"claude-sonnet-5":{"draws":38,"losses":38,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":62,"wins":42},"cohere/north-mini-code":{"draws":15,"losses":7,"wins":46},"deepseek/deepseek-v4-flash":{"draws":64,"losses":26,"wins":146},"deepseek/deepseek-v4-pro":{"draws":31,"losses":41,"wins":58},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":42,"wins":60},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":53,"wins":47},"fireworks/ember-1":{"draws":44,"losses":37,"wins":51},"gemini-3.1-pro-preview":{"draws":36,"losses":35,"wins":61},"google/gemini-3.1-flash-lite":{"draws":39,"losses":10,"wins":121},"google/gemini-3.5-flash":{"draws":55,"losses":52,"wins":93},"google/gemini-3.5-flash-lite":{"draws":83,"losses":34,"wins":175},"google/gemini-3.6-flash":{"draws":78,"losses":129,"wins":111},"google/gemini-3.8-flash":{"draws":30,"losses":63,"wins":51},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":43},"gpt-4.1":{"draws":29,"losses":9,"wins":42},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":49,"losses":52,"wins":101},"gpt-5.4":{"draws":29,"losses":56,"wins":51},"gpt-5.4-mini":{"draws":46,"losses":43,"wins":75},"gpt-5.4-nano":{"draws":52,"losses":59,"wins":147},"gpt-5.5":{"draws":71,"losses":99,"wins":68},"gpt-5.6-luna":{"draws":42,"losses":30,"wins":62},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":55},"gpt-5.6-terra":{"draws":36,"losses":37,"wins":61},"gpt-6-astra":{"draws":11,"losses":120,"wins":11},"gpt-6-luna":{"draws":33,"losses":36,"wins":59},"gpt-6-sol":{"draws":20,"losses":80,"wins":32},"gpt-6.1-sol":{"draws":7,"losses":110,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":11,"wins":57},"inclusionai/ling-3.0-flash":{"draws":57,"losses":0,"wins":81},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":42,"losses":31,"wins":112},"meta/muse-glimmer-30b":{"draws":34,"losses":17,"wins":69},"meta/muse-spark-1.2":{"draws":31,"losses":43,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":56,"wins":52},"meta/muse-wonder":{"draws":26,"losses":58,"wins":38},"minimax/minimax-m3":{"draws":33,"losses":18,"wins":79},"mistralai/mistral-large-4-0":{"draws":16,"losses":33,"wins":25},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":14,"wins":32},"moonshotai/kimi-k3":{"draws":41,"losses":53,"wins":50},"nex-agi/nex-n2-pro":{"draws":41,"losses":10,"wins":73},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":32,"wins":127},"o3":{"draws":36,"losses":68,"wins":148},"openai/gpt-oss-120b":{"draws":38,"losses":10,"wins":68},"poolside/laguna-s-2.1":{"draws":58,"losses":24,"wins":102},"qwen/qwen3.7-max":{"draws":48,"losses":40,"wins":63},"qwen/qwen3.7-plus":{"draws":31,"losses":24,"wins":77},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":54,"wins":46},"qwen/qwen3.8-27b":{"draws":21,"losses":31,"wins":42},"qwen/qwen3.8-flash":{"draws":34,"losses":20,"wins":42},"qwen/qwen3.8-max":{"draws":30,"losses":49,"wins":65},"qwen/qwen3.8-max-0902":{"draws":34,"losses":46,"wins":46},"stealth/ox-alpha":{"draws":100,"losses":167,"wins":157},"stealth/space-bunny-alpha":{"draws":30,"losses":24,"wins":52},"stepfun/step-3.7-flash":{"draws":16,"losses":22,"wins":72},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":41,"losses":28,"wins":63},"tencent/hy4-preview":{"draws":34,"losses":61,"wins":51},"thinkingmachines/inkling":{"draws":50,"losses":25,"wins":131},"thinkingmachines/inkling-small":{"draws":42,"losses":12,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":39,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":58,"losses":81,"wins":71},"x-ai/grok-4.6":{"draws":37,"losses":60,"wins":47},"x-ai/grok-4.7":{"draws":16,"losses":73,"wins":29},"x-ai/grok-build-0.1":{"draws":24,"losses":14,"wins":50},"xiaomi/mimo-v2.5":{"draws":123,"losses":39,"wins":224},"xiaomi/mimo-v2.5-pro":{"draws":33,"losses":33,"wins":72},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":38,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":39,"wins":34},"z-ai/glm-5.2":{"draws":121,"losses":85,"wins":194},"z-ai/glm-5.3":{"draws":24,"losses":72,"wins":34},"z-ai/glm-5.3-flash":{"draws":22,"losses":62,"wins":58},"z-ai/glm-5.3-flashx":{"draws":25,"losses":49,"wins":58}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":24,"wins":182},"claude-fable-5":{"draws":41,"losses":75,"wins":178},"claude-fable-5-1":{"draws":32,"losses":174,"wins":86},"claude-haiku-5-5":{"draws":35,"losses":38,"wins":151},"claude-opus-4-5":{"draws":121,"losses":83,"wins":534},"claude-opus-4-8":{"draws":79,"losses":82,"wins":273},"claude-opus-5":{"draws":122,"losses":435,"wins":435},"claude-opus-5-5":{"draws":25,"losses":167,"wins":78},"claude-sonnet-5":{"draws":35,"losses":43,"wins":190},"claude-sonnet-5-5":{"draws":25,"losses":81,"wins":140},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":85},"deepseek/deepseek-v4-flash":{"draws":48,"losses":25,"wins":353},"deepseek/deepseek-v4-pro":{"draws":30,"losses":33,"wins":185},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":28,"wins":188},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":36,"wins":170},"fireworks/ember-1":{"draws":27,"losses":43,"wins":176},"gemini-3.1-pro-preview":{"draws":24,"losses":37,"wins":185},"google/gemini-3.1-flash-lite":{"draws":28,"losses":9,"wins":175},"google/gemini-3.5-flash":{"draws":43,"losses":33,"wins":269},"google/gemini-3.5-flash-lite":{"draws":74,"losses":43,"wins":449},"google/gemini-3.6-flash":{"draws":78,"losses":117,"wins":427},"google/gemini-3.8-flash":{"draws":34,"losses":61,"wins":203},"google/gemma-4-31b-it":{"draws":21,"losses":10,"wins":97},"gpt-4.1":{"draws":20,"losses":11,"wins":126},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":18},"gpt-5":{"draws":44,"losses":29,"wins":281},"gpt-5.4":{"draws":29,"losses":36,"wins":189},"gpt-5.4-mini":{"draws":52,"losses":20,"wins":182},"gpt-5.4-nano":{"draws":43,"losses":37,"wins":306},"gpt-5.5":{"draws":61,"losses":104,"wins":301},"gpt-5.6-luna":{"draws":26,"losses":26,"wins":204},"gpt-5.6-sol":{"draws":37,"losses":63,"wins":196},"gpt-5.6-terra":{"draws":30,"losses":21,"wins":197},"gpt-6-astra":{"draws":30,"losses":169,"wins":65},"gpt-6-luna":{"draws":47,"losses":20,"wins":171},"gpt-6-sol":{"draws":33,"losses":93,"wins":120},"gpt-6.1-sol":{"draws":30,"losses":140,"wins":76},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":129},"inclusionai/ling-3.0-flash":{"draws":46,"losses":11,"wins":157},"meituan/longcat-2.0":{"draws":44,"losses":36,"wins":286},"meta/muse-glimmer-30b":{"draws":14,"losses":23,"wins":195},"meta/muse-spark-1.2":{"draws":32,"losses":34,"wins":186},"meta/muse-spark-1.3":{"draws":39,"losses":54,"wins":165},"meta/muse-wonder":{"draws":28,"losses":73,"wins":127},"minimax/minimax-m3":{"draws":25,"losses":14,"wins":169},"mistralai/mistral-large-4-0":{"draws":24,"losses":18,"wins":100},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":112},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":7,"wins":112},"moonshotai/kimi-k3":{"draws":49,"losses":53,"wins":202},"nex-agi/nex-n2-pro":{"draws":3,"losses":10,"wins":147},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":8,"wins":269},"o3":{"draws":28,"losses":26,"wins":358},"openai/gpt-oss-120b":{"draws":32,"losses":11,"wins":183},"poolside/laguna-s-2.1":{"draws":34,"losses":27,"wins":325},"qwen/qwen3.7-max":{"draws":30,"losses":24,"wins":192},"qwen/qwen3.7-plus":{"draws":24,"losses":15,"wins":129},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":46,"wins":199},"qwen/qwen3.8-27b":{"draws":28,"losses":13,"wins":131},"qwen/qwen3.8-flash":{"draws":28,"losses":16,"wins":136},"qwen/qwen3.8-max":{"draws":39,"losses":32,"wins":195},"qwen/qwen3.8-max-0902":{"draws":35,"losses":42,"wins":165},"stealth/ox-alpha":{"draws":137,"losses":134,"wins":642},"stealth/space-bunny-alpha":{"draws":29,"losses":14,"wins":153},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":153},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":45,"losses":20,"wins":179},"tencent/hy4-preview":{"draws":29,"losses":36,"wins":199},"thinkingmachines/inkling":{"draws":50,"losses":41,"wins":291},"thinkingmachines/inkling-small":{"draws":35,"losses":13,"wins":204},"unbiased/pareto-26.10-preview":{"draws":3,"losses":46,"wins":29},"upstage/solar-mini4":{"draws":7,"losses":1,"wins":40},"x-ai/grok-4.5":{"draws":59,"losses":79,"wins":280},"x-ai/grok-4.6":{"draws":39,"losses":59,"wins":177},"x-ai/grok-4.7":{"draws":21,"losses":99,"wins":100},"x-ai/grok-build-0.1":{"draws":22,"losses":8,"wins":84},"xiaomi/mimo-v2.5":{"draws":87,"losses":35,"wins":426},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":8,"wins":169},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":17,"wins":119},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":36,"wins":96},"z-ai/glm-5.2":{"draws":111,"losses":49,"wins":492},"z-ai/glm-5.3":{"draws":33,"losses":57,"wins":148},"z-ai/glm-5.3-flash":{"draws":35,"losses":61,"wins":196},"z-ai/glm-5.3-flashx":{"draws":36,"losses":44,"wins":166}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":13,"losses":21,"wins":122},"claude-fable-5-1":{"draws":16,"losses":63,"wins":95},"claude-haiku-5-5":{"draws":16,"losses":6,"wins":114},"claude-opus-4-5":{"draws":20,"losses":15,"wins":219},"claude-opus-4-8":{"draws":13,"losses":17,"wins":114},"claude-opus-5":{"draws":25,"losses":78,"wins":167},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":11,"losses":11,"wins":134},"claude-sonnet-5-5":{"draws":16,"losses":29,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":58},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":217},"deepseek/deepseek-v4-pro":{"draws":12,"losses":4,"wins":128},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":134},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":132},"fireworks/ember-1":{"draws":8,"losses":11,"wins":137},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":138},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":98},"google/gemini-3.5-flash":{"draws":13,"losses":9,"wins":174},"google/gemini-3.5-flash-lite":{"draws":17,"losses":2,"wins":253},"google/gemini-3.6-flash":{"draws":21,"losses":19,"wins":232},"google/gemini-3.8-flash":{"draws":16,"losses":20,"wins":120},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":71},"gpt-4.1":{"draws":5,"losses":1,"wins":46},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":5,"wins":124},"gpt-5.4":{"draws":11,"losses":11,"wins":128},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":97},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":152},"gpt-5.5":{"draws":15,"losses":15,"wins":114},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":134},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":123},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":138},"gpt-6-astra":{"draws":17,"losses":74,"wins":65},"gpt-6-luna":{"draws":16,"losses":1,"wins":131},"gpt-6-sol":{"draws":13,"losses":39,"wins":104},"gpt-6.1-sol":{"draws":18,"losses":63,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":102},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":102},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":154},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":131},"meta/muse-spark-1.2":{"draws":12,"losses":7,"wins":127},"meta/muse-spark-1.3":{"draws":8,"losses":9,"wins":129},"meta/muse-wonder":{"draws":9,"losses":28,"wins":101},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"mistralai/mistral-large-4-0":{"draws":12,"losses":4,"wins":68},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":36},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":126},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":74},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":137},"o3":{"draws":11,"losses":4,"wins":197},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":130},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":144},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":86},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":127},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":92},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":131},"qwen/qwen3.8-max-0902":{"draws":16,"losses":11,"wins":123},"stealth/ox-alpha":{"draws":49,"losses":30,"wins":421},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":116},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":98},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":78},"tencent/hy4-preview":{"draws":12,"losses":13,"wins":125},"thinkingmachines/inkling":{"draws":13,"losses":0,"wins":157},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10-preview":{"draws":1,"losses":21,"wins":24},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":18,"losses":15,"wins":123},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":123},"x-ai/grok-4.7":{"draws":11,"losses":31,"wins":96},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":82},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":2,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":10,"wins":76},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":283},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":112},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":132},"z-ai/glm-5.3-flashx":{"draws":15,"losses":10,"wins":131}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":77,"losses":45,"wins":118},"claude-fable-5":{"draws":55,"losses":159,"wins":42},"claude-fable-5-1":{"draws":15,"losses":265,"wins":9},"claude-haiku-5-5":{"draws":34,"losses":61,"wins":37},"claude-opus-4-5":{"draws":136,"losses":168,"wins":112},"claude-opus-4-8":{"draws":38,"losses":58,"wins":38},"claude-opus-5":{"draws":35,"losses":190,"wins":43},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":76,"losses":96,"wins":96},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":36},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":39},"deepseek/deepseek-v4-flash":{"draws":105,"losses":64,"wins":171},"deepseek/deepseek-v4-pro":{"draws":78,"losses":80,"wins":78},"deepseek/deepseek-v4-pro-0813":{"draws":75,"losses":92,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":53,"wins":48},"fireworks/ember-1":{"draws":44,"losses":60,"wins":40},"gemini-3.1-pro-preview":{"draws":43,"losses":50,"wins":51},"google/gemini-3.1-flash-lite":{"draws":34,"losses":7,"wins":67},"google/gemini-3.5-flash":{"draws":88,"losses":120,"wins":88},"google/gemini-3.5-flash-lite":{"draws":198,"losses":155,"wins":345},"google/gemini-3.6-flash":{"draws":160,"losses":280,"wins":216},"google/gemini-3.8-flash":{"draws":66,"losses":127,"wins":65},"google/gemma-4-31b-it":{"draws":23,"losses":12,"wins":41},"gpt-4.1":{"draws":17,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":40,"losses":35,"wins":53},"gpt-5.4":{"draws":116,"losses":188,"wins":80},"gpt-5.4-mini":{"draws":41,"losses":33,"wins":32},"gpt-5.4-nano":{"draws":37,"losses":41,"wins":74},"gpt-5.5":{"draws":52,"losses":65,"wins":25},"gpt-5.6-luna":{"draws":134,"losses":107,"wins":165},"gpt-5.6-sol":{"draws":66,"losses":312,"wins":61},"gpt-5.6-terra":{"draws":94,"losses":81,"wins":73},"gpt-6-astra":{"draws":12,"losses":232,"wins":16},"gpt-6-luna":{"draws":36,"losses":56,"wins":48},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":129,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":73,"losses":17,"wins":94},"inclusionai/ling-3.0-flash":{"draws":58,"losses":18,"wins":98},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":87,"losses":40,"wins":155},"meta/muse-glimmer-30b":{"draws":81,"losses":35,"wins":110},"meta/muse-spark-1.2":{"draws":93,"losses":113,"wins":92},"meta/muse-spark-1.3":{"draws":62,"losses":99,"wins":53},"meta/muse-wonder":{"draws":28,"losses":81,"wins":27},"minimax/minimax-m3":{"draws":21,"losses":17,"wins":46},"mistralai/mistral-large-4-0":{"draws":25,"losses":23,"wins":38},"mistralai/mistral-medium-3-5":{"draws":63,"losses":19,"wins":72},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":104,"losses":136,"wins":76},"nex-agi/nex-n2-pro":{"draws":29,"losses":11,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":30,"wins":56},"o3":{"draws":47,"losses":190,"wins":173},"openai/gpt-oss-120b":{"draws":79,"losses":31,"wins":122},"poolside/laguna-s-2.1":{"draws":93,"losses":35,"wins":138},"qwen/qwen3.7-max":{"draws":28,"losses":18,"wins":44},"qwen/qwen3.7-plus":{"draws":22,"losses":18,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":94,"losses":102,"wins":66},"qwen/qwen3.8-27b":{"draws":30,"losses":53,"wins":47},"qwen/qwen3.8-flash":{"draws":58,"losses":53,"wins":59},"qwen/qwen3.8-max":{"draws":81,"losses":102,"wins":82},"qwen/qwen3.8-max-0902":{"draws":38,"losses":66,"wins":34},"stealth/ox-alpha":{"draws":203,"losses":410,"wins":242},"stealth/space-bunny-alpha":{"draws":30,"losses":37,"wins":47},"stepfun/step-3.7-flash":{"draws":24,"losses":31,"wins":49},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":32,"losses":25,"wins":33},"tencent/hy4-preview":{"draws":78,"losses":116,"wins":64},"thinkingmachines/inkling":{"draws":79,"losses":37,"wins":152},"thinkingmachines/inkling-small":{"draws":80,"losses":47,"wins":133},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":103,"losses":157,"wins":66},"x-ai/grok-4.6":{"draws":71,"losses":129,"wins":60},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":21,"losses":3,"wins":28},"xiaomi/mimo-v2.5":{"draws":88,"losses":37,"wins":113},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":29,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":50,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":51,"wins":24},"z-ai/glm-5.2":{"draws":121,"losses":126,"wins":169},"z-ai/glm-5.3":{"draws":46,"losses":129,"wins":31},"z-ai/glm-5.3-flash":{"draws":55,"losses":132,"wins":69},"z-ai/glm-5.3-flashx":{"draws":39,"losses":72,"wins":33}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":79},"claude-fable-5":{"draws":24,"losses":62,"wins":58},"claude-fable-5-1":{"draws":9,"losses":119,"wins":34},"claude-haiku-5-5":{"draws":25,"losses":43,"wins":62},"claude-opus-4-5":{"draws":48,"losses":57,"wins":129},"claude-opus-4-8":{"draws":28,"losses":42,"wins":62},"claude-opus-5":{"draws":25,"losses":140,"wins":81},"claude-opus-5-5":{"draws":16,"losses":111,"wins":29},"claude-sonnet-5":{"draws":25,"losses":36,"wins":83},"claude-sonnet-5-5":{"draws":10,"losses":43,"wins":43},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":38},"deepseek/deepseek-v4-flash":{"draws":46,"losses":31,"wins":139},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":72},"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":15,"losses":12,"wins":69},"google/gemini-3.5-flash":{"draws":28,"losses":47,"wins":105},"google/gemini-3.5-flash-lite":{"draws":49,"losses":40,"wins":163},"google/gemini-3.6-flash":{"draws":45,"losses":90,"wins":117},"google/gemini-3.8-flash":{"draws":20,"losses":56,"wins":68},"google/gemma-4-31b-it":{"draws":13,"losses":16,"wins":45},"gpt-4.1":{"draws":10,"losses":8,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":27,"losses":26,"wins":73},"gpt-5.4":{"draws":37,"losses":42,"wins":59},"gpt-5.4-mini":{"draws":18,"losses":18,"wins":60},"gpt-5.4-nano":{"draws":21,"losses":18,"wins":105},"gpt-5.5":{"draws":29,"losses":42,"wins":61},"gpt-5.6-luna":{"draws":33,"losses":28,"wins":83},"gpt-5.6-sol":{"draws":15,"losses":70,"wins":59},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":74},"gpt-6-astra":{"draws":13,"losses":105,"wins":26},"gpt-6-luna":{"draws":32,"losses":42,"wins":66},"gpt-6-sol":{"draws":15,"losses":81,"wins":48},"gpt-6.1-sol":{"draws":5,"losses":103,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":65},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":21,"losses":31,"wins":104},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":27,"losses":41,"wins":66},"meta/muse-spark-1.3":{"draws":22,"losses":52,"wins":64},"meta/muse-wonder":{"draws":21,"losses":52,"wins":61},"minimax/minimax-m3":{"draws":13,"losses":13,"wins":52},"mistralai/mistral-large-4-0":{"draws":23,"losses":24,"wins":39},"mistralai/mistral-medium-3-5":{"draws":19,"losses":8,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":28,"losses":45,"wins":59},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":22,"wins":82},"o3":{"draws":17,"losses":45,"wins":130},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":82},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":87},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":17,"losses":12,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":49,"wins":63},"qwen/qwen3.8-27b":{"draws":17,"losses":25,"wins":60},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":23,"losses":41,"wins":80},"qwen/qwen3.8-max-0902":{"draws":24,"losses":51,"wins":63},"stealth/ox-alpha":{"draws":85,"losses":161,"wins":222},"stealth/space-bunny-alpha":{"draws":22,"losses":24,"wins":68},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":61},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":49},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":67},"thinkingmachines/inkling":{"draws":33,"losses":36,"wins":93},"thinkingmachines/inkling-small":{"draws":32,"losses":21,"wins":91},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":9},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":32,"losses":49,"wins":63},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":61},"x-ai/grok-4.7":{"draws":15,"losses":64,"wins":47},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":49,"losses":26,"wins":147},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":34,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":46},"z-ai/glm-5.2":{"draws":55,"losses":65,"wins":168},"z-ai/glm-5.3":{"draws":25,"losses":58,"wins":49},"z-ai/glm-5.3-flash":{"draws":20,"losses":55,"wins":69},"z-ai/glm-5.3-flashx":{"draws":25,"losses":54,"wins":65}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":23,"wins":14},"claude-fable-5":{"draws":6,"losses":44,"wins":2},"claude-fable-5-1":{"draws":0,"losses":60,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":31,"wins":9},"claude-opus-4-5":{"draws":16,"losses":81,"wins":13},"claude-opus-4-8":{"draws":15,"losses":46,"wins":7},"claude-opus-5":{"draws":9,"losses":85,"wins":4},"claude-opus-5-5":{"draws":2,"losses":58,"wins":0},"claude-sonnet-5":{"draws":9,"losses":39,"wins":10},"claude-sonnet-5-5":{"draws":6,"losses":38,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":26,"losses":36,"wins":32},"deepseek/deepseek-v4-pro":{"draws":9,"losses":31,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":29,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":32,"wins":7},"fireworks/ember-1":{"draws":8,"losses":31,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":27,"wins":13},"google/gemini-3.1-flash-lite":{"draws":19,"losses":27,"wins":26},"google/gemini-3.5-flash":{"draws":16,"losses":43,"wins":13},"google/gemini-3.5-flash-lite":{"draws":40,"losses":40,"wins":38},"google/gemini-3.6-flash":{"draws":30,"losses":74,"wins":10},"google/gemini-3.8-flash":{"draws":7,"losses":37,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":18,"wins":6},"gpt-4.1":{"draws":11,"losses":16,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":51,"wins":10},"gpt-5.4":{"draws":8,"losses":37,"wins":7},"gpt-5.4-mini":{"draws":15,"losses":28,"wins":11},"gpt-5.4-nano":{"draws":19,"losses":50,"wins":17},"gpt-5.5":{"draws":22,"losses":44,"wins":8},"gpt-5.6-luna":{"draws":16,"losses":31,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":42,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":35,"wins":8},"gpt-6-astra":{"draws":2,"losses":48,"wins":0},"gpt-6-luna":{"draws":10,"losses":30,"wins":8},"gpt-6-sol":{"draws":6,"losses":43,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":50,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":16,"wins":16},"inclusionai/ling-3.0-flash":{"draws":24,"losses":24,"wins":14},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":49,"wins":18},"meta/muse-glimmer-30b":{"draws":20,"losses":20,"wins":12},"meta/muse-spark-1.2":{"draws":3,"losses":39,"wins":12},"meta/muse-spark-1.3":{"draws":2,"losses":48,"wins":2},"meta/muse-wonder":{"draws":3,"losses":45,"wins":4},"minimax/minimax-m3":{"draws":9,"losses":24,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":20,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":13,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":34,"wins":11},"nex-agi/nex-n2-pro":{"draws":21,"losses":26,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":24,"wins":25},"o3":{"draws":18,"losses":68,"wins":18},"openai/gpt-oss-120b":{"draws":15,"losses":17,"wins":14},"poolside/laguna-s-2.1":{"draws":27,"losses":19,"wins":28},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":23,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":41,"wins":3},"qwen/qwen3.8-27b":{"draws":6,"losses":24,"wins":4},"qwen/qwen3.8-flash":{"draws":11,"losses":18,"wins":9},"qwen/qwen3.8-max":{"draws":8,"losses":40,"wins":4},"qwen/qwen3.8-max-0902":{"draws":7,"losses":38,"wins":5},"stealth/ox-alpha":{"draws":31,"losses":121,"wins":22},"stealth/space-bunny-alpha":{"draws":9,"losses":28,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":25,"wins":5},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":19,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":34,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":24,"wins":27},"thinkingmachines/inkling-small":{"draws":17,"losses":24,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":52,"wins":4},"x-ai/grok-4.6":{"draws":13,"losses":39,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":41,"wins":0},"x-ai/grok-build-0.1":{"draws":12,"losses":19,"wins":7},"xiaomi/mimo-v2.5":{"draws":45,"losses":41,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":23,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":22,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":27,"wins":5},"z-ai/glm-5.2":{"draws":36,"losses":65,"wins":19},"z-ai/glm-5.3":{"draws":5,"losses":41,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":36,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":38,"wins":3}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":102,"losses":97,"wins":101},"claude-fable-5":{"draws":59,"losses":220,"wins":21},"claude-fable-5-1":{"draws":13,"losses":299,"wins":2},"claude-haiku-5-5":{"draws":55,"losses":111,"wins":30},"claude-opus-4-5":{"draws":142,"losses":236,"wins":94},"claude-opus-4-8":{"draws":64,"losses":146,"wins":26},"claude-opus-5":{"draws":48,"losses":353,"wins":25},"claude-opus-5-5":{"draws":13,"losses":217,"wins":6},"claude-sonnet-5":{"draws":105,"losses":171,"wins":64},"claude-sonnet-5-5":{"draws":46,"losses":139,"wins":31},"cohere/north-mini-code":{"draws":26,"losses":32,"wins":36},"deepseek/deepseek-v4-flash":{"draws":114,"losses":133,"wins":133},"deepseek/deepseek-v4-pro":{"draws":96,"losses":141,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":107,"losses":128,"wins":69},"deepseek/deepseek-v4.1-flash":{"draws":75,"losses":116,"wins":25},"fireworks/ember-1":{"draws":70,"losses":109,"wins":37},"gemini-3.1-pro-preview":{"draws":69,"losses":95,"wins":52},"google/gemini-3.1-flash-lite":{"draws":59,"losses":56,"wins":109},"google/gemini-3.5-flash":{"draws":109,"losses":186,"wins":85},"google/gemini-3.5-flash-lite":{"draws":198,"losses":193,"wins":193},"google/gemini-3.6-flash":{"draws":152,"losses":318,"wins":90},"google/gemini-3.8-flash":{"draws":67,"losses":204,"wins":37},"google/gemma-4-31b-it":{"draws":40,"losses":22,"wins":44},"gpt-4.1":{"draws":40,"losses":43,"wins":21},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":84,"losses":105,"wins":47},"gpt-5.4":{"draws":102,"losses":162,"wins":40},"gpt-5.4-mini":{"draws":82,"losses":67,"wins":51},"gpt-5.4-nano":{"draws":74,"losses":105,"wins":111},"gpt-5.5":{"draws":100,"losses":119,"wins":23},"gpt-5.6-luna":{"draws":132,"losses":115,"wins":85},"gpt-5.6-sol":{"draws":44,"losses":222,"wins":34},"gpt-5.6-terra":{"draws":111,"losses":151,"wins":56},"gpt-6-astra":{"draws":14,"losses":262,"wins":6},"gpt-6-luna":{"draws":66,"losses":102,"wins":40},"gpt-6-sol":{"draws":32,"losses":168,"wins":16},"gpt-6.1-sol":{"draws":14,"losses":197,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":105,"losses":33,"wins":98},"inclusionai/ling-3.0-flash":{"draws":96,"losses":57,"wins":81},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":103,"losses":98,"wins":129},"meta/muse-glimmer-30b":{"draws":141,"losses":63,"wins":86},"meta/muse-spark-1.2":{"draws":71,"losses":134,"wins":51},"meta/muse-spark-1.3":{"draws":56,"losses":178,"wins":42},"meta/muse-wonder":{"draws":36,"losses":139,"wins":31},"minimax/minimax-m3":{"draws":54,"losses":60,"wins":58},"mistralai/mistral-large-4-0":{"draws":34,"losses":64,"wins":20},"mistralai/mistral-medium-3-5":{"draws":83,"losses":40,"wins":67},"moonshotai/kimi-k2.7-code":{"draws":19,"losses":36,"wins":17},"moonshotai/kimi-k3":{"draws":74,"losses":131,"wins":65},"nex-agi/nex-n2-pro":{"draws":39,"losses":49,"wins":74},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":110,"losses":67,"wins":87},"o3":{"draws":64,"losses":224,"wins":118},"openai/gpt-oss-120b":{"draws":123,"losses":87,"wins":82},"poolside/laguna-s-2.1":{"draws":136,"losses":93,"wins":89},"qwen/qwen3.7-max":{"draws":75,"losses":61,"wins":34},"qwen/qwen3.7-plus":{"draws":48,"losses":51,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":103,"losses":159,"wins":56},"qwen/qwen3.8-27b":{"draws":41,"losses":94,"wins":45},"qwen/qwen3.8-flash":{"draws":77,"losses":89,"wins":46},"qwen/qwen3.8-max":{"draws":109,"losses":151,"wins":58},"qwen/qwen3.8-max-0902":{"draws":58,"losses":122,"wins":28},"stealth/ox-alpha":{"draws":275,"losses":535,"wins":195},"stealth/space-bunny-alpha":{"draws":60,"losses":70,"wins":38},"stepfun/step-3.7-flash":{"draws":43,"losses":69,"wins":64},"stepfun/step-5-preview":{"draws":1,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":50,"losses":61,"wins":49},"tencent/hy4-preview":{"draws":87,"losses":157,"wins":58},"thinkingmachines/inkling":{"draws":113,"losses":95,"wins":114},"thinkingmachines/inkling-small":{"draws":151,"losses":66,"wins":127},"unbiased/pareto-26.10-preview":{"draws":0,"losses":65,"wins":1},"upstage/solar-mini4":{"draws":10,"losses":16,"wins":28},"x-ai/grok-4.5":{"draws":62,"losses":187,"wins":55},"x-ai/grok-4.6":{"draws":92,"losses":188,"wins":34},"x-ai/grok-4.7":{"draws":20,"losses":157,"wins":15},"x-ai/grok-build-0.1":{"draws":40,"losses":26,"wins":38},"xiaomi/mimo-v2.5":{"draws":177,"losses":161,"wins":140},"xiaomi/mimo-v2.5-pro":{"draws":55,"losses":63,"wins":52},"xiaomi/mimo-v2.6-flash":{"draws":33,"losses":79,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":90,"wins":23},"z-ai/glm-5.2":{"draws":223,"losses":246,"wins":139},"z-ai/glm-5.3":{"draws":68,"losses":176,"wins":16},"z-ai/glm-5.3-flash":{"draws":97,"losses":154,"wins":49},"z-ai/glm-5.3-flashx":{"draws":58,"losses":126,"wins":32}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":63,"losses":54,"wins":107},"claude-fable-5":{"draws":50,"losses":124,"wins":54},"claude-fable-5-1":{"draws":16,"losses":224,"wins":6},"claude-haiku-5-5":{"draws":33,"losses":44,"wins":39},"claude-opus-4-5":{"draws":77,"losses":102,"wins":107},"claude-opus-4-8":{"draws":31,"losses":58,"wins":41},"claude-opus-5":{"draws":30,"losses":185,"wins":33},"claude-opus-5-5":{"draws":12,"losses":128,"wins":4},"claude-sonnet-5":{"draws":78,"losses":78,"wins":80},"claude-sonnet-5-5":{"draws":32,"losses":67,"wins":33},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":31},"deepseek/deepseek-v4-flash":{"draws":96,"losses":61,"wins":141},"deepseek/deepseek-v4-pro":{"draws":48,"losses":54,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":75,"losses":76,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":53,"wins":41},"fireworks/ember-1":{"draws":41,"losses":53,"wins":38},"gemini-3.1-pro-preview":{"draws":35,"losses":44,"wins":53},"google/gemini-3.1-flash-lite":{"draws":28,"losses":5,"wins":57},"google/gemini-3.5-flash":{"draws":73,"losses":102,"wins":93},"google/gemini-3.5-flash-lite":{"draws":130,"losses":109,"wins":193},"google/gemini-3.6-flash":{"draws":105,"losses":151,"wins":138},"google/gemini-3.8-flash":{"draws":63,"losses":118,"wins":53},"google/gemma-4-31b-it":{"draws":26,"losses":14,"wins":32},"gpt-4.1":{"draws":13,"losses":9,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":39,"losses":31,"wins":53},"gpt-5.4":{"draws":65,"losses":98,"wins":65},"gpt-5.4-mini":{"draws":34,"losses":21,"wins":33},"gpt-5.4-nano":{"draws":27,"losses":43,"wins":66},"gpt-5.5":{"draws":42,"losses":60,"wins":30},"gpt-5.6-luna":{"draws":82,"losses":65,"wins":89},"gpt-5.6-sol":{"draws":27,"losses":139,"wins":54},"gpt-5.6-terra":{"draws":79,"losses":70,"wins":79},"gpt-6-astra":{"draws":15,"losses":183,"wins":20},"gpt-6-luna":{"draws":33,"losses":54,"wins":41},"gpt-6-sol":{"draws":14,"losses":98,"wins":20},"gpt-6.1-sol":{"draws":9,"losses":115,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":70,"losses":17,"wins":73},"inclusionai/ling-3.0-flash":{"draws":40,"losses":15,"wins":59},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":54,"losses":27,"wins":110},"meta/muse-glimmer-30b":{"draws":77,"losses":45,"wins":90},"meta/muse-spark-1.2":{"draws":33,"losses":80,"wins":73},"meta/muse-spark-1.3":{"draws":33,"losses":107,"wins":56},"meta/muse-wonder":{"draws":22,"losses":71,"wins":29},"minimax/minimax-m3":{"draws":16,"losses":11,"wins":47},"mistralai/mistral-large-4-0":{"draws":20,"losses":32,"wins":24},"mistralai/mistral-medium-3-5":{"draws":44,"losses":16,"wins":80},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":14},"moonshotai/kimi-k3":{"draws":47,"losses":76,"wins":59},"nex-agi/nex-n2-pro":{"draws":21,"losses":13,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":18,"wins":52},"o3":{"draws":43,"losses":94,"wins":135},"openai/gpt-oss-120b":{"draws":74,"losses":42,"wins":90},"poolside/laguna-s-2.1":{"draws":67,"losses":49,"wins":72},"qwen/qwen3.7-max":{"draws":27,"losses":16,"wins":39},"qwen/qwen3.7-plus":{"draws":18,"losses":12,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":72,"losses":94,"wins":64},"qwen/qwen3.8-27b":{"draws":27,"losses":48,"wins":41},"qwen/qwen3.8-flash":{"draws":46,"losses":59,"wins":51},"qwen/qwen3.8-max":{"draws":67,"losses":102,"wins":65},"qwen/qwen3.8-max-0902":{"draws":35,"losses":61,"wins":32},"stealth/ox-alpha":{"draws":210,"losses":317,"wins":231},"stealth/space-bunny-alpha":{"draws":31,"losses":28,"wins":47},"stepfun/step-3.7-flash":{"draws":21,"losses":21,"wins":50},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":18,"wins":30},"tencent/hy4-preview":{"draws":67,"losses":100,"wins":65},"thinkingmachines/inkling":{"draws":71,"losses":26,"wins":105},"thinkingmachines/inkling-small":{"draws":98,"losses":30,"wins":118},"unbiased/pareto-26.10-preview":{"draws":0,"losses":40,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":54,"losses":84,"wins":70},"x-ai/grok-4.6":{"draws":62,"losses":122,"wins":52},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":21},"x-ai/grok-build-0.1":{"draws":18,"losses":11,"wins":19},"xiaomi/mimo-v2.5":{"draws":83,"losses":30,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":32,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":45,"wins":25},"z-ai/glm-5.2":{"draws":138,"losses":110,"wins":136},"z-ai/glm-5.3":{"draws":43,"losses":107,"wins":42},"z-ai/glm-5.3-flash":{"draws":58,"losses":105,"wins":65},"z-ai/glm-5.3-flashx":{"draws":32,"losses":60,"wins":40}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":68,"losses":57,"wins":93},"claude-fable-5":{"draws":41,"losses":135,"wins":44},"claude-fable-5-1":{"draws":9,"losses":237,"wins":6},"claude-haiku-5-5":{"draws":30,"losses":62,"wins":28},"claude-opus-4-5":{"draws":80,"losses":101,"wins":109},"claude-opus-4-8":{"draws":30,"losses":60,"wins":42},"claude-opus-5":{"draws":24,"losses":188,"wins":28},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":75,"losses":67,"wins":92},"claude-sonnet-5-5":{"draws":22,"losses":77,"wins":33},"cohere/north-mini-code":{"draws":12,"losses":5,"wins":29},"deepseek/deepseek-v4-flash":{"draws":107,"losses":69,"wins":128},"deepseek/deepseek-v4-pro":{"draws":75,"losses":73,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":52,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":59,"wins":30},"fireworks/ember-1":{"draws":36,"losses":55,"wins":41},"gemini-3.1-pro-preview":{"draws":40,"losses":43,"wins":49},"google/gemini-3.1-flash-lite":{"draws":23,"losses":12,"wins":55},"google/gemini-3.5-flash":{"draws":90,"losses":113,"wins":77},"google/gemini-3.5-flash-lite":{"draws":152,"losses":84,"wins":172},"google/gemini-3.6-flash":{"draws":112,"losses":182,"wins":116},"google/gemini-3.8-flash":{"draws":62,"losses":106,"wins":62},"google/gemma-4-31b-it":{"draws":24,"losses":7,"wins":37},"gpt-4.1":{"draws":19,"losses":7,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":39,"losses":44,"wins":43},"gpt-5.4":{"draws":64,"losses":96,"wins":56},"gpt-5.4-mini":{"draws":33,"losses":19,"wins":38},"gpt-5.4-nano":{"draws":31,"losses":39,"wins":64},"gpt-5.5":{"draws":37,"losses":53,"wins":36},"gpt-5.6-luna":{"draws":83,"losses":70,"wins":85},"gpt-5.6-sol":{"draws":37,"losses":136,"wins":49},"gpt-5.6-terra":{"draws":73,"losses":86,"wins":73},"gpt-6-astra":{"draws":15,"losses":198,"wins":1},"gpt-6-luna":{"draws":38,"losses":46,"wins":44},"gpt-6-sol":{"draws":15,"losses":97,"wins":20},"gpt-6.1-sol":{"draws":8,"losses":121,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":63,"losses":20,"wins":79},"inclusionai/ling-3.0-flash":{"draws":53,"losses":21,"wins":48},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":75,"losses":35,"wins":90},"meta/muse-glimmer-30b":{"draws":82,"losses":35,"wins":95},"meta/muse-spark-1.2":{"draws":53,"losses":71,"wins":62},"meta/muse-spark-1.3":{"draws":47,"losses":90,"wins":57},"meta/muse-wonder":{"draws":26,"losses":73,"wins":27},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":46},"mistralai/mistral-large-4-0":{"draws":25,"losses":23,"wins":28},"mistralai/mistral-medium-3-5":{"draws":43,"losses":21,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":16,"wins":17},"moonshotai/kimi-k3":{"draws":56,"losses":55,"wins":71},"nex-agi/nex-n2-pro":{"draws":19,"losses":7,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":16,"wins":61},"o3":{"draws":44,"losses":76,"wins":138},"openai/gpt-oss-120b":{"draws":72,"losses":45,"wins":73},"poolside/laguna-s-2.1":{"draws":71,"losses":45,"wins":66},"qwen/qwen3.7-max":{"draws":30,"losses":19,"wins":35},"qwen/qwen3.7-plus":{"draws":21,"losses":19,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":88,"wins":75},"qwen/qwen3.8-27b":{"draws":32,"losses":46,"wins":40},"qwen/qwen3.8-flash":{"draws":59,"losses":48,"wins":45},"qwen/qwen3.8-max":{"draws":79,"losses":86,"wins":69},"qwen/qwen3.8-max-0902":{"draws":38,"losses":54,"wins":38},"stealth/ox-alpha":{"draws":204,"losses":295,"wins":259},"stealth/space-bunny-alpha":{"draws":31,"losses":26,"wins":47},"stepfun/step-3.7-flash":{"draws":28,"losses":19,"wins":51},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":33,"losses":19,"wins":26},"tencent/hy4-preview":{"draws":59,"losses":97,"wins":72},"thinkingmachines/inkling":{"draws":65,"losses":47,"wins":84},"thinkingmachines/inkling-small":{"draws":79,"losses":43,"wins":110},"unbiased/pareto-26.10-preview":{"draws":1,"losses":35,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":3,"wins":26},"x-ai/grok-4.5":{"draws":51,"losses":82,"wins":69},"x-ai/grok-4.6":{"draws":79,"losses":101,"wins":54},"x-ai/grok-4.7":{"draws":9,"losses":83,"wins":22},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":21},"xiaomi/mimo-v2.5":{"draws":91,"losses":34,"wins":101},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":30,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":43,"wins":26},"z-ai/glm-5.2":{"draws":140,"losses":108,"wins":132},"z-ai/glm-5.3":{"draws":41,"losses":98,"wins":47},"z-ai/glm-5.3-flash":{"draws":55,"losses":112,"wins":59},"z-ai/glm-5.3-flashx":{"draws":32,"losses":63,"wins":37}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":32,"wins":60},"claude-fable-5":{"draws":34,"losses":74,"wins":36},"claude-fable-5-1":{"draws":17,"losses":133,"wins":12},"claude-haiku-5-5":{"draws":39,"losses":52,"wins":39},"claude-opus-4-5":{"draws":62,"losses":68,"wins":104},"claude-opus-4-8":{"draws":32,"losses":47,"wins":53},"claude-opus-5":{"draws":40,"losses":170,"wins":36},"claude-opus-5-5":{"draws":9,"losses":132,"wins":15},"claude-sonnet-5":{"draws":43,"losses":48,"wins":53},"claude-sonnet-5-5":{"draws":31,"losses":72,"wins":41},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":32},"deepseek/deepseek-v4-flash":{"draws":75,"losses":25,"wins":116},"deepseek/deepseek-v4-pro":{"draws":38,"losses":41,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":30,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":36,"wins":36},"fireworks/ember-1":{"draws":47,"losses":51,"wins":46},"gemini-3.1-pro-preview":{"draws":43,"losses":49,"wins":52},"google/gemini-3.1-flash-lite":{"draws":35,"losses":9,"wins":52},"google/gemini-3.5-flash":{"draws":55,"losses":51,"wins":74},"google/gemini-3.5-flash-lite":{"draws":89,"losses":47,"wins":116},"google/gemini-3.6-flash":{"draws":70,"losses":98,"wins":84},"google/gemini-3.8-flash":{"draws":38,"losses":61,"wins":45},"google/gemma-4-31b-it":{"draws":30,"losses":12,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":43,"losses":28,"wins":55},"gpt-5.4":{"draws":46,"losses":53,"wins":39},"gpt-5.4-mini":{"draws":36,"losses":20,"wins":38},"gpt-5.4-nano":{"draws":36,"losses":35,"wins":73},"gpt-5.5":{"draws":45,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":54,"losses":26,"wins":64},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":43},"gpt-5.6-terra":{"draws":54,"losses":34,"wins":50},"gpt-6-astra":{"draws":16,"losses":120,"wins":6},"gpt-6-luna":{"draws":42,"losses":38,"wins":58},"gpt-6-sol":{"draws":26,"losses":85,"wins":33},"gpt-6.1-sol":{"draws":15,"losses":115,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":45,"losses":9,"wins":48},"inclusionai/ling-3.0-flash":{"draws":40,"losses":9,"wins":49},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":34,"wins":85},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":34,"losses":47,"wins":53},"meta/muse-spark-1.3":{"draws":27,"losses":57,"wins":54},"meta/muse-wonder":{"draws":36,"losses":60,"wins":36},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":42},"mistralai/mistral-large-4-0":{"draws":31,"losses":24,"wins":31},"mistralai/mistral-medium-3-5":{"draws":30,"losses":9,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3":{"draws":38,"losses":41,"wins":55},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":22,"wins":58},"o3":{"draws":40,"losses":62,"wins":90},"openai/gpt-oss-120b":{"draws":42,"losses":23,"wins":61},"poolside/laguna-s-2.1":{"draws":58,"losses":23,"wins":57},"qwen/qwen3.7-max":{"draws":31,"losses":19,"wins":34},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":50,"wins":58},"qwen/qwen3.8-27b":{"draws":24,"losses":29,"wins":49},"qwen/qwen3.8-flash":{"draws":36,"losses":19,"wins":41},"qwen/qwen3.8-max":{"draws":41,"losses":48,"wins":55},"qwen/qwen3.8-max-0902":{"draws":45,"losses":45,"wins":50},"stealth/ox-alpha":{"draws":111,"losses":179,"wins":178},"stealth/space-bunny-alpha":{"draws":36,"losses":25,"wins":53},"stepfun/step-3.7-flash":{"draws":22,"losses":16,"wins":58},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":15,"wins":36},"tencent/hy4-preview":{"draws":41,"losses":56,"wins":41},"thinkingmachines/inkling":{"draws":54,"losses":22,"wins":86},"thinkingmachines/inkling-small":{"draws":46,"losses":25,"wins":72},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":64,"wins":49},"x-ai/grok-4.6":{"draws":40,"losses":61,"wins":43},"x-ai/grok-4.7":{"draws":11,"losses":82,"wins":33},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":27},"xiaomi/mimo-v2.5":{"draws":80,"losses":26,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":32,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":23,"losses":41,"wins":30},"z-ai/glm-5.2":{"draws":103,"losses":62,"wins":122},"z-ai/glm-5.3":{"draws":28,"losses":79,"wins":27},"z-ai/glm-5.3-flash":{"draws":38,"losses":59,"wins":47},"z-ai/glm-5.3-flashx":{"draws":40,"losses":61,"wins":43}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":24,"wins":68},"claude-fable-5":{"draws":31,"losses":91,"wins":22},"claude-fable-5-1":{"draws":4,"losses":150,"wins":8},"claude-haiku-5-5":{"draws":33,"losses":62,"wins":35},"claude-opus-4-5":{"draws":82,"losses":62,"wins":90},"claude-opus-4-8":{"draws":44,"losses":51,"wins":37},"claude-opus-5":{"draws":27,"losses":176,"wins":43},"claude-opus-5-5":{"draws":8,"losses":137,"wins":11},"claude-sonnet-5":{"draws":44,"losses":40,"wins":60},"claude-sonnet-5-5":{"draws":30,"losses":72,"wins":42},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":31},"deepseek/deepseek-v4-flash":{"draws":70,"losses":37,"wins":109},"deepseek/deepseek-v4-pro":{"draws":41,"losses":38,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":41,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":47,"losses":46,"wins":51},"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":24,"losses":4,"wins":68},"google/gemini-3.5-flash":{"draws":53,"losses":58,"wins":69},"google/gemini-3.5-flash-lite":{"draws":95,"losses":44,"wins":113},"google/gemini-3.6-flash":{"draws":70,"losses":90,"wins":92},"google/gemini-3.8-flash":{"draws":35,"losses":61,"wins":48},"google/gemma-4-31b-it":{"draws":29,"losses":12,"wins":37},"gpt-4.1":{"draws":14,"losses":15,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":36,"losses":31,"wins":59},"gpt-5.4":{"draws":40,"losses":60,"wins":38},"gpt-5.4-mini":{"draws":37,"losses":15,"wins":44},"gpt-5.4-nano":{"draws":34,"losses":31,"wins":79},"gpt-5.5":{"draws":42,"losses":49,"wins":41},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":23,"losses":85,"wins":36},"gpt-5.6-terra":{"draws":44,"losses":36,"wins":58},"gpt-6-astra":{"draws":10,"losses":128,"wins":6},"gpt-6-luna":{"draws":38,"losses":41,"wins":61},"gpt-6-sol":{"draws":21,"losses":100,"wins":23},"gpt-6.1-sol":{"draws":10,"losses":117,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":44,"losses":6,"wins":52},"inclusionai/ling-3.0-flash":{"draws":42,"losses":4,"wins":50},"meituan/longcat-2.0":{"draws":49,"losses":19,"wins":87},"meta/muse-glimmer-30b":{"draws":44,"losses":15,"wins":67},"meta/muse-spark-1.2":{"draws":37,"losses":45,"wins":52},"meta/muse-spark-1.3":{"draws":37,"losses":62,"wins":41},"meta/muse-wonder":{"draws":34,"losses":72,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":5,"wins":54},"mistralai/mistral-large-4-0":{"draws":23,"losses":32,"wins":31},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":43,"losses":37,"wins":54},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":19,"wins":58},"o3":{"draws":39,"losses":50,"wins":105},"openai/gpt-oss-120b":{"draws":48,"losses":14,"wins":64},"poolside/laguna-s-2.1":{"draws":53,"losses":22,"wins":63},"qwen/qwen3.7-max":{"draws":26,"losses":19,"wins":39},"qwen/qwen3.7-plus":{"draws":23,"losses":11,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":47,"wins":47},"qwen/qwen3.8-27b":{"draws":29,"losses":38,"wins":35},"qwen/qwen3.8-flash":{"draws":34,"losses":27,"wins":35},"qwen/qwen3.8-max":{"draws":46,"losses":41,"wins":57},"qwen/qwen3.8-max-0902":{"draws":44,"losses":57,"wins":43},"stealth/ox-alpha":{"draws":126,"losses":175,"wins":167},"stealth/space-bunny-alpha":{"draws":36,"losses":23,"wins":55},"stepfun/step-3.7-flash":{"draws":21,"losses":18,"wins":59},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":36},"tencent/hy4-preview":{"draws":42,"losses":54,"wins":42},"thinkingmachines/inkling":{"draws":50,"losses":23,"wins":89},"thinkingmachines/inkling-small":{"draws":50,"losses":17,"wins":77},"unbiased/pareto-26.10-preview":{"draws":1,"losses":44,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":23},"x-ai/grok-4.5":{"draws":34,"losses":71,"wins":39},"x-ai/grok-4.6":{"draws":40,"losses":62,"wins":42},"x-ai/grok-4.7":{"draws":11,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":83,"losses":29,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":18,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":41,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":66,"wins":128},"z-ai/glm-5.3":{"draws":26,"losses":81,"wins":27},"z-ai/glm-5.3-flash":{"draws":32,"losses":67,"wins":45},"z-ai/glm-5.3-flashx":{"draws":35,"losses":58,"wins":51}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":39,"wins":57},"claude-fable-5":{"draws":27,"losses":87,"wins":30},"claude-fable-5-1":{"draws":6,"losses":150,"wins":6},"claude-haiku-5-5":{"draws":28,"losses":57,"wins":43},"claude-opus-4-5":{"draws":62,"losses":97,"wins":75},"claude-opus-4-8":{"draws":36,"losses":61,"wins":35},"claude-opus-5":{"draws":24,"losses":185,"wins":37},"claude-opus-5-5":{"draws":8,"losses":138,"wins":10},"claude-sonnet-5":{"draws":43,"losses":51,"wins":50},"claude-sonnet-5-5":{"draws":22,"losses":83,"wins":39},"cohere/north-mini-code":{"draws":14,"losses":13,"wins":27},"deepseek/deepseek-v4-flash":{"draws":69,"losses":52,"wins":95},"deepseek/deepseek-v4-pro":{"draws":35,"losses":53,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":49,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":52,"wins":49},"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":22,"losses":21,"wins":53},"google/gemini-3.5-flash":{"draws":43,"losses":78,"wins":59},"google/gemini-3.5-flash-lite":{"draws":81,"losses":64,"wins":107},"google/gemini-3.6-flash":{"draws":54,"losses":115,"wins":83},"google/gemini-3.8-flash":{"draws":28,"losses":82,"wins":34},"google/gemma-4-31b-it":{"draws":26,"losses":15,"wins":35},"gpt-4.1":{"draws":15,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":40,"losses":35,"wins":51},"gpt-5.4":{"draws":30,"losses":66,"wins":42},"gpt-5.4-mini":{"draws":38,"losses":24,"wins":34},"gpt-5.4-nano":{"draws":36,"losses":41,"wins":67},"gpt-5.5":{"draws":38,"losses":62,"wins":32},"gpt-5.6-luna":{"draws":42,"losses":47,"wins":55},"gpt-5.6-sol":{"draws":18,"losses":95,"wins":31},"gpt-5.6-terra":{"draws":47,"losses":44,"wins":47},"gpt-6-astra":{"draws":10,"losses":130,"wins":4},"gpt-6-luna":{"draws":36,"losses":46,"wins":60},"gpt-6-sol":{"draws":19,"losses":99,"wins":26},"gpt-6.1-sol":{"draws":8,"losses":126,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":40},"inclusionai/ling-3.0-flash":{"draws":35,"losses":10,"wins":53},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":37,"losses":44,"wins":73},"meta/muse-glimmer-30b":{"draws":49,"losses":15,"wins":62},"meta/muse-spark-1.2":{"draws":34,"losses":52,"wins":46},"meta/muse-spark-1.3":{"draws":26,"losses":77,"wins":37},"meta/muse-wonder":{"draws":26,"losses":82,"wins":20},"minimax/minimax-m3":{"draws":19,"losses":22,"wins":37},"mistralai/mistral-large-4-0":{"draws":19,"losses":33,"wins":32},"mistralai/mistral-medium-3-5":{"draws":32,"losses":10,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":17},"moonshotai/kimi-k3":{"draws":34,"losses":62,"wins":40},"nex-agi/nex-n2-pro":{"draws":21,"losses":11,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":28,"wins":50},"o3":{"draws":29,"losses":90,"wins":73},"openai/gpt-oss-120b":{"draws":44,"losses":27,"wins":55},"poolside/laguna-s-2.1":{"draws":47,"losses":32,"wins":59},"qwen/qwen3.7-max":{"draws":26,"losses":29,"wins":29},"qwen/qwen3.7-plus":{"draws":23,"losses":14,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":62,"wins":46},"qwen/qwen3.8-27b":{"draws":23,"losses":47,"wins":32},"qwen/qwen3.8-flash":{"draws":36,"losses":30,"wins":30},"qwen/qwen3.8-max":{"draws":43,"losses":54,"wins":47},"qwen/qwen3.8-max-0902":{"draws":37,"losses":66,"wins":35},"stealth/ox-alpha":{"draws":107,"losses":217,"wins":144},"stealth/space-bunny-alpha":{"draws":36,"losses":34,"wins":44},"stepfun/step-3.7-flash":{"draws":23,"losses":32,"wins":45},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":24,"losses":21,"wins":33},"tencent/hy4-preview":{"draws":33,"losses":65,"wins":40},"thinkingmachines/inkling":{"draws":47,"losses":41,"wins":74},"thinkingmachines/inkling-small":{"draws":45,"losses":29,"wins":70},"unbiased/pareto-26.10-preview":{"draws":1,"losses":44,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":13,"wins":18},"x-ai/grok-4.5":{"draws":31,"losses":73,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":76,"wins":28},"x-ai/grok-4.7":{"draws":14,"losses":89,"wins":23},"x-ai/grok-build-0.1":{"draws":17,"losses":13,"wins":18},"xiaomi/mimo-v2.5":{"draws":74,"losses":49,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":52,"wins":22},"z-ai/glm-5.2":{"draws":85,"losses":94,"wins":109},"z-ai/glm-5.3":{"draws":25,"losses":76,"wins":31},"z-ai/glm-5.3-flash":{"draws":36,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":35,"losses":75,"wins":34}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":48,"wins":20},"claude-fable-5":{"draws":12,"losses":83,"wins":3},"claude-fable-5-1":{"draws":5,"losses":104,"wins":0},"claude-haiku-5-5":{"draws":20,"losses":61,"wins":7},"claude-opus-4-5":{"draws":63,"losses":179,"wins":12},"claude-opus-4-8":{"draws":39,"losses":121,"wins":10},"claude-opus-5":{"draws":28,"losses":175,"wins":9},"claude-opus-5-5":{"draws":6,"losses":98,"wins":0},"claude-sonnet-5":{"draws":34,"losses":67,"wins":7},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":19,"losses":26,"wins":27},"deepseek/deepseek-v4-flash":{"draws":59,"losses":109,"wins":56},"deepseek/deepseek-v4-pro":{"draws":28,"losses":57,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":55,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":52,"wins":9},"fireworks/ember-1":{"draws":24,"losses":68,"wins":4},"gemini-3.1-pro-preview":{"draws":22,"losses":53,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":48,"wins":48},"google/gemini-3.5-flash":{"draws":35,"losses":89,"wins":18},"google/gemini-3.5-flash-lite":{"draws":65,"losses":107,"wins":46},"google/gemini-3.6-flash":{"draws":47,"losses":144,"wins":15},"google/gemini-3.8-flash":{"draws":26,"losses":70,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":26,"wins":15},"gpt-4.1":{"draws":25,"losses":33,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":51,"losses":84,"wins":5},"gpt-5.4":{"draws":22,"losses":71,"wins":7},"gpt-5.4-mini":{"draws":35,"losses":70,"wins":15},"gpt-5.4-nano":{"draws":40,"losses":123,"wins":49},"gpt-5.5":{"draws":44,"losses":89,"wins":9},"gpt-5.6-luna":{"draws":26,"losses":50,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":83,"wins":5},"gpt-5.6-terra":{"draws":30,"losses":66,"wins":10},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":21,"losses":60,"wins":11},"gpt-6-sol":{"draws":13,"losses":82,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":92,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":28,"wins":19},"inclusionai/ling-3.0-flash":{"draws":40,"losses":33,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":96,"wins":48},"meta/muse-glimmer-30b":{"draws":39,"losses":34,"wins":19},"meta/muse-spark-1.2":{"draws":24,"losses":66,"wins":10},"meta/muse-spark-1.3":{"draws":16,"losses":79,"wins":5},"meta/muse-wonder":{"draws":9,"losses":76,"wins":3},"minimax/minimax-m3":{"draws":29,"losses":50,"wins":41},"mistralai/mistral-large-4-0":{"draws":16,"losses":38,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":26,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":36,"wins":3},"moonshotai/kimi-k3":{"draws":24,"losses":58,"wins":10},"nex-agi/nex-n2-pro":{"draws":18,"losses":49,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":76,"wins":44},"o3":{"draws":30,"losses":154,"wins":14},"openai/gpt-oss-120b":{"draws":25,"losses":42,"wins":19},"poolside/laguna-s-2.1":{"draws":35,"losses":64,"wins":33},"qwen/qwen3.7-max":{"draws":33,"losses":55,"wins":18},"qwen/qwen3.7-plus":{"draws":28,"losses":59,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":70,"wins":3},"qwen/qwen3.8-27b":{"draws":15,"losses":48,"wins":11},"qwen/qwen3.8-flash":{"draws":28,"losses":34,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":66,"wins":1},"qwen/qwen3.8-max-0902":{"draws":27,"losses":63,"wins":2},"stealth/ox-alpha":{"draws":56,"losses":196,"wins":31},"stealth/space-bunny-alpha":{"draws":21,"losses":47,"wins":12},"stepfun/step-3.7-flash":{"draws":18,"losses":69,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":34,"losses":40,"wins":24},"tencent/hy4-preview":{"draws":23,"losses":74,"wins":3},"thinkingmachines/inkling":{"draws":48,"losses":75,"wins":49},"thinkingmachines/inkling-small":{"draws":34,"losses":40,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":29,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":19,"wins":7},"x-ai/grok-4.5":{"draws":27,"losses":95,"wins":4},"x-ai/grok-4.6":{"draws":18,"losses":72,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":79,"wins":1},"x-ai/grok-build-0.1":{"draws":21,"losses":38,"wins":9},"xiaomi/mimo-v2.5":{"draws":111,"losses":133,"wins":76},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":79,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":44,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":46,"wins":5},"z-ai/glm-5.2":{"draws":67,"losses":168,"wins":35},"z-ai/glm-5.3":{"draws":17,"losses":76,"wins":1},"z-ai/glm-5.3-flash":{"draws":25,"losses":64,"wins":11},"z-ai/glm-5.3-flashx":{"draws":25,"losses":64,"wins":7}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":75,"losses":61,"wins":120},"claude-fable-5":{"draws":59,"losses":171,"wins":54},"claude-fable-5-1":{"draws":23,"losses":279,"wins":14},"claude-haiku-5-5":{"draws":35,"losses":71,"wins":58},"claude-opus-4-5":{"draws":108,"losses":129,"wins":159},"claude-opus-4-8":{"draws":55,"losses":93,"wins":52},"claude-opus-5":{"draws":43,"losses":269,"wins":33},"claude-opus-5-5":{"draws":13,"losses":174,"wins":9},"claude-sonnet-5":{"draws":88,"losses":88,"wins":120},"claude-sonnet-5-5":{"draws":28,"losses":105,"wins":47},"cohere/north-mini-code":{"draws":16,"losses":13,"wins":43},"deepseek/deepseek-v4-flash":{"draws":109,"losses":85,"wins":186},"deepseek/deepseek-v4-pro":{"draws":73,"losses":93,"wins":102},"deepseek/deepseek-v4-pro-0813":{"draws":90,"losses":77,"wins":113},"deepseek/deepseek-v4.1-flash":{"draws":55,"losses":74,"wins":51},"fireworks/ember-1":{"draws":53,"losses":69,"wins":58},"gemini-3.1-pro-preview":{"draws":43,"losses":59,"wins":78},"google/gemini-3.1-flash-lite":{"draws":35,"losses":18,"wins":89},"google/gemini-3.5-flash":{"draws":56,"losses":92,"wins":92},"google/gemini-3.5-flash-lite":{"draws":143,"losses":130,"wins":227},"google/gemini-3.6-flash":{"draws":124,"losses":185,"wins":185},"google/gemini-3.8-flash":{"draws":64,"losses":150,"wins":82},"google/gemma-4-31b-it":{"draws":21,"losses":20,"wins":51},"gpt-4.1":{"draws":19,"losses":20,"wins":27},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":52,"losses":58,"wins":70},"gpt-5.4":{"draws":52,"losses":137,"wins":87},"gpt-5.4-mini":{"draws":48,"losses":31,"wins":57},"gpt-5.4-nano":{"draws":46,"losses":57,"wins":119},"gpt-5.5":{"draws":58,"losses":74,"wins":46},"gpt-5.6-luna":{"draws":91,"losses":75,"wins":120},"gpt-5.6-sol":{"draws":33,"losses":178,"wins":73},"gpt-5.6-terra":{"draws":94,"losses":97,"wins":81},"gpt-6-astra":{"draws":27,"losses":246,"wins":11},"gpt-6-luna":{"draws":49,"losses":58,"wins":69},"gpt-6-sol":{"draws":27,"losses":127,"wins":26},"gpt-6.1-sol":{"draws":12,"losses":151,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":73,"losses":21,"wins":98},"inclusionai/ling-3.0-flash":{"draws":52,"losses":16,"wins":92},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":61,"losses":44,"wins":149},"meta/muse-glimmer-30b":{"draws":82,"losses":44,"wins":118},"meta/muse-spark-1.2":{"draws":54,"losses":92,"wins":88},"meta/muse-spark-1.3":{"draws":49,"losses":129,"wins":70},"meta/muse-wonder":{"draws":27,"losses":117,"wins":28},"minimax/minimax-m3":{"draws":31,"losses":28,"wins":51},"mistralai/mistral-large-4-0":{"draws":31,"losses":36,"wins":35},"mistralai/mistral-medium-3-5":{"draws":49,"losses":26,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":19,"wins":16},"moonshotai/kimi-k3":{"draws":83,"losses":78,"wins":89},"nex-agi/nex-n2-pro":{"draws":29,"losses":21,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":36,"wins":85},"o3":{"draws":52,"losses":112,"wins":186},"openai/gpt-oss-120b":{"draws":81,"losses":51,"wins":114},"poolside/laguna-s-2.1":{"draws":75,"losses":46,"wins":115},"qwen/qwen3.7-max":{"draws":37,"losses":40,"wins":43},"qwen/qwen3.7-plus":{"draws":27,"losses":18,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":79,"losses":117,"wins":96},"qwen/qwen3.8-27b":{"draws":29,"losses":61,"wins":60},"qwen/qwen3.8-flash":{"draws":66,"losses":54,"wins":78},"qwen/qwen3.8-max":{"draws":90,"losses":87,"wins":101},"qwen/qwen3.8-max-0902":{"draws":48,"losses":83,"wins":45},"stealth/ox-alpha":{"draws":203,"losses":390,"wins":328},"stealth/space-bunny-alpha":{"draws":43,"losses":33,"wins":68},"stepfun/step-3.7-flash":{"draws":24,"losses":28,"wins":78},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":29,"wins":43},"tencent/hy4-preview":{"draws":63,"losses":143,"wins":74},"thinkingmachines/inkling":{"draws":63,"losses":51,"wins":142},"thinkingmachines/inkling-small":{"draws":83,"losses":51,"wins":138},"unbiased/pareto-26.10-preview":{"draws":0,"losses":47,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":55,"losses":121,"wins":86},"x-ai/grok-4.6":{"draws":83,"losses":154,"wins":55},"x-ai/grok-4.7":{"draws":15,"losses":118,"wins":25},"x-ai/grok-build-0.1":{"draws":21,"losses":10,"wins":37},"xiaomi/mimo-v2.5":{"draws":98,"losses":57,"wins":153},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":40,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":52,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":58,"wins":37},"z-ai/glm-5.2":{"draws":138,"losses":149,"wins":193},"z-ai/glm-5.3":{"draws":52,"losses":135,"wins":59},"z-ai/glm-5.3-flash":{"draws":67,"losses":127,"wins":96},"z-ai/glm-5.3-flashx":{"draws":48,"losses":87,"wins":43}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":157,"losses":145,"wins":138},"claude-fable-5":{"draws":84,"losses":257,"wins":55},"claude-fable-5-1":{"draws":28,"losses":375,"wins":3},"claude-haiku-5-5":{"draws":43,"losses":145,"wins":40},"claude-opus-4-5":{"draws":269,"losses":373,"wins":182},"claude-opus-4-8":{"draws":83,"losses":175,"wins":34},"claude-opus-5":{"draws":74,"losses":449,"wins":43},"claude-opus-5-5":{"draws":17,"losses":253,"wins":2},"claude-sonnet-5":{"draws":198,"losses":345,"wins":155},"claude-sonnet-5-5":{"draws":49,"losses":163,"wins":40},"cohere/north-mini-code":{"draws":40,"losses":38,"wins":40},"deepseek/deepseek-v4-flash":{"draws":198,"losses":193,"wins":193},"deepseek/deepseek-v4-pro":{"draws":130,"losses":193,"wins":109},"deepseek/deepseek-v4-pro-0813":{"draws":152,"losses":172,"wins":84},"deepseek/deepseek-v4.1-flash":{"draws":89,"losses":116,"wins":47},"fireworks/ember-1":{"draws":95,"losses":113,"wins":44},"gemini-3.1-pro-preview":{"draws":81,"losses":107,"wins":64},"google/gemini-3.1-flash-lite":{"draws":65,"losses":46,"wins":107},"google/gemini-3.5-flash":{"draws":143,"losses":227,"wins":130},"google/gemini-3.5-flash-lite":{"draws":440,"losses":430,"wins":430},"google/gemini-3.6-flash":{"draws":443,"losses":662,"wins":274},"google/gemini-3.8-flash":{"draws":88,"losses":274,"wins":28},"google/gemma-4-31b-it":{"draws":43,"losses":35,"wins":58},"gpt-4.1":{"draws":38,"losses":35,"wins":39},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":102,"losses":102,"wins":66},"gpt-5.4":{"draws":182,"losses":368,"wins":94},"gpt-5.4-mini":{"draws":82,"losses":80,"wins":54},"gpt-5.4-nano":{"draws":82,"losses":104,"wins":132},"gpt-5.5":{"draws":128,"losses":130,"wins":40},"gpt-5.6-luna":{"draws":230,"losses":274,"wins":214},"gpt-5.6-sol":{"draws":92,"losses":497,"wins":57},"gpt-5.6-terra":{"draws":139,"losses":191,"wins":94},"gpt-6-astra":{"draws":21,"losses":345,"wins":2},"gpt-6-luna":{"draws":81,"losses":114,"wins":55},"gpt-6-sol":{"draws":39,"losses":191,"wins":22},"gpt-6.1-sol":{"draws":16,"losses":235,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":151,"losses":61,"wins":136},"inclusionai/ling-3.0-flash":{"draws":150,"losses":69,"wins":181},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":173,"losses":213,"wins":257},"meta/muse-glimmer-30b":{"draws":180,"losses":97,"wins":149},"meta/muse-spark-1.2":{"draws":134,"losses":267,"wins":107},"meta/muse-spark-1.3":{"draws":84,"losses":211,"wins":67},"meta/muse-wonder":{"draws":43,"losses":168,"wins":27},"minimax/minimax-m3":{"draws":51,"losses":54,"wins":67},"mistralai/mistral-large-4-0":{"draws":39,"losses":70,"wins":29},"mistralai/mistral-medium-3-5":{"draws":105,"losses":60,"wins":119},"moonshotai/kimi-k2.7-code":{"draws":18,"losses":33,"wins":21},"moonshotai/kimi-k3":{"draws":210,"losses":298,"wins":126},"nex-agi/nex-n2-pro":{"draws":56,"losses":40,"wins":64},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":109,"losses":80,"wins":77},"o3":{"draws":131,"losses":518,"wins":229},"openai/gpt-oss-120b":{"draws":149,"losses":117,"wins":142},"poolside/laguna-s-2.1":{"draws":257,"losses":206,"wins":165},"qwen/qwen3.7-max":{"draws":52,"losses":67,"wins":55},"qwen/qwen3.7-plus":{"draws":53,"losses":51,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":145,"losses":207,"wins":78},"qwen/qwen3.8-27b":{"draws":40,"losses":130,"wins":50},"qwen/qwen3.8-flash":{"draws":112,"losses":125,"wins":49},"qwen/qwen3.8-max":{"draws":152,"losses":190,"wins":95},"qwen/qwen3.8-max-0902":{"draws":73,"losses":134,"wins":35},"stealth/ox-alpha":{"draws":338,"losses":755,"wins":290},"stealth/space-bunny-alpha":{"draws":58,"losses":84,"wins":60},"stepfun/step-3.7-flash":{"draws":53,"losses":63,"wins":76},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":66,"losses":64,"wins":32},"tencent/hy4-preview":{"draws":126,"losses":218,"wins":84},"thinkingmachines/inkling":{"draws":186,"losses":179,"wins":237},"thinkingmachines/inkling-small":{"draws":176,"losses":143,"wins":177},"unbiased/pareto-26.10-preview":{"draws":2,"losses":75,"wins":1},"upstage/solar-mini4":{"draws":20,"losses":25,"wins":23},"x-ai/grok-4.5":{"draws":175,"losses":369,"wins":132},"x-ai/grok-4.6":{"draws":119,"losses":232,"wins":57},"x-ai/grok-4.7":{"draws":20,"losses":170,"wins":28},"x-ai/grok-build-0.1":{"draws":47,"losses":34,"wins":30},"xiaomi/mimo-v2.5":{"draws":163,"losses":135,"wins":162},"xiaomi/mimo-v2.5-pro":{"draws":52,"losses":73,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":103,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":114,"wins":29},"z-ai/glm-5.2":{"draws":268,"losses":270,"wins":202},"z-ai/glm-5.3":{"draws":73,"losses":249,"wins":30},"z-ai/glm-5.3-flash":{"draws":122,"losses":235,"wins":69},"z-ai/glm-5.3-flashx":{"draws":67,"losses":137,"wins":47}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":108,"losses":86,"wins":192},"claude-fable-5":{"draws":73,"losses":213,"wins":124},"claude-fable-5-1":{"draws":34,"losses":382,"wins":32},"claude-haiku-5-5":{"draws":54,"losses":86,"wins":92},"claude-opus-4-5":{"draws":222,"losses":241,"wins":345},"claude-opus-4-8":{"draws":78,"losses":111,"wins":129},"claude-opus-5":{"draws":78,"losses":427,"wins":117},"claude-opus-5-5":{"draws":21,"losses":232,"wins":19},"claude-sonnet-5":{"draws":160,"losses":216,"wins":280},"claude-sonnet-5-5":{"draws":45,"losses":117,"wins":90},"cohere/north-mini-code":{"draws":30,"losses":10,"wins":74},"deepseek/deepseek-v4-flash":{"draws":152,"losses":90,"wins":318},"deepseek/deepseek-v4-pro":{"draws":105,"losses":138,"wins":151},"deepseek/deepseek-v4-pro-0813":{"draws":112,"losses":116,"wins":182},"deepseek/deepseek-v4.1-flash":{"draws":70,"losses":84,"wins":98},"fireworks/ember-1":{"draws":70,"losses":92,"wins":90},"gemini-3.1-pro-preview":{"draws":54,"losses":83,"wins":115},"google/gemini-3.1-flash-lite":{"draws":47,"losses":15,"wins":144},"google/gemini-3.5-flash":{"draws":124,"losses":185,"wins":185},"google/gemini-3.5-flash-lite":{"draws":443,"losses":274,"wins":662},"google/gemini-3.6-flash":{"draws":244,"losses":432,"wins":432},"google/gemini-3.8-flash":{"draws":90,"losses":200,"wins":135},"google/gemma-4-31b-it":{"draws":42,"losses":19,"wins":77},"gpt-4.1":{"draws":32,"losses":25,"wins":53},"gpt-4.1-nano":{"draws":12,"losses":2,"wins":14},"gpt-5":{"draws":62,"losses":91,"wins":127},"gpt-5.4":{"draws":157,"losses":290,"wins":195},"gpt-5.4-mini":{"draws":63,"losses":42,"wins":116},"gpt-5.4-nano":{"draws":72,"losses":70,"wins":176},"gpt-5.5":{"draws":102,"losses":111,"wins":105},"gpt-5.6-luna":{"draws":193,"losses":153,"wins":304},"gpt-5.6-sol":{"draws":91,"losses":363,"wins":188},"gpt-5.6-terra":{"draws":123,"losses":112,"wins":165},"gpt-6-astra":{"draws":35,"losses":334,"wins":29},"gpt-6-luna":{"draws":69,"losses":61,"wins":114},"gpt-6-sol":{"draws":30,"losses":165,"wins":57},"gpt-6.1-sol":{"draws":13,"losses":212,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":108,"losses":25,"wins":151},"inclusionai/ling-3.0-flash":{"draws":166,"losses":52,"wins":180},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":165,"losses":99,"wins":348},"meta/muse-glimmer-30b":{"draws":141,"losses":51,"wins":190},"meta/muse-spark-1.2":{"draws":94,"losses":205,"wins":191},"meta/muse-spark-1.3":{"draws":65,"losses":165,"wins":132},"meta/muse-wonder":{"draws":39,"losses":133,"wins":64},"minimax/minimax-m3":{"draws":38,"losses":29,"wins":103},"mistralai/mistral-large-4-0":{"draws":30,"losses":52,"wins":60},"mistralai/mistral-medium-3-5":{"draws":88,"losses":28,"wins":120},"moonshotai/kimi-k2.7-code":{"draws":22,"losses":19,"wins":41},"moonshotai/kimi-k3":{"draws":183,"losses":207,"wins":244},"nex-agi/nex-n2-pro":{"draws":40,"losses":21,"wins":103},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":81,"losses":39,"wins":138},"o3":{"draws":116,"losses":292,"wins":434},"openai/gpt-oss-120b":{"draws":130,"losses":50,"wins":180},"poolside/laguna-s-2.1":{"draws":219,"losses":97,"wins":264},"qwen/qwen3.7-max":{"draws":48,"losses":40,"wins":98},"qwen/qwen3.7-plus":{"draws":53,"losses":26,"wins":93},"qwen/qwen3.8-2.4t-a95b":{"draws":118,"losses":148,"wins":166},"qwen/qwen3.8-27b":{"draws":43,"losses":79,"wins":100},"qwen/qwen3.8-flash":{"draws":112,"losses":68,"wins":112},"qwen/qwen3.8-max":{"draws":125,"losses":155,"wins":171},"qwen/qwen3.8-max-0902":{"draws":59,"losses":95,"wins":88},"stealth/ox-alpha":{"draws":299,"losses":531,"wins":550},"stealth/space-bunny-alpha":{"draws":55,"losses":41,"wins":106},"stepfun/step-3.7-flash":{"draws":40,"losses":29,"wins":128},"stepfun/step-5-preview":{"draws":6,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":58,"losses":45,"wins":81},"tencent/hy4-preview":{"draws":101,"losses":171,"wins":164},"thinkingmachines/inkling":{"draws":167,"losses":75,"wins":330},"thinkingmachines/inkling-small":{"draws":135,"losses":82,"wins":205},"unbiased/pareto-26.10-preview":{"draws":5,"losses":66,"wins":7},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":47},"x-ai/grok-4.5":{"draws":140,"losses":275,"wins":281},"x-ai/grok-4.6":{"draws":105,"losses":177,"wins":138},"x-ai/grok-4.7":{"draws":8,"losses":157,"wins":53},"x-ai/grok-build-0.1":{"draws":31,"losses":5,"wins":62},"xiaomi/mimo-v2.5":{"draws":169,"losses":60,"wins":247},"xiaomi/mimo-v2.5-pro":{"draws":44,"losses":40,"wins":102},"xiaomi/mimo-v2.6-flash":{"draws":24,"losses":66,"wins":66},"xiaomi/mimo-v2.6-pro":{"draws":35,"losses":72,"wins":55},"z-ai/glm-5.2":{"draws":200,"losses":198,"wins":288},"z-ai/glm-5.3":{"draws":67,"losses":192,"wins":89},"z-ai/glm-5.3-flash":{"draws":91,"losses":190,"wins":135},"z-ai/glm-5.3-flashx":{"draws":62,"losses":99,"wins":91}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":38,"wins":111},"claude-fable-5":{"draws":41,"losses":126,"wins":97},"claude-fable-5-1":{"draws":22,"losses":257,"wins":27},"claude-haiku-5-5":{"draws":32,"losses":39,"wins":59},"claude-opus-4-5":{"draws":99,"losses":63,"wins":172},"claude-opus-4-8":{"draws":30,"losses":51,"wins":63},"claude-opus-5":{"draws":34,"losses":203,"wins":61},"claude-opus-5-5":{"draws":16,"losses":120,"wins":20},"claude-sonnet-5":{"draws":66,"losses":65,"wins":127},"claude-sonnet-5-5":{"draws":20,"losses":68,"wins":56},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":37},"deepseek/deepseek-v4-flash":{"draws":67,"losses":37,"wins":204},"deepseek/deepseek-v4-pro":{"draws":63,"losses":53,"wins":118},"deepseek/deepseek-v4-pro-0813":{"draws":62,"losses":62,"wins":106},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":45,"wins":61},"fireworks/ember-1":{"draws":35,"losses":48,"wins":61},"gemini-3.1-pro-preview":{"draws":28,"losses":34,"wins":82},"google/gemini-3.1-flash-lite":{"draws":26,"losses":4,"wins":70},"google/gemini-3.5-flash":{"draws":64,"losses":82,"wins":150},"google/gemini-3.5-flash-lite":{"draws":88,"losses":28,"wins":274},"google/gemini-3.6-flash":{"draws":90,"losses":135,"wins":200},"google/gemini-3.8-flash":{"draws":46,"losses":67,"wins":67},"google/gemma-4-31b-it":{"draws":22,"losses":9,"wins":47},"gpt-4.1":{"draws":17,"losses":7,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":34,"losses":35,"wins":69},"gpt-5.4":{"draws":61,"losses":103,"wins":92},"gpt-5.4-mini":{"draws":28,"losses":19,"wins":63},"gpt-5.4-nano":{"draws":32,"losses":27,"wins":93},"gpt-5.5":{"draws":49,"losses":46,"wins":43},"gpt-5.6-luna":{"draws":57,"losses":48,"wins":133},"gpt-5.6-sol":{"draws":37,"losses":135,"wins":99},"gpt-5.6-terra":{"draws":79,"losses":63,"wins":102},"gpt-6-astra":{"draws":29,"losses":227,"wins":18},"gpt-6-luna":{"draws":42,"losses":33,"wins":67},"gpt-6-sol":{"draws":22,"losses":89,"wins":33},"gpt-6.1-sol":{"draws":20,"losses":106,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":60,"losses":6,"wins":92},"inclusionai/ling-3.0-flash":{"draws":31,"losses":3,"wins":82},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":43,"losses":22,"wins":126},"meta/muse-glimmer-30b":{"draws":61,"losses":25,"wins":112},"meta/muse-spark-1.2":{"draws":39,"losses":81,"wins":84},"meta/muse-spark-1.3":{"draws":44,"losses":76,"wins":90},"meta/muse-wonder":{"draws":34,"losses":66,"wins":38},"minimax/minimax-m3":{"draws":19,"losses":7,"wins":58},"mistralai/mistral-large-4-0":{"draws":20,"losses":25,"wins":35},"mistralai/mistral-medium-3-5":{"draws":37,"losses":7,"wins":80},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":16,"wins":14},"moonshotai/kimi-k3":{"draws":57,"losses":48,"wins":111},"nex-agi/nex-n2-pro":{"draws":15,"losses":7,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":11,"wins":80},"o3":{"draws":37,"losses":69,"wins":180},"openai/gpt-oss-120b":{"draws":50,"losses":14,"wins":122},"poolside/laguna-s-2.1":{"draws":46,"losses":21,"wins":117},"qwen/qwen3.7-max":{"draws":29,"losses":24,"wins":37},"qwen/qwen3.7-plus":{"draws":21,"losses":7,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":63,"losses":79,"wins":116},"qwen/qwen3.8-27b":{"draws":21,"losses":36,"wins":73},"qwen/qwen3.8-flash":{"draws":42,"losses":43,"wins":81},"qwen/qwen3.8-max":{"draws":68,"losses":81,"wins":101},"qwen/qwen3.8-max-0902":{"draws":36,"losses":45,"wins":59},"stealth/ox-alpha":{"draws":185,"losses":274,"wins":391},"stealth/space-bunny-alpha":{"draws":31,"losses":17,"wins":66},"stepfun/step-3.7-flash":{"draws":19,"losses":9,"wins":72},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":38,"losses":9,"wins":39},"tencent/hy4-preview":{"draws":55,"losses":91,"wins":90},"thinkingmachines/inkling":{"draws":56,"losses":14,"wins":122},"thinkingmachines/inkling-small":{"draws":79,"losses":30,"wins":121},"unbiased/pareto-26.10-preview":{"draws":0,"losses":40,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":40,"losses":104,"wins":76},"x-ai/grok-4.6":{"draws":76,"losses":99,"wins":87},"x-ai/grok-4.7":{"draws":14,"losses":85,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":70,"losses":20,"wins":138},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":15,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":28,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":44,"wins":26},"z-ai/glm-5.2":{"draws":103,"losses":86,"wins":203},"z-ai/glm-5.3":{"draws":46,"losses":103,"wins":67},"z-ai/glm-5.3-flash":{"draws":53,"losses":91,"wins":114},"z-ai/glm-5.3-flashx":{"draws":29,"losses":51,"wins":64}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":21,"wins":24},"claude-fable-5":{"draws":16,"losses":50,"wins":8},"claude-fable-5-1":{"draws":4,"losses":79,"wins":1},"claude-haiku-5-5":{"draws":21,"losses":50,"wins":9},"claude-opus-4-5":{"draws":43,"losses":64,"wins":15},"claude-opus-4-8":{"draws":19,"losses":43,"wins":10},"claude-opus-5":{"draws":21,"losses":97,"wins":10},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":23,"losses":41,"wins":12},"claude-sonnet-5-5":{"draws":13,"losses":45,"wins":16},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":40,"losses":44,"wins":22},"deepseek/deepseek-v4-pro":{"draws":26,"losses":32,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":37,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":38,"wins":12},"fireworks/ember-1":{"draws":29,"losses":37,"wins":12},"gemini-3.1-pro-preview":{"draws":26,"losses":35,"wins":15},"google/gemini-3.1-flash-lite":{"draws":15,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":21,"losses":51,"wins":20},"google/gemini-3.5-flash-lite":{"draws":43,"losses":58,"wins":35},"google/gemini-3.6-flash":{"draws":42,"losses":77,"wins":19},"google/gemini-3.8-flash":{"draws":22,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":7},"gpt-4.1":{"draws":9,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":26,"losses":32,"wins":8},"gpt-5.4":{"draws":22,"losses":39,"wins":9},"gpt-5.4-mini":{"draws":18,"losses":22,"wins":10},"gpt-5.4-nano":{"draws":22,"losses":39,"wins":15},"gpt-5.5":{"draws":25,"losses":37,"wins":6},"gpt-5.6-luna":{"draws":26,"losses":30,"wins":18},"gpt-5.6-sol":{"draws":11,"losses":61,"wins":6},"gpt-5.6-terra":{"draws":27,"losses":36,"wins":9},"gpt-6-astra":{"draws":4,"losses":70,"wins":0},"gpt-6-luna":{"draws":28,"losses":36,"wins":18},"gpt-6-sol":{"draws":9,"losses":65,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":72,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":26,"losses":13,"wins":13},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":31,"wins":24},"meta/muse-glimmer-30b":{"draws":34,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":23,"losses":34,"wins":17},"meta/muse-spark-1.3":{"draws":21,"losses":53,"wins":8},"meta/muse-wonder":{"draws":17,"losses":60,"wins":7},"minimax/minimax-m3":{"draws":15,"losses":14,"wins":11},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":20,"losses":7,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":27,"losses":34,"wins":13},"nex-agi/nex-n2-pro":{"draws":13,"losses":11,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":18,"wins":18},"o3":{"draws":15,"losses":66,"wins":21},"openai/gpt-oss-120b":{"draws":25,"losses":33,"wins":10},"poolside/laguna-s-2.1":{"draws":21,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":13,"losses":20,"wins":13},"qwen/qwen3.7-plus":{"draws":14,"losses":15,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":41,"wins":10},"qwen/qwen3.8-27b":{"draws":17,"losses":27,"wins":10},"qwen/qwen3.8-flash":{"draws":25,"losses":23,"wins":6},"qwen/qwen3.8-max":{"draws":27,"losses":41,"wins":8},"qwen/qwen3.8-max-0902":{"draws":25,"losses":46,"wins":9},"stealth/ox-alpha":{"draws":52,"losses":144,"wins":40},"stealth/space-bunny-alpha":{"draws":22,"losses":26,"wins":14},"stepfun/step-3.7-flash":{"draws":16,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":14,"wins":9},"tencent/hy4-preview":{"draws":24,"losses":39,"wins":11},"thinkingmachines/inkling":{"draws":32,"losses":26,"wins":30},"thinkingmachines/inkling-small":{"draws":29,"losses":25,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":27,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":19,"losses":47,"wins":10},"x-ai/grok-4.6":{"draws":21,"losses":53,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.5":{"draws":50,"losses":41,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":22,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":32,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":39,"wins":4},"z-ai/glm-5.2":{"draws":60,"losses":68,"wins":28},"z-ai/glm-5.3":{"draws":21,"losses":53,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":45,"wins":10},"z-ai/glm-5.3-flashx":{"draws":25,"losses":45,"wins":6}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":11,"wins":17},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":8},"claude-opus-4-5":{"draws":58,"losses":37,"wins":27},"claude-opus-4-8":{"draws":29,"losses":42,"wins":9},"claude-opus-5":{"draws":20,"losses":126,"wins":11},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":11,"losses":5,"wins":16},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":43},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":38,"losses":39,"wins":35},"google/gemini-3.6-flash":{"draws":32,"losses":53,"wins":25},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":7},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":24,"losses":21,"wins":25},"gpt-5.4":{"draws":15,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":29,"losses":27,"wins":12},"gpt-5.4-nano":{"draws":21,"losses":37,"wins":34},"gpt-5.5":{"draws":27,"losses":38,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"gpt-6-astra":{"draws":5,"losses":45,"wins":0},"gpt-6-luna":{"draws":11,"losses":18,"wins":17},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":28,"losses":1,"wins":34},"meituan/longcat-2.0":{"draws":26,"losses":16,"wins":42},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":16},"meta/muse-spark-1.2":{"draws":17,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":18,"losses":30,"wins":4},"meta/muse-wonder":{"draws":7,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":28},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":15,"wins":33},"o3":{"draws":17,"losses":35,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":24,"losses":20,"wins":30},"qwen/qwen3.7-max":{"draws":26,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":19,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":77,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":20},"tencent/hy4-preview":{"draws":13,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":20,"losses":32,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":36,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":14,"losses":8,"wins":12},"xiaomi/mimo-v2.5":{"draws":60,"losses":30,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":14,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":49,"losses":54,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":32,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":38,"wins":44},"claude-fable-5":{"draws":28,"losses":81,"wins":27},"claude-fable-5-1":{"draws":7,"losses":134,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":56,"wins":27},"claude-opus-4-5":{"draws":104,"losses":105,"wins":95},"claude-opus-4-8":{"draws":49,"losses":101,"wins":52},"claude-opus-5":{"draws":44,"losses":281,"wins":29},"claude-opus-5-5":{"draws":9,"losses":124,"wins":5},"claude-sonnet-5":{"draws":40,"losses":53,"wins":35},"claude-sonnet-5-5":{"draws":27,"losses":73,"wins":26},"cohere/north-mini-code":{"draws":15,"losses":10,"wins":51},"deepseek/deepseek-v4-flash":{"draws":84,"losses":47,"wins":105},"deepseek/deepseek-v4-pro":{"draws":39,"losses":53,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":43,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":55,"wins":28},"fireworks/ember-1":{"draws":36,"losses":59,"wins":31},"gemini-3.1-pro-preview":{"draws":40,"losses":51,"wins":35},"google/gemini-3.1-flash-lite":{"draws":51,"losses":5,"wins":84},"google/gemini-3.5-flash":{"draws":52,"losses":70,"wins":58},"google/gemini-3.5-flash-lite":{"draws":102,"losses":66,"wins":102},"google/gemini-3.6-flash":{"draws":62,"losses":127,"wins":91},"google/gemini-3.8-flash":{"draws":34,"losses":69,"wins":35},"google/gemma-4-31b-it":{"draws":26,"losses":8,"wins":32},"gpt-4.1":{"draws":24,"losses":25,"wins":21},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":32,"losses":42,"wins":42},"gpt-5.4":{"draws":32,"losses":68,"wins":26},"gpt-5.4-mini":{"draws":53,"losses":49,"wins":42},"gpt-5.4-nano":{"draws":38,"losses":64,"wins":94},"gpt-5.5":{"draws":72,"losses":92,"wins":48},"gpt-5.6-luna":{"draws":40,"losses":36,"wins":52},"gpt-5.6-sol":{"draws":20,"losses":93,"wins":19},"gpt-5.6-terra":{"draws":36,"losses":56,"wins":36},"gpt-6-astra":{"draws":9,"losses":115,"wins":2},"gpt-6-luna":{"draws":39,"losses":45,"wins":42},"gpt-6-sol":{"draws":15,"losses":95,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":115,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":10,"wins":41},"inclusionai/ling-3.0-flash":{"draws":45,"losses":38,"wins":45},"meituan/longcat-2.0":{"draws":66,"losses":47,"wins":95},"meta/muse-glimmer-30b":{"draws":46,"losses":26,"wins":54},"meta/muse-spark-1.2":{"draws":34,"losses":63,"wins":35},"meta/muse-spark-1.3":{"draws":28,"losses":75,"wins":29},"meta/muse-wonder":{"draws":22,"losses":71,"wins":23},"minimax/minimax-m3":{"draws":36,"losses":30,"wins":54},"mistralai/mistral-large-4-0":{"draws":21,"losses":33,"wins":16},"mistralai/mistral-medium-3-5":{"draws":27,"losses":17,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":24,"wins":21},"moonshotai/kimi-k3":{"draws":38,"losses":50,"wins":42},"nex-agi/nex-n2-pro":{"draws":30,"losses":20,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":78,"losses":36,"wins":76},"o3":{"draws":43,"losses":79,"wins":112},"openai/gpt-oss-120b":{"draws":40,"losses":21,"wins":53},"poolside/laguna-s-2.1":{"draws":67,"losses":58,"wins":57},"qwen/qwen3.7-max":{"draws":54,"losses":26,"wins":48},"qwen/qwen3.7-plus":{"draws":30,"losses":17,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":58,"wins":36},"qwen/qwen3.8-27b":{"draws":18,"losses":42,"wins":34},"qwen/qwen3.8-flash":{"draws":31,"losses":31,"wins":32},"qwen/qwen3.8-max":{"draws":43,"losses":56,"wins":29},"qwen/qwen3.8-max-0902":{"draws":32,"losses":58,"wins":30},"stealth/ox-alpha":{"draws":107,"losses":205,"wins":128},"stealth/space-bunny-alpha":{"draws":26,"losses":35,"wins":39},"stepfun/step-3.7-flash":{"draws":31,"losses":19,"wins":64},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":42,"losses":43,"wins":39},"tencent/hy4-preview":{"draws":42,"losses":52,"wins":36},"thinkingmachines/inkling":{"draws":56,"losses":40,"wins":104},"thinkingmachines/inkling-small":{"draws":53,"losses":20,"wins":55},"unbiased/pareto-26.10-preview":{"draws":1,"losses":38,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":23},"x-ai/grok-4.5":{"draws":35,"losses":93,"wins":44},"x-ai/grok-4.6":{"draws":42,"losses":73,"wins":21},"x-ai/grok-4.7":{"draws":10,"losses":84,"wins":18},"x-ai/grok-build-0.1":{"draws":27,"losses":16,"wins":33},"xiaomi/mimo-v2.5":{"draws":129,"losses":63,"wins":128},"xiaomi/mimo-v2.5-pro":{"draws":36,"losses":30,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":33,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":49,"wins":22},"z-ai/glm-5.2":{"draws":123,"losses":109,"wins":126},"z-ai/glm-5.3":{"draws":19,"losses":81,"wins":22},"z-ai/glm-5.3-flash":{"draws":38,"losses":68,"wins":30},"z-ai/glm-5.3-flashx":{"draws":38,"losses":56,"wins":32}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":47,"wins":91},"claude-fable-5":{"draws":65,"losses":112,"wins":83},"claude-fable-5-1":{"draws":19,"losses":230,"wins":33},"claude-haiku-5-5":{"draws":26,"losses":47,"wins":49},"claude-opus-4-5":{"draws":109,"losses":81,"wins":196},"claude-opus-4-8":{"draws":29,"losses":51,"wins":56},"claude-opus-5":{"draws":29,"losses":189,"wins":36},"claude-opus-5-5":{"draws":11,"losses":128,"wins":11},"claude-sonnet-5":{"draws":116,"losses":80,"wins":188},"claude-sonnet-5-5":{"draws":37,"losses":59,"wins":42},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":37},"deepseek/deepseek-v4-flash":{"draws":102,"losses":40,"wins":162},"deepseek/deepseek-v4-pro":{"draws":65,"losses":65,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":64,"losses":56,"wins":96},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":39,"wins":53},"fireworks/ember-1":{"draws":40,"losses":38,"wins":60},"gemini-3.1-pro-preview":{"draws":30,"losses":42,"wins":66},"google/gemini-3.1-flash-lite":{"draws":22,"losses":7,"wins":71},"google/gemini-3.5-flash":{"draws":52,"losses":87,"wins":137},"google/gemini-3.5-flash-lite":{"draws":182,"losses":94,"wins":368},"google/gemini-3.6-flash":{"draws":157,"losses":195,"wins":290},"google/gemini-3.8-flash":{"draws":61,"losses":92,"wins":103},"google/gemma-4-31b-it":{"draws":22,"losses":9,"wins":39},"gpt-4.1":{"draws":15,"losses":10,"wins":25},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":6},"gpt-5":{"draws":32,"losses":26,"wins":68},"gpt-5.4":{"draws":72,"losses":112,"wins":112},"gpt-5.4-mini":{"draws":32,"losses":6,"wins":54},"gpt-5.4-nano":{"draws":25,"losses":36,"wins":83},"gpt-5.5":{"draws":44,"losses":43,"wins":45},"gpt-5.6-luna":{"draws":141,"losses":56,"wins":200},"gpt-5.6-sol":{"draws":77,"losses":192,"wins":133},"gpt-5.6-terra":{"draws":79,"losses":50,"wins":111},"gpt-6-astra":{"draws":18,"losses":201,"wins":31},"gpt-6-luna":{"draws":42,"losses":33,"wins":59},"gpt-6-sol":{"draws":15,"losses":99,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":109,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":74,"losses":3,"wins":61},"inclusionai/ling-3.0-flash":{"draws":38,"losses":24,"wins":84},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":76,"losses":35,"wins":151},"meta/muse-glimmer-30b":{"draws":68,"losses":30,"wins":98},"meta/muse-spark-1.2":{"draws":63,"losses":94,"wins":123},"meta/muse-spark-1.3":{"draws":47,"losses":72,"wins":87},"meta/muse-wonder":{"draws":28,"losses":62,"wins":42},"minimax/minimax-m3":{"draws":18,"losses":17,"wins":43},"mistralai/mistral-large-4-0":{"draws":25,"losses":15,"wins":36},"mistralai/mistral-medium-3-5":{"draws":50,"losses":20,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":20},"moonshotai/kimi-k3":{"draws":63,"losses":72,"wins":169},"nex-agi/nex-n2-pro":{"draws":20,"losses":14,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":7,"wins":71},"o3":{"draws":45,"losses":83,"wins":260},"openai/gpt-oss-120b":{"draws":81,"losses":25,"wins":90},"poolside/laguna-s-2.1":{"draws":93,"losses":22,"wins":131},"qwen/qwen3.7-max":{"draws":18,"losses":21,"wins":43},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":96,"wins":93},"qwen/qwen3.8-27b":{"draws":27,"losses":29,"wins":70},"qwen/qwen3.8-flash":{"draws":44,"losses":45,"wins":65},"qwen/qwen3.8-max":{"draws":76,"losses":84,"wins":92},"qwen/qwen3.8-max-0902":{"draws":32,"losses":44,"wins":58},"stealth/ox-alpha":{"draws":246,"losses":250,"wins":311},"stealth/space-bunny-alpha":{"draws":34,"losses":16,"wins":60},"stepfun/step-3.7-flash":{"draws":24,"losses":15,"wins":61},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":15,"wins":33},"tencent/hy4-preview":{"draws":61,"losses":79,"wins":102},"thinkingmachines/inkling":{"draws":65,"losses":42,"wins":139},"thinkingmachines/inkling-small":{"draws":98,"losses":24,"wins":101},"unbiased/pareto-26.10-preview":{"draws":2,"losses":34,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":68,"losses":104,"wins":143},"x-ai/grok-4.6":{"draws":81,"losses":87,"wins":92},"x-ai/grok-4.7":{"draws":13,"losses":79,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":67,"losses":13,"wins":138},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":12,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":27,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":36,"wins":37},"z-ai/glm-5.2":{"draws":123,"losses":79,"wins":172},"z-ai/glm-5.3":{"draws":43,"losses":93,"wins":72},"z-ai/glm-5.3-flash":{"draws":51,"losses":90,"wins":105},"z-ai/glm-5.3-flashx":{"draws":34,"losses":54,"wins":50}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":32,"wins":25},"claude-fable-5":{"draws":22,"losses":63,"wins":11},"claude-fable-5-1":{"draws":4,"losses":104,"wins":0},"claude-haiku-5-5":{"draws":26,"losses":49,"wins":11},"claude-opus-4-5":{"draws":95,"losses":109,"wins":66},"claude-opus-4-8":{"draws":46,"losses":75,"wins":43},"claude-opus-5":{"draws":52,"losses":182,"wins":20},"claude-opus-5-5":{"draws":5,"losses":97,"wins":2},"claude-sonnet-5":{"draws":41,"losses":32,"wins":33},"claude-sonnet-5-5":{"draws":18,"losses":60,"wins":18},"cohere/north-mini-code":{"draws":15,"losses":11,"wins":28},"deepseek/deepseek-v4-flash":{"draws":82,"losses":51,"wins":67},"deepseek/deepseek-v4-pro":{"draws":34,"losses":33,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":38,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":38,"wins":20},"fireworks/ember-1":{"draws":37,"losses":44,"wins":15},"gemini-3.1-pro-preview":{"draws":38,"losses":34,"wins":24},"google/gemini-3.1-flash-lite":{"draws":35,"losses":15,"wins":70},"google/gemini-3.5-flash":{"draws":48,"losses":57,"wins":31},"google/gemini-3.5-flash-lite":{"draws":82,"losses":54,"wins":80},"google/gemini-3.6-flash":{"draws":63,"losses":116,"wins":42},"google/gemini-3.8-flash":{"draws":28,"losses":63,"wins":19},"google/gemma-4-31b-it":{"draws":18,"losses":10,"wins":22},"gpt-4.1":{"draws":29,"losses":12,"wins":27},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":53,"losses":42,"wins":49},"gpt-5.4":{"draws":32,"losses":54,"wins":6},"gpt-5.4-mini":{"draws":28,"losses":18,"wins":18},"gpt-5.4-nano":{"draws":54,"losses":89,"wins":53},"gpt-5.5":{"draws":77,"losses":56,"wins":23},"gpt-5.6-luna":{"draws":38,"losses":33,"wins":29},"gpt-5.6-sol":{"draws":23,"losses":67,"wins":14},"gpt-5.6-terra":{"draws":42,"losses":35,"wins":23},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":43,"losses":40,"wins":13},"gpt-6-sol":{"draws":13,"losses":72,"wins":11},"gpt-6.1-sol":{"draws":5,"losses":87,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":15,"wins":23},"inclusionai/ling-3.0-flash":{"draws":59,"losses":19,"wins":42},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":71,"losses":44,"wins":61},"meta/muse-glimmer-30b":{"draws":43,"losses":11,"wins":30},"meta/muse-spark-1.2":{"draws":27,"losses":47,"wins":22},"meta/muse-spark-1.3":{"draws":19,"losses":62,"wins":13},"meta/muse-wonder":{"draws":22,"losses":58,"wins":10},"minimax/minimax-m3":{"draws":38,"losses":40,"wins":42},"mistralai/mistral-large-4-0":{"draws":24,"losses":20,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":25,"wins":11},"moonshotai/kimi-k3":{"draws":43,"losses":50,"wins":29},"nex-agi/nex-n2-pro":{"draws":40,"losses":22,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":82,"losses":40,"wins":40},"o3":{"draws":34,"losses":75,"wins":45},"openai/gpt-oss-120b":{"draws":37,"losses":21,"wins":32},"poolside/laguna-s-2.1":{"draws":71,"losses":34,"wins":49},"qwen/qwen3.7-max":{"draws":37,"losses":45,"wins":26},"qwen/qwen3.7-plus":{"draws":32,"losses":40,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":51,"wins":13},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":19},"qwen/qwen3.8-flash":{"draws":25,"losses":26,"wins":13},"qwen/qwen3.8-max":{"draws":47,"losses":40,"wins":19},"qwen/qwen3.8-max-0902":{"draws":36,"losses":44,"wins":14},"stealth/ox-alpha":{"draws":95,"losses":164,"wins":65},"stealth/space-bunny-alpha":{"draws":28,"losses":33,"wins":15},"stepfun/step-3.7-flash":{"draws":28,"losses":25,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":36,"losses":28,"wins":22},"tencent/hy4-preview":{"draws":35,"losses":48,"wins":13},"thinkingmachines/inkling":{"draws":62,"losses":42,"wins":50},"thinkingmachines/inkling-small":{"draws":45,"losses":26,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":29,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":47,"losses":69,"wins":16},"x-ai/grok-4.6":{"draws":34,"losses":50,"wins":16},"x-ai/grok-4.7":{"draws":14,"losses":66,"wins":4},"x-ai/grok-build-0.1":{"draws":28,"losses":16,"wins":26},"xiaomi/mimo-v2.5":{"draws":126,"losses":76,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":29,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":31,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":36,"wins":9},"z-ai/glm-5.2":{"draws":140,"losses":96,"wins":46},"z-ai/glm-5.3":{"draws":23,"losses":58,"wins":9},"z-ai/glm-5.3-flash":{"draws":35,"losses":51,"wins":16},"z-ai/glm-5.3-flashx":{"draws":27,"losses":56,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":58,"wins":49},"claude-fable-5":{"draws":19,"losses":112,"wins":15},"claude-fable-5-1":{"draws":1,"losses":155,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":70,"wins":37},"claude-opus-4-5":{"draws":105,"losses":174,"wins":115},"claude-opus-4-8":{"draws":52,"losses":147,"wins":59},"claude-opus-5":{"draws":43,"losses":306,"wins":37},"claude-opus-5-5":{"draws":6,"losses":152,"wins":2},"claude-sonnet-5":{"draws":37,"losses":74,"wins":41},"claude-sonnet-5-5":{"draws":21,"losses":105,"wins":18},"cohere/north-mini-code":{"draws":19,"losses":17,"wins":50},"deepseek/deepseek-v4-flash":{"draws":74,"losses":111,"wins":105},"deepseek/deepseek-v4-pro":{"draws":27,"losses":66,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":64,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":73,"wins":35},"fireworks/ember-1":{"draws":34,"losses":79,"wins":31},"gemini-3.1-pro-preview":{"draws":36,"losses":67,"wins":41},"google/gemini-3.1-flash-lite":{"draws":40,"losses":49,"wins":123},"google/gemini-3.5-flash":{"draws":46,"losses":119,"wins":57},"google/gemini-3.5-flash-lite":{"draws":82,"losses":132,"wins":104},"google/gemini-3.6-flash":{"draws":72,"losses":176,"wins":70},"google/gemini-3.8-flash":{"draws":32,"losses":93,"wins":27},"google/gemma-4-31b-it":{"draws":22,"losses":15,"wins":39},"gpt-4.1":{"draws":21,"losses":34,"wins":37},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":38,"losses":94,"wins":64},"gpt-5.4":{"draws":25,"losses":83,"wins":36},"gpt-5.4-mini":{"draws":54,"losses":53,"wins":89},"gpt-5.4-nano":{"draws":50,"losses":103,"wins":103},"gpt-5.5":{"draws":69,"losses":115,"wins":68},"gpt-5.6-luna":{"draws":40,"losses":63,"wins":49},"gpt-5.6-sol":{"draws":19,"losses":115,"wins":14},"gpt-5.6-terra":{"draws":27,"losses":76,"wins":39},"gpt-6-astra":{"draws":4,"losses":141,"wins":1},"gpt-6-luna":{"draws":28,"losses":70,"wins":40},"gpt-6-sol":{"draws":19,"losses":113,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":132,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":18,"wins":58},"inclusionai/ling-3.0-flash":{"draws":63,"losses":37,"wins":72},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":52,"losses":83,"wins":133},"meta/muse-glimmer-30b":{"draws":31,"losses":43,"wins":50},"meta/muse-spark-1.2":{"draws":21,"losses":69,"wins":42},"meta/muse-spark-1.3":{"draws":27,"losses":87,"wins":26},"meta/muse-wonder":{"draws":12,"losses":101,"wins":19},"minimax/minimax-m3":{"draws":46,"losses":52,"wins":76},"mistralai/mistral-large-4-0":{"draws":14,"losses":46,"wins":16},"mistralai/mistral-medium-3-5":{"draws":19,"losses":18,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":28,"wins":28},"moonshotai/kimi-k3":{"draws":43,"losses":92,"wins":37},"nex-agi/nex-n2-pro":{"draws":31,"losses":47,"wins":64},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":73,"losses":77,"wins":90},"o3":{"draws":25,"losses":131,"wins":116},"openai/gpt-oss-120b":{"draws":39,"losses":50,"wins":43},"poolside/laguna-s-2.1":{"draws":74,"losses":85,"wins":73},"qwen/qwen3.7-max":{"draws":51,"losses":71,"wins":54},"qwen/qwen3.7-plus":{"draws":36,"losses":65,"wins":63},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":89,"wins":32},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":34},"qwen/qwen3.8-flash":{"draws":31,"losses":46,"wins":29},"qwen/qwen3.8-max":{"draws":36,"losses":77,"wins":37},"qwen/qwen3.8-max-0902":{"draws":38,"losses":69,"wins":31},"stealth/ox-alpha":{"draws":85,"losses":245,"wins":120},"stealth/space-bunny-alpha":{"draws":26,"losses":47,"wins":39},"stepfun/step-3.7-flash":{"draws":20,"losses":43,"wins":65},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":61,"wins":31},"tencent/hy4-preview":{"draws":23,"losses":91,"wins":32},"thinkingmachines/inkling":{"draws":42,"losses":69,"wins":91},"thinkingmachines/inkling-small":{"draws":53,"losses":45,"wins":56},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":15,"wins":22},"x-ai/grok-4.5":{"draws":36,"losses":113,"wins":49},"x-ai/grok-4.6":{"draws":24,"losses":96,"wins":24},"x-ai/grok-4.7":{"draws":17,"losses":104,"wins":11},"x-ai/grok-build-0.1":{"draws":20,"losses":27,"wins":51},"xiaomi/mimo-v2.5":{"draws":118,"losses":160,"wins":198},"xiaomi/mimo-v2.5-pro":{"draws":38,"losses":75,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":50,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":64,"wins":17},"z-ai/glm-5.2":{"draws":113,"losses":163,"wins":138},"z-ai/glm-5.3":{"draws":20,"losses":93,"wins":25},"z-ai/glm-5.3-flash":{"draws":29,"losses":79,"wins":36},"z-ai/glm-5.3-flashx":{"draws":28,"losses":81,"wins":33}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":24,"wins":56},"claude-fable-5":{"draws":31,"losses":66,"wins":41},"claude-fable-5-1":{"draws":5,"losses":131,"wins":18},"claude-haiku-5-5":{"draws":43,"losses":43,"wins":34},"claude-opus-4-5":{"draws":153,"losses":86,"wins":131},"claude-opus-4-8":{"draws":71,"losses":68,"wins":99},"claude-opus-5":{"draws":61,"losses":301,"wins":104},"claude-opus-5-5":{"draws":15,"losses":114,"wins":15},"claude-sonnet-5":{"draws":52,"losses":25,"wins":65},"claude-sonnet-5-5":{"draws":29,"losses":61,"wins":42},"cohere/north-mini-code":{"draws":22,"losses":8,"wins":44},"deepseek/deepseek-v4-flash":{"draws":100,"losses":23,"wins":119},"deepseek/deepseek-v4-pro":{"draws":42,"losses":30,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":36,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":45,"wins":42},"fireworks/ember-1":{"draws":42,"losses":41,"wins":49},"gemini-3.1-pro-preview":{"draws":38,"losses":32,"wins":62},"google/gemini-3.1-flash-lite":{"draws":44,"losses":9,"wins":89},"google/gemini-3.5-flash":{"draws":58,"losses":46,"wins":74},"google/gemini-3.5-flash-lite":{"draws":128,"losses":40,"wins":130},"google/gemini-3.6-flash":{"draws":102,"losses":105,"wins":111},"google/gemini-3.8-flash":{"draws":49,"losses":43,"wins":46},"google/gemma-4-31b-it":{"draws":25,"losses":6,"wins":37},"gpt-4.1":{"draws":27,"losses":19,"wins":38},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":72,"losses":48,"wins":92},"gpt-5.4":{"draws":44,"losses":45,"wins":43},"gpt-5.4-mini":{"draws":77,"losses":23,"wins":56},"gpt-5.4-nano":{"draws":69,"losses":68,"wins":115},"gpt-5.5":{"draws":76,"losses":48,"wins":48},"gpt-5.6-luna":{"draws":49,"losses":24,"wins":59},"gpt-5.6-sol":{"draws":30,"losses":60,"wins":48},"gpt-5.6-terra":{"draws":48,"losses":31,"wins":49},"gpt-6-astra":{"draws":5,"losses":119,"wins":10},"gpt-6-luna":{"draws":50,"losses":27,"wins":49},"gpt-6-sol":{"draws":20,"losses":83,"wins":29},"gpt-6.1-sol":{"draws":8,"losses":103,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":42},"inclusionai/ling-3.0-flash":{"draws":78,"losses":12,"wins":60},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":87,"losses":42,"wins":92},"meta/muse-glimmer-30b":{"draws":54,"losses":18,"wins":60},"meta/muse-spark-1.2":{"draws":29,"losses":42,"wins":63},"meta/muse-spark-1.3":{"draws":31,"losses":49,"wins":46},"meta/muse-wonder":{"draws":36,"losses":58,"wins":34},"minimax/minimax-m3":{"draws":40,"losses":21,"wins":67},"mistralai/mistral-large-4-0":{"draws":26,"losses":21,"wins":29},"mistralai/mistral-medium-3-5":{"draws":28,"losses":8,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":30,"losses":19,"wins":17},"moonshotai/kimi-k3":{"draws":50,"losses":59,"wins":47},"nex-agi/nex-n2-pro":{"draws":33,"losses":11,"wins":76},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":94,"losses":14,"wins":96},"o3":{"draws":52,"losses":50,"wins":134},"openai/gpt-oss-120b":{"draws":49,"losses":16,"wins":57},"poolside/laguna-s-2.1":{"draws":78,"losses":41,"wins":79},"qwen/qwen3.7-max":{"draws":55,"losses":29,"wins":58},"qwen/qwen3.7-plus":{"draws":53,"losses":12,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":45,"wins":49},"qwen/qwen3.8-27b":{"draws":28,"losses":26,"wins":44},"qwen/qwen3.8-flash":{"draws":37,"losses":21,"wins":42},"qwen/qwen3.8-max":{"draws":44,"losses":43,"wins":51},"qwen/qwen3.8-max-0902":{"draws":44,"losses":43,"wins":41},"stealth/ox-alpha":{"draws":129,"losses":168,"wins":159},"stealth/space-bunny-alpha":{"draws":41,"losses":19,"wins":46},"stepfun/step-3.7-flash":{"draws":26,"losses":15,"wins":69},"stepfun/step-5-preview":{"draws":6,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":67,"losses":17,"wins":52},"tencent/hy4-preview":{"draws":46,"losses":47,"wins":41},"thinkingmachines/inkling":{"draws":69,"losses":39,"wins":116},"thinkingmachines/inkling-small":{"draws":50,"losses":18,"wins":64},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":20},"x-ai/grok-4.5":{"draws":57,"losses":79,"wins":66},"x-ai/grok-4.6":{"draws":47,"losses":58,"wins":39},"x-ai/grok-4.7":{"draws":11,"losses":69,"wins":36},"x-ai/grok-build-0.1":{"draws":51,"losses":14,"wins":21},"xiaomi/mimo-v2.5":{"draws":164,"losses":34,"wins":156},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":27,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":26,"losses":23,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":34,"wins":30},"z-ai/glm-5.2":{"draws":148,"losses":75,"wins":157},"z-ai/glm-5.3":{"draws":33,"losses":67,"wins":26},"z-ai/glm-5.3-flash":{"draws":33,"losses":60,"wins":45},"z-ai/glm-5.3-flashx":{"draws":42,"losses":46,"wins":44}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":77,"losses":86,"wins":71},"claude-fable-5":{"draws":61,"losses":133,"wins":34},"claude-fable-5-1":{"draws":15,"losses":206,"wins":9},"claude-haiku-5-5":{"draws":37,"losses":69,"wins":24},"claude-opus-4-5":{"draws":142,"losses":159,"wins":105},"claude-opus-4-8":{"draws":42,"losses":62,"wins":30},"claude-opus-5":{"draws":26,"losses":204,"wins":26},"claude-opus-5-5":{"draws":17,"losses":134,"wins":5},"claude-sonnet-5":{"draws":134,"losses":165,"wins":107},"claude-sonnet-5-5":{"draws":33,"losses":83,"wins":28},"cohere/north-mini-code":{"draws":16,"losses":9,"wins":31},"deepseek/deepseek-v4-flash":{"draws":132,"losses":85,"wins":115},"deepseek/deepseek-v4-pro":{"draws":82,"losses":89,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":83,"losses":85,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":64,"wins":26},"fireworks/ember-1":{"draws":50,"losses":54,"wins":40},"gemini-3.1-pro-preview":{"draws":42,"losses":55,"wins":47},"google/gemini-3.1-flash-lite":{"draws":26,"losses":20,"wins":50},"google/gemini-3.5-flash":{"draws":91,"losses":120,"wins":75},"google/gemini-3.5-flash-lite":{"draws":230,"losses":214,"wins":274},"google/gemini-3.6-flash":{"draws":193,"losses":304,"wins":153},"google/gemini-3.8-flash":{"draws":57,"losses":133,"wins":48},"google/gemma-4-31b-it":{"draws":26,"losses":18,"wins":30},"gpt-4.1":{"draws":17,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":40,"losses":52,"wins":36},"gpt-5.4":{"draws":141,"losses":200,"wins":56},"gpt-5.4-mini":{"draws":38,"losses":29,"wins":33},"gpt-5.4-nano":{"draws":40,"losses":49,"wins":63},"gpt-5.5":{"draws":49,"losses":59,"wins":24},"gpt-5.6-luna":{"draws":124,"losses":75,"wins":75},"gpt-5.6-sol":{"draws":59,"losses":247,"wins":66},"gpt-5.6-terra":{"draws":82,"losses":85,"wins":85},"gpt-6-astra":{"draws":25,"losses":177,"wins":2},"gpt-6-luna":{"draws":48,"losses":58,"wins":38},"gpt-6-sol":{"draws":24,"losses":106,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":94,"losses":33,"wins":61},"inclusionai/ling-3.0-flash":{"draws":64,"losses":43,"wins":57},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":85,"losses":82,"wins":119},"meta/muse-glimmer-30b":{"draws":103,"losses":61,"wins":74},"meta/muse-spark-1.2":{"draws":80,"losses":136,"wins":78},"meta/muse-spark-1.3":{"draws":56,"losses":104,"wins":46},"meta/muse-wonder":{"draws":28,"losses":81,"wins":25},"minimax/minimax-m3":{"draws":25,"losses":21,"wins":32},"mistralai/mistral-large-4-0":{"draws":27,"losses":40,"wins":15},"mistralai/mistral-medium-3-5":{"draws":66,"losses":24,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":99,"losses":137,"wins":70},"nex-agi/nex-n2-pro":{"draws":24,"losses":12,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":33,"wins":42},"o3":{"draws":66,"losses":187,"wins":147},"openai/gpt-oss-120b":{"draws":110,"losses":52,"wins":74},"poolside/laguna-s-2.1":{"draws":111,"losses":73,"wins":94},"qwen/qwen3.7-max":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.7-plus":{"draws":26,"losses":21,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":95,"losses":98,"wins":49},"qwen/qwen3.8-27b":{"draws":37,"losses":55,"wins":32},"qwen/qwen3.8-flash":{"draws":60,"losses":62,"wins":50},"qwen/qwen3.8-max":{"draws":90,"losses":106,"wins":54},"qwen/qwen3.8-max-0902":{"draws":49,"losses":61,"wins":32},"stealth/ox-alpha":{"draws":260,"losses":350,"wins":185},"stealth/space-bunny-alpha":{"draws":43,"losses":40,"wins":31},"stepfun/step-3.7-flash":{"draws":26,"losses":33,"wins":41},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":28,"wins":21},"tencent/hy4-preview":{"draws":77,"losses":111,"wins":46},"thinkingmachines/inkling":{"draws":99,"losses":53,"wins":114},"thinkingmachines/inkling-small":{"draws":115,"losses":78,"wins":85},"unbiased/pareto-26.10-preview":{"draws":3,"losses":38,"wins":3},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":17},"x-ai/grok-4.5":{"draws":80,"losses":133,"wins":95},"x-ai/grok-4.6":{"draws":67,"losses":131,"wins":42},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":19,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":93,"losses":47,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":34,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":58,"wins":17},"z-ai/glm-5.2":{"draws":154,"losses":153,"wins":93},"z-ai/glm-5.3":{"draws":47,"losses":122,"wins":29},"z-ai/glm-5.3-flash":{"draws":75,"losses":113,"wins":52},"z-ai/glm-5.3-flashx":{"draws":42,"losses":73,"wins":29}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":28,"wins":147},"claude-fable-5":{"draws":35,"losses":124,"wins":111},"claude-fable-5-1":{"draws":25,"losses":249,"wins":44},"claude-haiku-5-5":{"draws":21,"losses":38,"wins":71},"claude-opus-4-5":{"draws":73,"losses":83,"wins":264},"claude-opus-4-8":{"draws":26,"losses":55,"wins":75},"claude-opus-5":{"draws":37,"losses":196,"wins":63},"claude-opus-5-5":{"draws":12,"losses":123,"wins":21},"claude-sonnet-5":{"draws":66,"losses":61,"wins":312},"claude-sonnet-5-5":{"draws":15,"losses":59,"wins":70},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":42},"deepseek/deepseek-v4-flash":{"draws":44,"losses":34,"wins":222},"deepseek/deepseek-v4-pro":{"draws":27,"losses":54,"wins":139},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":49,"wins":136},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":43,"wins":75},"fireworks/ember-1":{"draws":23,"losses":36,"wins":85},"gemini-3.1-pro-preview":{"draws":18,"losses":31,"wins":95},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":83},"google/gemini-3.5-flash":{"draws":33,"losses":73,"wins":178},"google/gemini-3.5-flash-lite":{"draws":92,"losses":57,"wins":497},"google/gemini-3.6-flash":{"draws":91,"losses":188,"wins":363},"google/gemini-3.8-flash":{"draws":37,"losses":99,"wins":135},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":61},"gpt-4.1":{"draws":10,"losses":6,"wins":34},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":20,"losses":19,"wins":93},"gpt-5.4":{"draws":77,"losses":133,"wins":192},"gpt-5.4-mini":{"draws":23,"losses":14,"wins":67},"gpt-5.4-nano":{"draws":19,"losses":14,"wins":115},"gpt-5.5":{"draws":30,"losses":48,"wins":60},"gpt-5.6-luna":{"draws":59,"losses":66,"wins":247},"gpt-5.6-sol":{"draws":40,"losses":132,"wins":132},"gpt-5.6-terra":{"draws":64,"losses":45,"wins":147},"gpt-6-astra":{"draws":29,"losses":226,"wins":27},"gpt-6-luna":{"draws":30,"losses":22,"wins":86},"gpt-6-sol":{"draws":13,"losses":85,"wins":46},"gpt-6.1-sol":{"draws":13,"losses":110,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":33,"losses":1,"wins":116},"inclusionai/ling-3.0-flash":{"draws":22,"losses":10,"wins":124},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":43,"losses":27,"wins":204},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":129},"meta/muse-spark-1.2":{"draws":37,"losses":72,"wins":193},"meta/muse-spark-1.3":{"draws":34,"losses":62,"wins":110},"meta/muse-wonder":{"draws":22,"losses":62,"wins":52},"minimax/minimax-m3":{"draws":15,"losses":4,"wins":61},"mistralai/mistral-large-4-0":{"draws":17,"losses":18,"wins":49},"mistralai/mistral-medium-3-5":{"draws":24,"losses":7,"wins":91},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":24},"moonshotai/kimi-k3":{"draws":53,"losses":67,"wins":188},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":12,"wins":100},"o3":{"draws":25,"losses":70,"wins":297},"openai/gpt-oss-120b":{"draws":29,"losses":13,"wins":148},"poolside/laguna-s-2.1":{"draws":47,"losses":10,"wins":211},"qwen/qwen3.7-max":{"draws":13,"losses":15,"wins":60},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":67,"wins":149},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":85},"qwen/qwen3.8-flash":{"draws":35,"losses":35,"wins":94},"qwen/qwen3.8-max":{"draws":50,"losses":61,"wins":146},"qwen/qwen3.8-max-0902":{"draws":21,"losses":34,"wins":84},"stealth/ox-alpha":{"draws":128,"losses":217,"wins":508},"stealth/space-bunny-alpha":{"draws":20,"losses":14,"wins":80},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":81},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":58},"tencent/hy4-preview":{"draws":35,"losses":83,"wins":132},"thinkingmachines/inkling":{"draws":43,"losses":21,"wins":184},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":171},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":32},"x-ai/grok-4.5":{"draws":41,"losses":106,"wins":181},"x-ai/grok-4.6":{"draws":53,"losses":105,"wins":118},"x-ai/grok-4.7":{"draws":16,"losses":66,"wins":44},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":34},"xiaomi/mimo-v2.5":{"draws":41,"losses":16,"wins":173},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":21,"wins":59},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":31,"wins":41},"z-ai/glm-5.2":{"draws":48,"losses":62,"wins":268},"z-ai/glm-5.3":{"draws":39,"losses":74,"wins":105},"z-ai/glm-5.3-flash":{"draws":46,"losses":90,"wins":132},"z-ai/glm-5.3-flashx":{"draws":23,"losses":41,"wins":80}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":68,"losses":43,"wins":107},"claude-fable-5":{"draws":68,"losses":150,"wins":40},"claude-fable-5-1":{"draws":22,"losses":244,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":54,"wins":36},"claude-opus-4-5":{"draws":106,"losses":109,"wins":85},"claude-opus-4-8":{"draws":36,"losses":61,"wins":37},"claude-opus-5":{"draws":30,"losses":197,"wins":21},"claude-opus-5-5":{"draws":9,"losses":138,"wins":3},"claude-sonnet-5":{"draws":94,"losses":73,"wins":81},"claude-sonnet-5-5":{"draws":34,"losses":74,"wins":30},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":35},"deepseek/deepseek-v4-flash":{"draws":111,"losses":56,"wins":151},"deepseek/deepseek-v4-pro":{"draws":79,"losses":79,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":73,"losses":73,"wins":86},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":50,"wins":34},"fireworks/ember-1":{"draws":44,"losses":58,"wins":36},"gemini-3.1-pro-preview":{"draws":47,"losses":47,"wins":44},"google/gemini-3.1-flash-lite":{"draws":30,"losses":10,"wins":66},"google/gemini-3.5-flash":{"draws":94,"losses":81,"wins":97},"google/gemini-3.5-flash-lite":{"draws":139,"losses":94,"wins":191},"google/gemini-3.6-flash":{"draws":123,"losses":165,"wins":112},"google/gemini-3.8-flash":{"draws":79,"losses":102,"wins":63},"google/gemma-4-31b-it":{"draws":27,"losses":9,"wins":36},"gpt-4.1":{"draws":23,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":36,"losses":36,"wins":56},"gpt-5.4":{"draws":79,"losses":111,"wins":50},"gpt-5.4-mini":{"draws":42,"losses":23,"wins":35},"gpt-5.4-nano":{"draws":27,"losses":39,"wins":76},"gpt-5.5":{"draws":48,"losses":49,"wins":31},"gpt-5.6-luna":{"draws":82,"losses":85,"wins":85},"gpt-5.6-sol":{"draws":64,"losses":147,"wins":45},"gpt-5.6-terra":{"draws":60,"losses":52,"wins":52},"gpt-6-astra":{"draws":20,"losses":216,"wins":10},"gpt-6-luna":{"draws":38,"losses":56,"wins":40},"gpt-6-sol":{"draws":24,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":78,"losses":14,"wins":82},"inclusionai/ling-3.0-flash":{"draws":42,"losses":11,"wins":77},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":66,"losses":47,"wins":103},"meta/muse-glimmer-30b":{"draws":92,"losses":31,"wins":97},"meta/muse-spark-1.2":{"draws":67,"losses":79,"wins":58},"meta/muse-spark-1.3":{"draws":51,"losses":93,"wins":60},"meta/muse-wonder":{"draws":29,"losses":70,"wins":29},"minimax/minimax-m3":{"draws":23,"losses":15,"wins":44},"mistralai/mistral-large-4-0":{"draws":30,"losses":26,"wins":18},"mistralai/mistral-medium-3-5":{"draws":48,"losses":16,"wins":80},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":12,"wins":16},"moonshotai/kimi-k3":{"draws":63,"losses":80,"wins":65},"nex-agi/nex-n2-pro":{"draws":21,"losses":8,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":60},"o3":{"draws":53,"losses":108,"wins":115},"openai/gpt-oss-120b":{"draws":82,"losses":25,"wins":115},"poolside/laguna-s-2.1":{"draws":77,"losses":21,"wins":86},"qwen/qwen3.7-max":{"draws":29,"losses":18,"wins":47},"qwen/qwen3.7-plus":{"draws":27,"losses":12,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":94,"losses":109,"wins":53},"qwen/qwen3.8-27b":{"draws":44,"losses":41,"wins":41},"qwen/qwen3.8-flash":{"draws":52,"losses":50,"wins":52},"qwen/qwen3.8-max":{"draws":106,"losses":80,"wins":66},"qwen/qwen3.8-max-0902":{"draws":46,"losses":53,"wins":37},"stealth/ox-alpha":{"draws":248,"losses":317,"wins":221},"stealth/space-bunny-alpha":{"draws":37,"losses":32,"wins":39},"stepfun/step-3.7-flash":{"draws":28,"losses":20,"wins":50},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":16,"wins":30},"tencent/hy4-preview":{"draws":61,"losses":100,"wins":65},"thinkingmachines/inkling":{"draws":61,"losses":32,"wins":103},"thinkingmachines/inkling-small":{"draws":83,"losses":42,"wins":121},"unbiased/pareto-26.10-preview":{"draws":3,"losses":35,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":25},"x-ai/grok-4.5":{"draws":60,"losses":115,"wins":53},"x-ai/grok-4.6":{"draws":82,"losses":136,"wins":44},"x-ai/grok-4.7":{"draws":13,"losses":86,"wins":21},"x-ai/grok-build-0.1":{"draws":17,"losses":7,"wins":26},"xiaomi/mimo-v2.5":{"draws":86,"losses":15,"wins":127},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":14,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":31,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":40,"wins":24},"z-ai/glm-5.2":{"draws":176,"losses":87,"wins":145},"z-ai/glm-5.3":{"draws":63,"losses":104,"wins":35},"z-ai/glm-5.3-flash":{"draws":66,"losses":104,"wins":72},"z-ai/glm-5.3-flashx":{"draws":38,"losses":63,"wins":37}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":15,"wins":153},"claude-fable-5":{"draws":19,"losses":53,"wins":204},"claude-fable-5-1":{"draws":27,"losses":111,"wins":186},"claude-haiku-5-5":{"draws":10,"losses":7,"wins":113},"claude-opus-4-5":{"draws":23,"losses":19,"wins":280},"claude-opus-4-8":{"draws":11,"losses":11,"wins":120},"claude-opus-5":{"draws":30,"losses":65,"wins":169},"claude-opus-5-5":{"draws":17,"losses":65,"wins":74},"claude-sonnet-5":{"draws":12,"losses":16,"wins":232},"claude-sonnet-5-5":{"draws":13,"losses":26,"wins":105},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":48},"deepseek/deepseek-v4-flash":{"draws":14,"losses":6,"wins":262},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":183},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":1,"wins":198},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":6,"wins":120},"fireworks/ember-1":{"draws":10,"losses":6,"wins":128},"gemini-3.1-pro-preview":{"draws":10,"losses":4,"wins":130},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":27,"losses":11,"wins":246},"google/gemini-3.5-flash-lite":{"draws":21,"losses":2,"wins":345},"google/gemini-3.6-flash":{"draws":35,"losses":29,"wins":334},"google/gemini-3.8-flash":{"draws":29,"losses":18,"wins":227},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":70},"gpt-4.1":{"draws":5,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":2,"wins":115},"gpt-5.4":{"draws":18,"losses":31,"wins":201},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":141},"gpt-5.5":{"draws":5,"losses":10,"wins":119},"gpt-5.6-luna":{"draws":25,"losses":2,"wins":177},"gpt-5.6-sol":{"draws":29,"losses":27,"wins":226},"gpt-5.6-terra":{"draws":20,"losses":10,"wins":216},"gpt-6-astra":{"draws":18,"losses":87,"wins":87},"gpt-6-luna":{"draws":16,"losses":8,"wins":116},"gpt-6-sol":{"draws":15,"losses":26,"wins":103},"gpt-6.1-sol":{"draws":18,"losses":49,"wins":77},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":112},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":101},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":170},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":146},"meta/muse-spark-1.2":{"draws":12,"losses":5,"wins":179},"meta/muse-spark-1.3":{"draws":22,"losses":15,"wins":163},"meta/muse-wonder":{"draws":14,"losses":15,"wins":105},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":77},"mistralai/mistral-large-4-0":{"draws":9,"losses":5,"wins":66},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":87},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":34},"moonshotai/kimi-k3":{"draws":17,"losses":18,"wins":179},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":68},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":116},"o3":{"draws":8,"losses":2,"wins":262},"openai/gpt-oss-120b":{"draws":13,"losses":0,"wins":145},"poolside/laguna-s-2.1":{"draws":18,"losses":0,"wins":156},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":78},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":13,"wins":227},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":129},"qwen/qwen3.8-flash":{"draws":22,"losses":5,"wins":131},"qwen/qwen3.8-max":{"draws":26,"losses":4,"wins":210},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":127},"stealth/ox-alpha":{"draws":93,"losses":44,"wins":703},"stealth/space-bunny-alpha":{"draws":6,"losses":0,"wins":108},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":90},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":0,"wins":67},"tencent/hy4-preview":{"draws":20,"losses":14,"wins":210},"thinkingmachines/inkling":{"draws":9,"losses":2,"wins":171},"thinkingmachines/inkling-small":{"draws":15,"losses":0,"wins":187},"unbiased/pareto-26.10-preview":{"draws":6,"losses":19,"wins":21},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":10,"losses":22,"wins":184},"x-ai/grok-4.6":{"draws":22,"losses":28,"wins":224},"x-ai/grok-4.7":{"draws":12,"losses":22,"wins":92},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":209},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":80},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":81},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":27,"losses":13,"wins":312},"z-ai/glm-5.3":{"draws":34,"losses":14,"wins":172},"z-ai/glm-5.3-flash":{"draws":32,"losses":15,"wins":209},"z-ai/glm-5.3-flashx":{"draws":14,"losses":9,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":35,"wins":54},"claude-fable-5":{"draws":31,"losses":79,"wins":28},"claude-fable-5-1":{"draws":10,"losses":142,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":60,"wins":39},"claude-opus-4-5":{"draws":77,"losses":74,"wins":75},"claude-opus-4-8":{"draws":33,"losses":59,"wins":36},"claude-opus-5":{"draws":47,"losses":171,"wins":20},"claude-opus-5-5":{"draws":16,"losses":131,"wins":1},"claude-sonnet-5":{"draws":36,"losses":48,"wins":56},"claude-sonnet-5-5":{"draws":32,"losses":66,"wins":42},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":30},"deepseek/deepseek-v4-flash":{"draws":66,"losses":40,"wins":102},"deepseek/deepseek-v4-pro":{"draws":33,"losses":41,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":44,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":58,"wins":38},"fireworks/ember-1":{"draws":38,"losses":61,"wins":41},"gemini-3.1-pro-preview":{"draws":36,"losses":60,"wins":46},"google/gemini-3.1-flash-lite":{"draws":21,"losses":11,"wins":60},"google/gemini-3.5-flash":{"draws":49,"losses":69,"wins":58},"google/gemini-3.5-flash-lite":{"draws":81,"losses":55,"wins":114},"google/gemini-3.6-flash":{"draws":69,"losses":114,"wins":61},"google/gemini-3.8-flash":{"draws":42,"losses":67,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":36},"gpt-4.1":{"draws":11,"losses":17,"wins":18},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":39,"losses":42,"wins":45},"gpt-5.4":{"draws":42,"losses":59,"wins":33},"gpt-5.4-mini":{"draws":43,"losses":13,"wins":40},"gpt-5.4-nano":{"draws":28,"losses":40,"wins":70},"gpt-5.5":{"draws":50,"losses":49,"wins":27},"gpt-5.6-luna":{"draws":48,"losses":38,"wins":58},"gpt-5.6-sol":{"draws":30,"losses":86,"wins":22},"gpt-5.6-terra":{"draws":38,"losses":40,"wins":56},"gpt-6-astra":{"draws":16,"losses":116,"wins":8},"gpt-6-luna":{"draws":20,"losses":34,"wins":34},"gpt-6-sol":{"draws":24,"losses":95,"wins":19},"gpt-6.1-sol":{"draws":13,"losses":121,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":39,"losses":9,"wins":52},"inclusionai/ling-3.0-flash":{"draws":33,"losses":13,"wins":52},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":35,"losses":32,"wins":82},"meta/muse-glimmer-30b":{"draws":41,"losses":18,"wins":62},"meta/muse-spark-1.2":{"draws":40,"losses":56,"wins":36},"meta/muse-spark-1.3":{"draws":23,"losses":79,"wins":36},"meta/muse-wonder":{"draws":33,"losses":76,"wins":29},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":42},"mistralai/mistral-large-4-0":{"draws":25,"losses":31,"wins":30},"mistralai/mistral-medium-3-5":{"draws":28,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":10,"wins":14},"moonshotai/kimi-k3":{"draws":43,"losses":50,"wins":39},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":25,"wins":59},"o3":{"draws":29,"losses":59,"wins":98},"openai/gpt-oss-120b":{"draws":37,"losses":25,"wins":58},"poolside/laguna-s-2.1":{"draws":37,"losses":34,"wins":59},"qwen/qwen3.7-max":{"draws":18,"losses":27,"wins":35},"qwen/qwen3.7-plus":{"draws":23,"losses":12,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":54,"wins":48},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":41},"qwen/qwen3.8-flash":{"draws":26,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":36,"losses":52,"wins":50},"qwen/qwen3.8-max-0902":{"draws":38,"losses":54,"wins":44},"stealth/ox-alpha":{"draws":109,"losses":202,"wins":151},"stealth/space-bunny-alpha":{"draws":37,"losses":23,"wins":50},"stepfun/step-3.7-flash":{"draws":18,"losses":23,"wins":55},"stepfun/step-5-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":38,"losses":64,"wins":34},"thinkingmachines/inkling":{"draws":50,"losses":27,"wins":83},"thinkingmachines/inkling-small":{"draws":34,"losses":32,"wins":72},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":35,"losses":62,"wins":43},"x-ai/grok-4.6":{"draws":36,"losses":79,"wins":23},"x-ai/grok-4.7":{"draws":10,"losses":90,"wins":20},"x-ai/grok-build-0.1":{"draws":20,"losses":4,"wins":24},"xiaomi/mimo-v2.5":{"draws":80,"losses":29,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":18,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":48,"wins":27},"z-ai/glm-5.2":{"draws":101,"losses":72,"wins":111},"z-ai/glm-5.3":{"draws":26,"losses":79,"wins":25},"z-ai/glm-5.3-flash":{"draws":39,"losses":70,"wins":33},"z-ai/glm-5.3-flashx":{"draws":30,"losses":72,"wins":40}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":102},"claude-fable-5":{"draws":19,"losses":43,"wins":82},"claude-fable-5-1":{"draws":14,"losses":110,"wins":38},"claude-haiku-5-5":{"draws":27,"losses":24,"wins":77},"claude-opus-4-5":{"draws":36,"losses":28,"wins":170},"claude-opus-4-8":{"draws":20,"losses":32,"wins":80},"claude-opus-5":{"draws":33,"losses":120,"wins":93},"claude-opus-5-5":{"draws":13,"losses":104,"wins":39},"claude-sonnet-5":{"draws":24,"losses":19,"wins":101},"claude-sonnet-5-5":{"draws":15,"losses":48,"wins":81},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":43},"deepseek/deepseek-v4-flash":{"draws":32,"losses":16,"wins":168},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":97},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":33,"wins":85},"fireworks/ember-1":{"draws":21,"losses":23,"wins":100},"gemini-3.1-pro-preview":{"draws":19,"losses":26,"wins":99},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":82},"google/gemini-3.5-flash":{"draws":27,"losses":26,"wins":127},"google/gemini-3.5-flash-lite":{"draws":39,"losses":22,"wins":191},"google/gemini-3.6-flash":{"draws":30,"losses":57,"wins":165},"google/gemini-3.8-flash":{"draws":22,"losses":33,"wins":89},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":65},"gpt-4.1":{"draws":7,"losses":7,"wins":34},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":15,"losses":16,"wins":95},"gpt-5.4":{"draws":15,"losses":22,"wins":99},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":72},"gpt-5.4-nano":{"draws":19,"losses":12,"wins":113},"gpt-5.5":{"draws":20,"losses":29,"wins":83},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":106},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":85},"gpt-5.6-terra":{"draws":24,"losses":16,"wins":98},"gpt-6-astra":{"draws":15,"losses":103,"wins":26},"gpt-6-luna":{"draws":24,"losses":19,"wins":95},"gpt-6-sol":{"draws":14,"losses":41,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":91,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":82},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":75},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":131},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":97},"meta/muse-spark-1.2":{"draws":18,"losses":23,"wins":93},"meta/muse-spark-1.3":{"draws":23,"losses":21,"wins":94},"meta/muse-wonder":{"draws":18,"losses":45,"wins":73},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"mistralai/mistral-large-4-0":{"draws":15,"losses":14,"wins":55},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":28},"moonshotai/kimi-k3":{"draws":14,"losses":24,"wins":96},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":106},"o3":{"draws":10,"losses":16,"wins":166},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":101},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":58},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":32,"wins":93},"qwen/qwen3.8-27b":{"draws":17,"losses":14,"wins":71},"qwen/qwen3.8-flash":{"draws":9,"losses":18,"wins":69},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":99},"qwen/qwen3.8-max-0902":{"draws":16,"losses":28,"wins":96},"stealth/ox-alpha":{"draws":62,"losses":72,"wins":334},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":87},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":81},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":58},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":92},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":132},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":118},"unbiased/pareto-26.10-preview":{"draws":5,"losses":32,"wins":7},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":21,"losses":30,"wins":93},"x-ai/grok-4.6":{"draws":21,"losses":30,"wins":93},"x-ai/grok-4.7":{"draws":13,"losses":63,"wins":50},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":38},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":170},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":63},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":18,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":23,"wins":53},"z-ai/glm-5.2":{"draws":45,"losses":31,"wins":212},"z-ai/glm-5.3":{"draws":21,"losses":43,"wins":70},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":20,"losses":37,"wins":87}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":114},"claude-fable-5":{"draws":11,"losses":32,"wins":101},"claude-fable-5-1":{"draws":13,"losses":72,"wins":77},"claude-haiku-5-5":{"draws":15,"losses":10,"wins":105},"claude-opus-4-5":{"draws":20,"losses":16,"wins":198},"claude-opus-4-8":{"draws":7,"losses":15,"wins":110},"claude-opus-5":{"draws":30,"losses":76,"wins":140},"claude-opus-5-5":{"draws":18,"losses":75,"wins":63},"claude-sonnet-5":{"draws":6,"losses":9,"wins":129},"claude-sonnet-5-5":{"draws":5,"losses":36,"wins":103},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":50},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":197},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":115},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":121},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":115},"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":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":12,"losses":17,"wins":151},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":235},"google/gemini-3.6-flash":{"draws":13,"losses":27,"wins":212},"google/gemini-3.8-flash":{"draws":20,"losses":18,"wins":106},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":72},"gpt-4.1":{"draws":4,"losses":1,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":17},"gpt-5":{"draws":6,"losses":5,"wins":115},"gpt-5.4":{"draws":9,"losses":20,"wins":109},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":87},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":132},"gpt-5.5":{"draws":8,"losses":21,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":13,"losses":21,"wins":110},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":122},"gpt-6-astra":{"draws":18,"losses":77,"wins":49},"gpt-6-luna":{"draws":13,"losses":6,"wins":121},"gpt-6-sol":{"draws":17,"losses":36,"wins":91},"gpt-6.1-sol":{"draws":6,"losses":45,"wins":45},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":93},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":96},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":140},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":117},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":107},"meta/muse-spark-1.3":{"draws":14,"losses":11,"wins":113},"meta/muse-wonder":{"draws":19,"losses":26,"wins":89},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":64},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":31},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":108},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":68},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":112},"o3":{"draws":3,"losses":9,"wins":186},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":118},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":128},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":75},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":113},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":82},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":124},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":119},"stealth/ox-alpha":{"draws":43,"losses":30,"wins":395},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":97},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":118},"thinkingmachines/inkling":{"draws":12,"losses":6,"wins":144},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10-preview":{"draws":2,"losses":23,"wins":17},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":118},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":114},"x-ai/grok-4.7":{"draws":6,"losses":41,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":195},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":70},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":15,"wins":61},"z-ai/glm-5.2":{"draws":30,"losses":12,"wins":246},"z-ai/glm-5.3":{"draws":22,"losses":21,"wins":91},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":115},"z-ai/glm-5.3-flashx":{"draws":19,"losses":18,"wins":107}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":57,"wins":47},"claude-fable-5":{"draws":45,"losses":88,"wins":7},"claude-fable-5-1":{"draws":11,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":26,"losses":64,"wins":4},"claude-opus-4-5":{"draws":90,"losses":120,"wins":12},"claude-opus-4-8":{"draws":32,"losses":57,"wins":11},"claude-opus-5":{"draws":31,"losses":129,"wins":6},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":73,"losses":94,"wins":17},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":16,"wins":16},"deepseek/deepseek-v4-flash":{"draws":105,"losses":98,"wins":33},"deepseek/deepseek-v4-pro":{"draws":70,"losses":73,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":63,"losses":79,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":48,"wins":9},"fireworks/ember-1":{"draws":44,"losses":52,"wins":6},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":22},"google/gemini-3.1-flash-lite":{"draws":29,"losses":19,"wins":28},"google/gemini-3.5-flash":{"draws":73,"losses":98,"wins":21},"google/gemini-3.5-flash-lite":{"draws":151,"losses":136,"wins":61},"google/gemini-3.6-flash":{"draws":108,"losses":151,"wins":25},"google/gemini-3.8-flash":{"draws":60,"losses":92,"wins":6},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":16},"gpt-4.1":{"draws":15,"losses":13,"wins":14},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":35,"losses":41,"wins":10},"gpt-5.4":{"draws":74,"losses":61,"wins":3},"gpt-5.4-mini":{"draws":34,"losses":23,"wins":15},"gpt-5.4-nano":{"draws":34,"losses":58,"wins":18},"gpt-5.5":{"draws":40,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":94,"losses":61,"wins":33},"gpt-5.6-sol":{"draws":33,"losses":116,"wins":1},"gpt-5.6-terra":{"draws":78,"losses":82,"wins":14},"gpt-6-astra":{"draws":12,"losses":112,"wins":0},"gpt-6-luna":{"draws":39,"losses":52,"wins":9},"gpt-6-sol":{"draws":16,"losses":82,"wins":4},"gpt-6.1-sol":{"draws":9,"losses":93,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":56,"losses":20,"wins":20},"inclusionai/ling-3.0-flash":{"draws":49,"losses":30,"wins":23},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":63,"losses":60,"wins":37},"meta/muse-glimmer-30b":{"draws":87,"losses":47,"wins":34},"meta/muse-spark-1.2":{"draws":54,"losses":76,"wins":16},"meta/muse-spark-1.3":{"draws":47,"losses":85,"wins":14},"meta/muse-wonder":{"draws":25,"losses":65,"wins":4},"minimax/minimax-m3":{"draws":26,"losses":21,"wins":13},"mistralai/mistral-large-4-0":{"draws":23,"losses":26,"wins":9},"mistralai/mistral-medium-3-5":{"draws":57,"losses":32,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":20,"wins":2},"moonshotai/kimi-k3":{"draws":66,"losses":72,"wins":14},"nex-agi/nex-n2-pro":{"draws":22,"losses":19,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":29,"wins":25},"o3":{"draws":44,"losses":133,"wins":23},"openai/gpt-oss-120b":{"draws":75,"losses":55,"wins":38},"poolside/laguna-s-2.1":{"draws":64,"losses":40,"wins":34},"qwen/qwen3.7-max":{"draws":29,"losses":26,"wins":15},"qwen/qwen3.7-plus":{"draws":22,"losses":28,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":84,"wins":13},"qwen/qwen3.8-27b":{"draws":23,"losses":55,"wins":8},"qwen/qwen3.8-flash":{"draws":60,"losses":52,"wins":12},"qwen/qwen3.8-max":{"draws":80,"losses":78,"wins":16},"qwen/qwen3.8-max-0902":{"draws":40,"losses":48,"wins":10},"stealth/ox-alpha":{"draws":170,"losses":271,"wins":62},"stealth/space-bunny-alpha":{"draws":37,"losses":35,"wins":10},"stepfun/step-3.7-flash":{"draws":26,"losses":40,"wins":8},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":17,"wins":15},"tencent/hy4-preview":{"draws":71,"losses":78,"wins":15},"thinkingmachines/inkling":{"draws":65,"losses":45,"wins":38},"thinkingmachines/inkling-small":{"draws":95,"losses":63,"wins":44},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":56,"losses":91,"wins":7},"x-ai/grok-4.6":{"draws":52,"losses":89,"wins":17},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":20,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":81,"losses":66,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":27,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":41,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":46,"wins":1},"z-ai/glm-5.2":{"draws":126,"losses":135,"wins":31},"z-ai/glm-5.3":{"draws":48,"losses":79,"wins":7},"z-ai/glm-5.3-flash":{"draws":56,"losses":87,"wins":17},"z-ai/glm-5.3-flashx":{"draws":29,"losses":68,"wins":5}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":52,"losses":52,"wins":22},"claude-fable-5":{"draws":22,"losses":85,"wins":5},"claude-fable-5-1":{"draws":7,"losses":113,"wins":0},"claude-haiku-5-5":{"draws":26,"losses":57,"wins":5},"claude-opus-4-5":{"draws":95,"losses":121,"wins":40},"claude-opus-4-8":{"draws":57,"losses":81,"wins":0},"claude-opus-5":{"draws":46,"losses":157,"wins":11},"claude-opus-5-5":{"draws":7,"losses":102,"wins":0},"claude-sonnet-5":{"draws":58,"losses":98,"wins":18},"claude-sonnet-5-5":{"draws":26,"losses":65,"wins":7},"cohere/north-mini-code":{"draws":24,"losses":14,"wins":24},"deepseek/deepseek-v4-flash":{"draws":96,"losses":81,"wins":57},"deepseek/deepseek-v4-pro":{"draws":40,"losses":59,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":48,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":49,"wins":9},"fireworks/ember-1":{"draws":42,"losses":50,"wins":4},"gemini-3.1-pro-preview":{"draws":35,"losses":53,"wins":10},"google/gemini-3.1-flash-lite":{"draws":40,"losses":39,"wins":33},"google/gemini-3.5-flash":{"draws":52,"losses":92,"wins":16},"google/gemini-3.5-flash-lite":{"draws":150,"losses":181,"wins":69},"google/gemini-3.6-flash":{"draws":166,"losses":180,"wins":52},"google/gemini-3.8-flash":{"draws":31,"losses":82,"wins":3},"google/gemma-4-31b-it":{"draws":26,"losses":13,"wins":13},"gpt-4.1":{"draws":28,"losses":34,"wins":1},"gpt-4.1-nano":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":45,"losses":45,"wins":38},"gpt-5.4":{"draws":38,"losses":84,"wins":24},"gpt-5.4-mini":{"draws":59,"losses":42,"wins":19},"gpt-5.4-nano":{"draws":63,"losses":72,"wins":37},"gpt-5.5":{"draws":78,"losses":60,"wins":12},"gpt-5.6-luna":{"draws":64,"losses":57,"wins":43},"gpt-5.6-sol":{"draws":22,"losses":124,"wins":10},"gpt-5.6-terra":{"draws":42,"losses":77,"wins":11},"gpt-6-astra":{"draws":6,"losses":101,"wins":1},"gpt-6-luna":{"draws":33,"losses":52,"wins":13},"gpt-6-sol":{"draws":15,"losses":75,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":96,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":49,"losses":23,"wins":30},"inclusionai/ling-3.0-flash":{"draws":40,"losses":40,"wins":40},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":111,"losses":96,"wins":63},"meta/muse-glimmer-30b":{"draws":61,"losses":37,"wins":20},"meta/muse-spark-1.2":{"draws":44,"losses":67,"wins":21},"meta/muse-spark-1.3":{"draws":20,"losses":81,"wins":13},"meta/muse-wonder":{"draws":18,"losses":75,"wins":5},"minimax/minimax-m3":{"draws":52,"losses":45,"wins":23},"mistralai/mistral-large-4-0":{"draws":22,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":32,"losses":31,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":22,"wins":8},"moonshotai/kimi-k3":{"draws":64,"losses":86,"wins":26},"nex-agi/nex-n2-pro":{"draws":50,"losses":30,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":70,"losses":38,"wins":32},"o3":{"draws":35,"losses":150,"wins":35},"openai/gpt-oss-120b":{"draws":49,"losses":55,"wins":14},"poolside/laguna-s-2.1":{"draws":102,"losses":76,"wins":30},"qwen/qwen3.7-max":{"draws":56,"losses":43,"wins":13},"qwen/qwen3.7-plus":{"draws":42,"losses":31,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":75,"wins":7},"qwen/qwen3.8-27b":{"draws":15,"losses":54,"wins":13},"qwen/qwen3.8-flash":{"draws":35,"losses":50,"wins":11},"qwen/qwen3.8-max":{"draws":54,"losses":62,"wins":21},"qwen/qwen3.8-max-0902":{"draws":35,"losses":52,"wins":9},"stealth/ox-alpha":{"draws":105,"losses":246,"wins":39},"stealth/space-bunny-alpha":{"draws":34,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":28,"losses":36,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":35,"losses":42,"wins":11},"tencent/hy4-preview":{"draws":39,"losses":74,"wins":9},"thinkingmachines/inkling":{"draws":89,"losses":74,"wins":55},"thinkingmachines/inkling-small":{"draws":59,"losses":50,"wins":28},"unbiased/pareto-26.10-preview":{"draws":2,"losses":30,"wins":0},"upstage/solar-mini4":{"draws":10,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":62,"losses":143,"wins":19},"x-ai/grok-4.6":{"draws":42,"losses":71,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":73,"wins":5},"x-ai/grok-build-0.1":{"draws":24,"losses":36,"wins":4},"xiaomi/mimo-v2.5":{"draws":112,"losses":90,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":35,"losses":49,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":41,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":47,"wins":5},"z-ai/glm-5.2":{"draws":139,"losses":94,"wins":41},"z-ai/glm-5.3":{"draws":28,"losses":77,"wins":3},"z-ai/glm-5.3-flash":{"draws":34,"losses":71,"wins":9},"z-ai/glm-5.3-flashx":{"draws":31,"losses":59,"wins":8}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":0,"wins":0},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":0,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":0},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":3,"losses":0,"wins":1},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":3,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":6,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":4,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":0,"losses":2,"wins":0},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":1},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":0,"wins":0}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":63,"losses":81,"wins":54},"claude-fable-5":{"draws":34,"losses":128,"wins":30},"claude-fable-5-1":{"draws":5,"losses":188,"wins":6},"claude-haiku-5-5":{"draws":25,"losses":89,"wins":18},"claude-opus-4-5":{"draws":122,"losses":245,"wins":78},"claude-opus-4-8":{"draws":42,"losses":112,"wins":31},"claude-opus-5":{"draws":44,"losses":286,"wins":36},"claude-opus-5-5":{"draws":11,"losses":154,"wins":7},"claude-sonnet-5":{"draws":87,"losses":155,"wins":40},"claude-sonnet-5-5":{"draws":21,"losses":104,"wins":31},"cohere/north-mini-code":{"draws":23,"losses":18,"wins":49},"deepseek/deepseek-v4-flash":{"draws":103,"losses":129,"wins":98},"deepseek/deepseek-v4-pro":{"draws":54,"losses":110,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":75,"losses":90,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":85,"wins":34},"fireworks/ember-1":{"draws":49,"losses":87,"wins":19},"gemini-3.1-pro-preview":{"draws":37,"losses":73,"wins":44},"google/gemini-3.1-flash-lite":{"draws":37,"losses":48,"wins":96},"google/gemini-3.5-flash":{"draws":61,"losses":149,"wins":44},"google/gemini-3.5-flash-lite":{"draws":173,"losses":257,"wins":213},"google/gemini-3.6-flash":{"draws":165,"losses":348,"wins":99},"google/gemini-3.8-flash":{"draws":43,"losses":126,"wins":22},"google/gemma-4-31b-it":{"draws":25,"losses":24,"wins":31},"gpt-4.1":{"draws":26,"losses":42,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":66,"losses":95,"wins":47},"gpt-5.4":{"draws":76,"losses":151,"wins":35},"gpt-5.4-mini":{"draws":71,"losses":61,"wins":44},"gpt-5.4-nano":{"draws":52,"losses":133,"wins":83},"gpt-5.5":{"draws":87,"losses":92,"wins":42},"gpt-5.6-luna":{"draws":85,"losses":119,"wins":82},"gpt-5.6-sol":{"draws":43,"losses":204,"wins":27},"gpt-5.6-terra":{"draws":66,"losses":103,"wins":47},"gpt-6-astra":{"draws":10,"losses":170,"wins":4},"gpt-6-luna":{"draws":35,"losses":82,"wins":32},"gpt-6-sol":{"draws":11,"losses":131,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":140,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":63,"losses":37,"wins":60},"inclusionai/ling-3.0-flash":{"draws":111,"losses":63,"wins":96},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":82,"losses":74,"wins":74},"meta/muse-glimmer-30b":{"draws":71,"losses":66,"wins":53},"meta/muse-spark-1.2":{"draws":53,"losses":118,"wins":55},"meta/muse-spark-1.3":{"draws":42,"losses":116,"wins":25},"meta/muse-wonder":{"draws":26,"losses":98,"wins":16},"minimax/minimax-m3":{"draws":30,"losses":48,"wins":56},"mistralai/mistral-large-4-0":{"draws":26,"losses":40,"wins":14},"mistralai/mistral-medium-3-5":{"draws":54,"losses":33,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":34,"wins":9},"moonshotai/kimi-k3":{"draws":92,"losses":151,"wins":45},"nex-agi/nex-n2-pro":{"draws":34,"losses":41,"wins":65},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":84,"losses":64,"wins":56},"o3":{"draws":56,"losses":247,"wins":103},"openai/gpt-oss-120b":{"draws":68,"losses":45,"wins":73},"poolside/laguna-s-2.1":{"draws":128,"losses":105,"wins":99},"qwen/qwen3.7-max":{"draws":53,"losses":68,"wins":24},"qwen/qwen3.7-plus":{"draws":32,"losses":43,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":122,"wins":30},"qwen/qwen3.8-27b":{"draws":23,"losses":78,"wins":21},"qwen/qwen3.8-flash":{"draws":56,"losses":60,"wins":28},"qwen/qwen3.8-max":{"draws":70,"losses":108,"wins":39},"qwen/qwen3.8-max-0902":{"draws":29,"losses":95,"wins":23},"stealth/ox-alpha":{"draws":160,"losses":401,"wins":95},"stealth/space-bunny-alpha":{"draws":40,"losses":56,"wins":29},"stepfun/step-3.7-flash":{"draws":31,"losses":53,"wins":44},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":47,"losses":46,"wins":39},"tencent/hy4-preview":{"draws":55,"losses":116,"wins":27},"thinkingmachines/inkling":{"draws":80,"losses":123,"wins":105},"thinkingmachines/inkling-small":{"draws":69,"losses":68,"wins":81},"unbiased/pareto-26.10-preview":{"draws":1,"losses":42,"wins":1},"upstage/solar-mini4":{"draws":7,"losses":16,"wins":17},"x-ai/grok-4.5":{"draws":75,"losses":220,"wins":59},"x-ai/grok-4.6":{"draws":61,"losses":116,"wins":30},"x-ai/grok-4.7":{"draws":8,"losses":120,"wins":8},"x-ai/grok-build-0.1":{"draws":31,"losses":31,"wins":28},"xiaomi/mimo-v2.5":{"draws":128,"losses":115,"wins":132},"xiaomi/mimo-v2.5-pro":{"draws":45,"losses":65,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":54,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":72,"wins":9},"z-ai/glm-5.2":{"draws":137,"losses":195,"wins":110},"z-ai/glm-5.3":{"draws":38,"losses":120,"wins":16},"z-ai/glm-5.3-flash":{"draws":49,"losses":114,"wins":41},"z-ai/glm-5.3-flashx":{"draws":36,"losses":100,"wins":19}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":92,"losses":68,"wins":64},"claude-fable-5":{"draws":48,"losses":120,"wins":14},"claude-fable-5-1":{"draws":13,"losses":161,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":62,"wins":15},"claude-opus-4-5":{"draws":96,"losses":132,"wins":38},"claude-opus-4-8":{"draws":34,"losses":69,"wins":17},"claude-opus-5":{"draws":14,"losses":195,"wins":23},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":81,"losses":110,"wins":35},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":20,"losses":12,"wins":20},"deepseek/deepseek-v4-flash":{"draws":141,"losses":86,"wins":63},"deepseek/deepseek-v4-pro":{"draws":77,"losses":90,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":82,"losses":95,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":60,"wins":14},"fireworks/ember-1":{"draws":44,"losses":67,"wins":15},"gemini-3.1-pro-preview":{"draws":49,"losses":62,"wins":15},"google/gemini-3.1-flash-lite":{"draws":39,"losses":19,"wins":34},"google/gemini-3.5-flash":{"draws":82,"losses":118,"wins":44},"google/gemini-3.5-flash-lite":{"draws":180,"losses":149,"wins":97},"google/gemini-3.6-flash":{"draws":141,"losses":190,"wins":51},"google/gemini-3.8-flash":{"draws":61,"losses":112,"wins":25},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":17},"gpt-4.1":{"draws":19,"losses":16,"wins":11},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":46,"losses":54,"wins":26},"gpt-5.4":{"draws":68,"losses":98,"wins":30},"gpt-5.4-mini":{"draws":43,"losses":30,"wins":11},"gpt-5.4-nano":{"draws":31,"losses":50,"wins":43},"gpt-5.5":{"draws":54,"losses":60,"wins":18},"gpt-5.6-luna":{"draws":103,"losses":74,"wins":61},"gpt-5.6-sol":{"draws":31,"losses":129,"wins":14},"gpt-5.6-terra":{"draws":92,"losses":97,"wins":31},"gpt-6-astra":{"draws":8,"losses":146,"wins":0},"gpt-6-luna":{"draws":41,"losses":62,"wins":18},"gpt-6-sol":{"draws":19,"losses":97,"wins":10},"gpt-6.1-sol":{"draws":8,"losses":117,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":87,"losses":34,"wins":47},"inclusionai/ling-3.0-flash":{"draws":61,"losses":20,"wins":37},"meituan/longcat-2.0":{"draws":71,"losses":53,"wins":66},"meta/muse-glimmer-30b":{"draws":74,"losses":35,"wins":35},"meta/muse-spark-1.2":{"draws":48,"losses":95,"wins":33},"meta/muse-spark-1.3":{"draws":62,"losses":89,"wins":25},"meta/muse-wonder":{"draws":25,"losses":78,"wins":15},"minimax/minimax-m3":{"draws":28,"losses":28,"wins":22},"mistralai/mistral-large-4-0":{"draws":24,"losses":33,"wins":19},"mistralai/mistral-medium-3-5":{"draws":70,"losses":20,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":19,"wins":10},"moonshotai/kimi-k3":{"draws":54,"losses":92,"wins":30},"nex-agi/nex-n2-pro":{"draws":27,"losses":14,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":27,"wins":30},"o3":{"draws":51,"losses":148,"wins":43},"openai/gpt-oss-120b":{"draws":96,"losses":63,"wins":53},"poolside/laguna-s-2.1":{"draws":90,"losses":59,"wins":43},"qwen/qwen3.7-max":{"draws":30,"losses":29,"wins":19},"qwen/qwen3.7-plus":{"draws":29,"losses":16,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":87,"losses":98,"wins":27},"qwen/qwen3.8-27b":{"draws":30,"losses":60,"wins":14},"qwen/qwen3.8-flash":{"draws":67,"losses":38,"wins":39},"qwen/qwen3.8-max":{"draws":69,"losses":90,"wins":47},"qwen/qwen3.8-max-0902":{"draws":46,"losses":66,"wins":12},"stealth/ox-alpha":{"draws":191,"losses":393,"wins":102},"stealth/space-bunny-alpha":{"draws":39,"losses":36,"wins":27},"stepfun/step-3.7-flash":{"draws":22,"losses":27,"wins":41},"tencent/hy3-preview":{"draws":30,"losses":30,"wins":12},"tencent/hy4-preview":{"draws":81,"losses":105,"wins":20},"thinkingmachines/inkling":{"draws":73,"losses":52,"wins":71},"thinkingmachines/inkling-small":{"draws":115,"losses":46,"wins":83},"unbiased/pareto-26.10-preview":{"draws":0,"losses":38,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":9},"x-ai/grok-4.5":{"draws":51,"losses":107,"wins":24},"x-ai/grok-4.6":{"draws":69,"losses":107,"wins":20},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":13},"x-ai/grok-build-0.1":{"draws":18,"losses":16,"wins":10},"xiaomi/mimo-v2.5":{"draws":85,"losses":50,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":31,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":43,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":52,"wins":13},"z-ai/glm-5.2":{"draws":167,"losses":128,"wins":63},"z-ai/glm-5.3":{"draws":37,"losses":107,"wins":20},"z-ai/glm-5.3-flash":{"draws":67,"losses":116,"wins":23},"z-ai/glm-5.3-flashx":{"draws":36,"losses":71,"wins":19}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":52,"losses":51,"wins":81},"claude-fable-5":{"draws":34,"losses":118,"wins":48},"claude-fable-5-1":{"draws":13,"losses":200,"wins":11},"claude-haiku-5-5":{"draws":26,"losses":65,"wins":39},"claude-opus-4-5":{"draws":90,"losses":98,"wins":150},"claude-opus-4-8":{"draws":31,"losses":60,"wins":43},"claude-opus-5":{"draws":32,"losses":186,"wins":34},"claude-opus-5-5":{"draws":12,"losses":127,"wins":7},"claude-sonnet-5":{"draws":93,"losses":92,"wins":113},"claude-sonnet-5-5":{"draws":27,"losses":66,"wins":41},"cohere/north-mini-code":{"draws":3,"losses":12,"wins":39},"deepseek/deepseek-v4-flash":{"draws":71,"losses":51,"wins":134},"deepseek/deepseek-v4-pro":{"draws":33,"losses":73,"wins":80},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":62,"wins":71},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":53,"wins":47},"fireworks/ember-1":{"draws":37,"losses":52,"wins":45},"gemini-3.1-pro-preview":{"draws":34,"losses":46,"wins":52},"google/gemini-3.1-flash-lite":{"draws":24,"losses":10,"wins":66},"google/gemini-3.5-flash":{"draws":54,"losses":88,"wins":92},"google/gemini-3.5-flash-lite":{"draws":134,"losses":107,"wins":267},"google/gemini-3.6-flash":{"draws":94,"losses":191,"wins":205},"google/gemini-3.8-flash":{"draws":39,"losses":84,"wins":81},"google/gemma-4-31b-it":{"draws":23,"losses":17,"wins":34},"gpt-4.1":{"draws":17,"losses":10,"wins":23},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":34,"losses":35,"wins":63},"gpt-5.4":{"draws":63,"losses":123,"wins":94},"gpt-5.4-mini":{"draws":27,"losses":22,"wins":47},"gpt-5.4-nano":{"draws":21,"losses":42,"wins":69},"gpt-5.5":{"draws":29,"losses":63,"wins":42},"gpt-5.6-luna":{"draws":80,"losses":78,"wins":136},"gpt-5.6-sol":{"draws":37,"losses":193,"wins":72},"gpt-5.6-terra":{"draws":67,"losses":58,"wins":79},"gpt-6-astra":{"draws":12,"losses":179,"wins":5},"gpt-6-luna":{"draws":40,"losses":36,"wins":56},"gpt-6-sol":{"draws":18,"losses":93,"wins":23},"gpt-6.1-sol":{"draws":9,"losses":107,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":54,"losses":16,"wins":76},"inclusionai/ling-3.0-flash":{"draws":44,"losses":21,"wins":67},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":53,"losses":55,"wins":118},"meta/muse-glimmer-30b":{"draws":48,"losses":33,"wins":95},"meta/muse-spark-1.2":{"draws":36,"losses":50,"wins":50},"meta/muse-spark-1.3":{"draws":38,"losses":73,"wins":63},"meta/muse-wonder":{"draws":26,"losses":68,"wins":40},"minimax/minimax-m3":{"draws":18,"losses":11,"wins":57},"mistralai/mistral-large-4-0":{"draws":15,"losses":24,"wins":41},"mistralai/mistral-medium-3-5":{"draws":33,"losses":18,"wins":69},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":15,"wins":16},"moonshotai/kimi-k3":{"draws":53,"losses":98,"wins":87},"nex-agi/nex-n2-pro":{"draws":13,"losses":13,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":19,"wins":68},"o3":{"draws":34,"losses":146,"wins":132},"openai/gpt-oss-120b":{"draws":54,"losses":22,"wins":102},"poolside/laguna-s-2.1":{"draws":58,"losses":31,"wins":129},"qwen/qwen3.7-max":{"draws":11,"losses":20,"wins":59},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":55,"losses":83,"wins":64},"qwen/qwen3.8-27b":{"draws":24,"losses":51,"wins":39},"qwen/qwen3.8-flash":{"draws":40,"losses":44,"wins":56},"qwen/qwen3.8-max":{"draws":58,"losses":82,"wins":65},"qwen/qwen3.8-max-0902":{"draws":29,"losses":54,"wins":49},"stealth/ox-alpha":{"draws":162,"losses":309,"wins":204},"stealth/space-bunny-alpha":{"draws":31,"losses":26,"wins":51},"stepfun/step-3.7-flash":{"draws":15,"losses":23,"wins":58},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":23,"losses":16,"wins":45},"tencent/hy4-preview":{"draws":35,"losses":90,"wins":71},"thinkingmachines/inkling":{"draws":72,"losses":34,"wins":116},"thinkingmachines/inkling-small":{"draws":63,"losses":43,"wins":102},"unbiased/pareto-26.10-preview":{"draws":0,"losses":40,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":22},"x-ai/grok-4.5":{"draws":59,"losses":124,"wins":65},"x-ai/grok-4.6":{"draws":49,"losses":112,"wins":43},"x-ai/grok-4.7":{"draws":9,"losses":82,"wins":29},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":33},"xiaomi/mimo-v2.5":{"draws":66,"losses":28,"wins":124},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":29,"wins":52},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":27,"wins":48},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":49,"wins":27},"z-ai/glm-5.2":{"draws":84,"losses":102,"wins":158},"z-ai/glm-5.3":{"draws":29,"losses":84,"wins":57},"z-ai/glm-5.3-flash":{"draws":33,"losses":93,"wins":76},"z-ai/glm-5.3-flashx":{"draws":29,"losses":60,"wins":47}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":46,"losses":31,"wins":104},"claude-fable-5":{"draws":39,"losses":107,"wins":58},"claude-fable-5-1":{"draws":13,"losses":199,"wins":18},"claude-haiku-5-5":{"draws":22,"losses":59,"wins":51},"claude-opus-4-5":{"draws":63,"losses":67,"wins":152},"claude-opus-4-8":{"draws":28,"losses":52,"wins":56},"claude-opus-5":{"draws":39,"losses":165,"wins":54},"claude-opus-5-5":{"draws":8,"losses":129,"wins":9},"claude-sonnet-5":{"draws":62,"losses":53,"wins":99},"claude-sonnet-5-5":{"draws":22,"losses":64,"wins":52},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":48},"deepseek/deepseek-v4-flash":{"draws":56,"losses":42,"wins":178},"deepseek/deepseek-v4-pro":{"draws":33,"losses":56,"wins":107},"deepseek/deepseek-v4-pro-0813":{"draws":47,"losses":57,"wins":90},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":54,"wins":57},"fireworks/ember-1":{"draws":37,"losses":41,"wins":62},"gemini-3.1-pro-preview":{"draws":26,"losses":37,"wins":77},"google/gemini-3.1-flash-lite":{"draws":16,"losses":5,"wins":79},"google/gemini-3.5-flash":{"draws":49,"losses":70,"wins":129},"google/gemini-3.5-flash-lite":{"draws":84,"losses":67,"wins":211},"google/gemini-3.6-flash":{"draws":65,"losses":132,"wins":165},"google/gemini-3.8-flash":{"draws":44,"losses":90,"wins":76},"google/gemma-4-31b-it":{"draws":21,"losses":8,"wins":53},"gpt-4.1":{"draws":18,"losses":4,"wins":30},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":28,"losses":29,"wins":75},"gpt-5.4":{"draws":47,"losses":87,"wins":72},"gpt-5.4-mini":{"draws":19,"losses":13,"wins":62},"gpt-5.4-nano":{"draws":27,"losses":26,"wins":87},"gpt-5.5":{"draws":31,"losses":46,"wins":49},"gpt-5.6-luna":{"draws":56,"losses":46,"wins":104},"gpt-5.6-sol":{"draws":34,"losses":110,"wins":62},"gpt-5.6-terra":{"draws":51,"losses":60,"wins":93},"gpt-6-astra":{"draws":22,"losses":163,"wins":15},"gpt-6-luna":{"draws":23,"losses":36,"wins":79},"gpt-6-sol":{"draws":23,"losses":94,"wins":21},"gpt-6.1-sol":{"draws":14,"losses":113,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":47,"losses":14,"wins":85},"inclusionai/ling-3.0-flash":{"draws":20,"losses":13,"wins":81},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":42,"losses":25,"wins":116},"meta/muse-glimmer-30b":{"draws":62,"losses":25,"wins":89},"meta/muse-spark-1.2":{"draws":38,"losses":63,"wins":73},"meta/muse-spark-1.3":{"draws":20,"losses":46,"wins":46},"meta/muse-wonder":{"draws":27,"losses":72,"wins":41},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":62},"mistralai/mistral-large-4-0":{"draws":20,"losses":22,"wins":44},"mistralai/mistral-medium-3-5":{"draws":31,"losses":6,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":42,"losses":56,"wins":92},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":55},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":14,"wins":85},"o3":{"draws":24,"losses":78,"wins":154},"openai/gpt-oss-120b":{"draws":49,"losses":23,"wins":106},"poolside/laguna-s-2.1":{"draws":46,"losses":35,"wins":89},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":46},"qwen/qwen3.7-plus":{"draws":15,"losses":16,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":81,"wins":85},"qwen/qwen3.8-27b":{"draws":21,"losses":42,"wins":55},"qwen/qwen3.8-flash":{"draws":41,"losses":42,"wins":65},"qwen/qwen3.8-max":{"draws":54,"losses":56,"wins":102},"qwen/qwen3.8-max-0902":{"draws":36,"losses":53,"wins":49},"stealth/ox-alpha":{"draws":146,"losses":256,"wins":294},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":69},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":83},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":14,"losses":16,"wins":56},"tencent/hy4-preview":{"draws":45,"losses":77,"wins":80},"thinkingmachines/inkling":{"draws":36,"losses":16,"wins":138},"thinkingmachines/inkling-small":{"draws":63,"losses":23,"wins":124},"unbiased/pareto-26.10-preview":{"draws":2,"losses":38,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":26},"x-ai/grok-4.5":{"draws":28,"losses":83,"wins":87},"x-ai/grok-4.6":{"draws":46,"losses":91,"wins":73},"x-ai/grok-4.7":{"draws":11,"losses":79,"wins":30},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":57,"losses":21,"wins":152},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":44,"wins":33},"z-ai/glm-5.2":{"draws":79,"losses":84,"wins":177},"z-ai/glm-5.3":{"draws":36,"losses":92,"wins":54},"z-ai/glm-5.3-flash":{"draws":45,"losses":95,"wins":74},"z-ai/glm-5.3-flashx":{"draws":28,"losses":55,"wins":56}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":16,"wins":83},"claude-fable-5":{"draws":25,"losses":56,"wins":55},"claude-fable-5-1":{"draws":13,"losses":112,"wins":31},"claude-haiku-5-5":{"draws":28,"losses":29,"wins":75},"claude-opus-4-5":{"draws":45,"losses":41,"wins":136},"claude-opus-4-8":{"draws":26,"losses":38,"wins":58},"claude-opus-5":{"draws":28,"losses":127,"wins":73},"claude-opus-5-5":{"draws":9,"losses":101,"wins":28},"claude-sonnet-5":{"draws":28,"losses":27,"wins":81},"claude-sonnet-5-5":{"draws":21,"losses":61,"wins":52},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":45},"deepseek/deepseek-v4-flash":{"draws":36,"losses":31,"wins":139},"deepseek/deepseek-v4-pro":{"draws":22,"losses":29,"wins":71},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":27,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":36,"wins":60},"fireworks/ember-1":{"draws":34,"losses":30,"wins":72},"gemini-3.1-pro-preview":{"draws":26,"losses":20,"wins":82},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":76},"google/gemini-3.5-flash":{"draws":27,"losses":28,"wins":117},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":168},"google/gemini-3.6-flash":{"draws":39,"losses":64,"wins":133},"google/gemini-3.8-flash":{"draws":34,"losses":38,"wins":66},"google/gemma-4-31b-it":{"draws":17,"losses":7,"wins":60},"gpt-4.1":{"draws":7,"losses":6,"wins":31},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":22,"losses":23,"wins":71},"gpt-5.4":{"draws":28,"losses":42,"wins":62},"gpt-5.4-mini":{"draws":22,"losses":10,"wins":58},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":101},"gpt-5.5":{"draws":36,"losses":34,"wins":58},"gpt-5.6-luna":{"draws":28,"losses":25,"wins":81},"gpt-5.6-sol":{"draws":22,"losses":52,"wins":62},"gpt-5.6-terra":{"draws":29,"losses":29,"wins":70},"gpt-6-astra":{"draws":14,"losses":105,"wins":15},"gpt-6-luna":{"draws":33,"losses":29,"wins":76},"gpt-6-sol":{"draws":18,"losses":73,"wins":45},"gpt-6.1-sol":{"draws":19,"losses":89,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":4,"wins":65},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":75},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":26,"losses":16,"wins":98},"meta/muse-glimmer-30b":{"draws":25,"losses":15,"wins":78},"meta/muse-spark-1.2":{"draws":26,"losses":40,"wins":68},"meta/muse-spark-1.3":{"draws":27,"losses":41,"wins":72},"meta/muse-wonder":{"draws":18,"losses":39,"wins":39},"minimax/minimax-m3":{"draws":12,"losses":11,"wins":49},"mistralai/mistral-large-4-0":{"draws":19,"losses":23,"wins":48},"mistralai/mistral-medium-3-5":{"draws":15,"losses":6,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":19},"moonshotai/kimi-k3":{"draws":24,"losses":25,"wins":83},"nex-agi/nex-n2-pro":{"draws":13,"losses":6,"wins":47},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":8,"wins":75},"o3":{"draws":12,"losses":32,"wins":142},"openai/gpt-oss-120b":{"draws":22,"losses":10,"wins":84},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":99},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":57},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":38,"wins":72},"qwen/qwen3.8-27b":{"draws":18,"losses":14,"wins":68},"qwen/qwen3.8-flash":{"draws":24,"losses":11,"wins":57},"qwen/qwen3.8-max":{"draws":28,"losses":28,"wins":76},"qwen/qwen3.8-max-0902":{"draws":31,"losses":32,"wins":71},"stealth/ox-alpha":{"draws":91,"losses":118,"wins":237},"stealth/space-bunny-alpha":{"draws":27,"losses":18,"wins":61},"stepfun/step-3.7-flash":{"draws":12,"losses":10,"wins":78},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":13,"losses":12,"wins":47},"tencent/hy4-preview":{"draws":26,"losses":35,"wins":67},"thinkingmachines/inkling":{"draws":36,"losses":16,"wins":104},"thinkingmachines/inkling-small":{"draws":30,"losses":15,"wins":91},"unbiased/pareto-26.10-preview":{"draws":4,"losses":33,"wins":9},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":32},"x-ai/grok-4.5":{"draws":29,"losses":30,"wins":77},"x-ai/grok-4.6":{"draws":38,"losses":36,"wins":58},"x-ai/grok-4.7":{"draws":16,"losses":60,"wins":36},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":33},"xiaomi/mimo-v2.5":{"draws":43,"losses":17,"wins":146},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":57},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":36,"wins":43},"z-ai/glm-5.2":{"draws":65,"losses":43,"wins":166},"z-ai/glm-5.3":{"draws":17,"losses":59,"wins":62},"z-ai/glm-5.3-flash":{"draws":28,"losses":43,"wins":67},"z-ai/glm-5.3-flashx":{"draws":32,"losses":37,"wins":65}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":41,"wins":17},"claude-fable-5":{"draws":20,"losses":54,"wins":6},"claude-fable-5-1":{"draws":2,"losses":83,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":49,"wins":13},"claude-opus-4-5":{"draws":60,"losses":120,"wins":22},"claude-opus-4-8":{"draws":33,"losses":79,"wins":18},"claude-opus-5":{"draws":25,"losses":169,"wins":14},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":21,"losses":46,"wins":17},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":9,"losses":19,"wins":24},"deepseek/deepseek-v4-flash":{"draws":54,"losses":58,"wins":60},"deepseek/deepseek-v4-pro":{"draws":16,"losses":47,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":46,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":42,"wins":17},"fireworks/ember-1":{"draws":19,"losses":54,"wins":5},"gemini-3.1-pro-preview":{"draws":19,"losses":37,"wins":22},"google/gemini-3.1-flash-lite":{"draws":29,"losses":41,"wins":50},"google/gemini-3.5-flash":{"draws":31,"losses":51,"wins":28},"google/gemini-3.5-flash-lite":{"draws":51,"losses":67,"wins":54},"google/gemini-3.6-flash":{"draws":38,"losses":103,"wins":29},"google/gemini-3.8-flash":{"draws":19,"losses":58,"wins":7},"google/gemma-4-31b-it":{"draws":15,"losses":11,"wins":14},"gpt-4.1":{"draws":18,"losses":28,"wins":14},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":36,"losses":54,"wins":30},"gpt-5.4":{"draws":18,"losses":43,"wins":17},"gpt-5.4-mini":{"draws":38,"losses":42,"wins":40},"gpt-5.4-nano":{"draws":46,"losses":76,"wins":52},"gpt-5.5":{"draws":40,"losses":67,"wins":21},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":21},"gpt-5.6-sol":{"draws":15,"losses":61,"wins":4},"gpt-5.6-terra":{"draws":23,"losses":44,"wins":15},"gpt-6-astra":{"draws":1,"losses":77,"wins":2},"gpt-6-luna":{"draws":18,"losses":42,"wins":14},"gpt-6-sol":{"draws":9,"losses":62,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":70,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":13,"wins":21},"inclusionai/ling-3.0-flash":{"draws":52,"losses":23,"wins":45},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":30,"losses":56,"wins":48},"meta/muse-glimmer-30b":{"draws":28,"losses":22,"wins":28},"meta/muse-spark-1.2":{"draws":18,"losses":57,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":62,"wins":7},"meta/muse-wonder":{"draws":12,"losses":49,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":11,"losses":20,"wins":13},"mistralai/mistral-medium-3-5":{"draws":15,"losses":18,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":25,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":58,"wins":16},"nex-agi/nex-n2-pro":{"draws":24,"losses":21,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":39,"wins":49},"o3":{"draws":26,"losses":84,"wins":30},"openai/gpt-oss-120b":{"draws":25,"losses":30,"wins":21},"poolside/laguna-s-2.1":{"draws":46,"losses":48,"wins":38},"qwen/qwen3.7-max":{"draws":41,"losses":45,"wins":20},"qwen/qwen3.7-plus":{"draws":24,"losses":33,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":53,"wins":9},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":28,"wins":19},"qwen/qwen3.8-max":{"draws":25,"losses":41,"wins":14},"qwen/qwen3.8-max-0902":{"draws":20,"losses":46,"wins":8},"stealth/ox-alpha":{"draws":64,"losses":153,"wins":41},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":13},"stepfun/step-3.7-flash":{"draws":12,"losses":18,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":40,"wins":22},"tencent/hy4-preview":{"draws":19,"losses":52,"wins":7},"thinkingmachines/inkling":{"draws":31,"losses":48,"wins":45},"thinkingmachines/inkling-small":{"draws":25,"losses":21,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":20,"losses":80,"wins":8},"x-ai/grok-4.6":{"draws":24,"losses":56,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":61,"wins":9},"x-ai/grok-build-0.1":{"draws":20,"losses":25,"wins":17},"xiaomi/mimo-v2.5":{"draws":92,"losses":80,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":39,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":28,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":8},"z-ai/glm-5.2":{"draws":72,"losses":88,"wins":46},"z-ai/glm-5.3":{"draws":17,"losses":51,"wins":6},"z-ai/glm-5.3-flash":{"draws":20,"losses":44,"wins":14},"z-ai/glm-5.3-flashx":{"draws":20,"losses":46,"wins":12}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":22,"wins":32},"claude-fable-5":{"draws":14,"losses":45,"wins":23},"claude-fable-5-1":{"draws":4,"losses":84,"wins":6},"claude-haiku-5-5":{"draws":30,"losses":28,"wins":28},"claude-opus-4-5":{"draws":41,"losses":46,"wins":47},"claude-opus-4-8":{"draws":16,"losses":25,"wins":33},"claude-opus-5":{"draws":24,"losses":100,"wins":18},"claude-opus-5-5":{"draws":12,"losses":68,"wins":4},"claude-sonnet-5":{"draws":25,"losses":38,"wins":23},"claude-sonnet-5-5":{"draws":23,"losses":39,"wins":24},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":20},"deepseek/deepseek-v4-flash":{"draws":34,"losses":20,"wins":64},"deepseek/deepseek-v4-pro":{"draws":20,"losses":24,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":28,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":31,"wins":24},"fireworks/ember-1":{"draws":23,"losses":31,"wins":32},"gemini-3.1-pro-preview":{"draws":19,"losses":32,"wins":33},"google/gemini-3.1-flash-lite":{"draws":16,"losses":2,"wins":38},"google/gemini-3.5-flash":{"draws":31,"losses":35,"wins":36},"google/gemini-3.5-flash-lite":{"draws":39,"losses":29,"wins":70},"google/gemini-3.6-flash":{"draws":30,"losses":60,"wins":52},"google/gemini-3.8-flash":{"draws":20,"losses":35,"wins":25},"google/gemma-4-31b-it":{"draws":19,"losses":9,"wins":24},"gpt-4.1":{"draws":10,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":21,"losses":16,"wins":33},"gpt-5.4":{"draws":25,"losses":36,"wins":15},"gpt-5.4-mini":{"draws":24,"losses":12,"wins":20},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":46},"gpt-5.5":{"draws":26,"losses":29,"wins":21},"gpt-5.6-luna":{"draws":27,"losses":15,"wins":40},"gpt-5.6-sol":{"draws":17,"losses":49,"wins":18},"gpt-5.6-terra":{"draws":30,"losses":18,"wins":26},"gpt-6-astra":{"draws":9,"losses":66,"wins":5},"gpt-6-luna":{"draws":25,"losses":30,"wins":31},"gpt-6-sol":{"draws":15,"losses":55,"wins":14},"gpt-6.1-sol":{"draws":9,"losses":64,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":9,"wins":26},"inclusionai/ling-3.0-flash":{"draws":22,"losses":9,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":14,"wins":40},"meta/muse-glimmer-30b":{"draws":24,"losses":19,"wins":33},"meta/muse-spark-1.2":{"draws":15,"losses":41,"wins":24},"meta/muse-spark-1.3":{"draws":20,"losses":44,"wins":22},"meta/muse-wonder":{"draws":19,"losses":48,"wins":23},"minimax/minimax-m3":{"draws":11,"losses":13,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":15,"losses":7,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":10},"moonshotai/kimi-k3":{"draws":28,"losses":29,"wins":27},"nex-agi/nex-n2-pro":{"draws":12,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":18,"wins":28},"o3":{"draws":26,"losses":37,"wins":53},"openai/gpt-oss-120b":{"draws":26,"losses":14,"wins":34},"poolside/laguna-s-2.1":{"draws":29,"losses":20,"wins":35},"qwen/qwen3.7-max":{"draws":17,"losses":5,"wins":26},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":36,"wins":26},"qwen/qwen3.8-27b":{"draws":17,"losses":21,"wins":22},"qwen/qwen3.8-flash":{"draws":17,"losses":17,"wins":20},"qwen/qwen3.8-max":{"draws":23,"losses":27,"wins":30},"qwen/qwen3.8-max-0902":{"draws":30,"losses":40,"wins":18},"stealth/ox-alpha":{"draws":84,"losses":106,"wins":80},"stealth/space-bunny-alpha":{"draws":23,"losses":14,"wins":31},"stepfun/step-3.7-flash":{"draws":18,"losses":9,"wins":33},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":20,"losses":15,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":36,"wins":28},"thinkingmachines/inkling":{"draws":33,"losses":10,"wins":53},"thinkingmachines/inkling-small":{"draws":26,"losses":14,"wins":44},"unbiased/pareto-26.10-preview":{"draws":3,"losses":24,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":13},"x-ai/grok-4.5":{"draws":20,"losses":31,"wins":29},"x-ai/grok-4.6":{"draws":27,"losses":42,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":38,"wins":16},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":45,"losses":18,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":20,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":26,"wins":19},"z-ai/glm-5.2":{"draws":62,"losses":33,"wins":67},"z-ai/glm-5.3":{"draws":11,"losses":49,"wins":18},"z-ai/glm-5.3-flash":{"draws":20,"losses":42,"wins":22},"z-ai/glm-5.3-flashx":{"draws":23,"losses":34,"wins":25}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":47,"wins":35},"claude-fable-5":{"draws":37,"losses":68,"wins":11},"claude-fable-5-1":{"draws":6,"losses":97,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":50,"wins":4},"claude-opus-4-5":{"draws":52,"losses":109,"wins":15},"claude-opus-4-8":{"draws":27,"losses":47,"wins":6},"claude-opus-5":{"draws":22,"losses":112,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":63,"losses":72,"wins":19},"claude-sonnet-5-5":{"draws":19,"losses":57,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":11,"wins":13},"deepseek/deepseek-v4-flash":{"draws":83,"losses":67,"wins":40},"deepseek/deepseek-v4-pro":{"draws":44,"losses":80,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":68,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":45,"wins":9},"fireworks/ember-1":{"draws":27,"losses":51,"wins":6},"gemini-3.1-pro-preview":{"draws":32,"losses":42,"wins":10},"google/gemini-3.1-flash-lite":{"draws":14,"losses":18,"wins":26},"google/gemini-3.5-flash":{"draws":49,"losses":81,"wins":26},"google/gemini-3.5-flash-lite":{"draws":105,"losses":119,"wins":60},"google/gemini-3.6-flash":{"draws":88,"losses":120,"wins":28},"google/gemini-3.8-flash":{"draws":37,"losses":80,"wins":7},"google/gemma-4-31b-it":{"draws":20,"losses":21,"wins":7},"gpt-4.1":{"draws":15,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":27,"losses":34,"wins":17},"gpt-5.4":{"draws":50,"losses":56,"wins":20},"gpt-5.4-mini":{"draws":24,"losses":24,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":47,"wins":18},"gpt-5.5":{"draws":28,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":66,"losses":68,"wins":24},"gpt-5.6-sol":{"draws":24,"losses":91,"wins":7},"gpt-5.6-terra":{"draws":48,"losses":80,"wins":16},"gpt-6-astra":{"draws":7,"losses":87,"wins":0},"gpt-6-luna":{"draws":28,"losses":47,"wins":7},"gpt-6-sol":{"draws":7,"losses":73,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":81,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":57,"losses":35,"wins":32},"inclusionai/ling-3.0-flash":{"draws":32,"losses":21,"wins":31},"meituan/longcat-2.0":{"draws":54,"losses":51,"wins":33},"meta/muse-glimmer-30b":{"draws":70,"losses":54,"wins":20},"meta/muse-spark-1.2":{"draws":33,"losses":69,"wins":18},"meta/muse-spark-1.3":{"draws":31,"losses":81,"wins":6},"meta/muse-wonder":{"draws":15,"losses":59,"wins":6},"minimax/minimax-m3":{"draws":15,"losses":21,"wins":18},"mistralai/mistral-large-4-0":{"draws":15,"losses":22,"wins":7},"mistralai/mistral-medium-3-5":{"draws":24,"losses":12,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":42,"losses":73,"wins":11},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":26,"wins":12},"o3":{"draws":35,"losses":107,"wins":20},"openai/gpt-oss-120b":{"draws":69,"losses":45,"wins":28},"poolside/laguna-s-2.1":{"draws":57,"losses":49,"wins":26},"qwen/qwen3.7-max":{"draws":26,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":19,"losses":14,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":94,"wins":6},"qwen/qwen3.8-27b":{"draws":21,"losses":42,"wins":5},"qwen/qwen3.8-flash":{"draws":39,"losses":48,"wins":11},"qwen/qwen3.8-max":{"draws":50,"losses":79,"wins":17},"qwen/qwen3.8-max-0902":{"draws":28,"losses":48,"wins":6},"stealth/ox-alpha":{"draws":130,"losses":256,"wins":68},"stealth/space-bunny-alpha":{"draws":24,"losses":30,"wins":12},"stepfun/step-3.7-flash":{"draws":21,"losses":25,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":50,"losses":75,"wins":11},"thinkingmachines/inkling":{"draws":46,"losses":54,"wins":28},"thinkingmachines/inkling-small":{"draws":79,"losses":59,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":15,"wins":1},"x-ai/grok-4.5":{"draws":32,"losses":78,"wins":14},"x-ai/grok-4.6":{"draws":49,"losses":71,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":13,"wins":3},"xiaomi/mimo-v2.5":{"draws":58,"losses":43,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":24,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":33,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":106,"losses":103,"wins":31},"z-ai/glm-5.3":{"draws":27,"losses":81,"wins":8},"z-ai/glm-5.3-flash":{"draws":45,"losses":66,"wins":21},"z-ai/glm-5.3-flashx":{"draws":21,"losses":55,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":16},"claude-fable-5":{"draws":9,"losses":21,"wins":8},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":29,"losses":50,"wins":29},"claude-opus-4-8":{"draws":16,"losses":32,"wins":14},"claude-opus-5":{"draws":13,"losses":112,"wins":7},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"fireworks/ember-1":{"draws":12,"losses":13,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":36},"google/gemini-3.5-flash":{"draws":13,"losses":16,"wins":19},"google/gemini-3.5-flash-lite":{"draws":18,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":22,"losses":41,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":11,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":21,"wins":24},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":11,"wins":25},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":28},"gpt-5.5":{"draws":30,"losses":17,"wins":19},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":12},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":22},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":25},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":12,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":33},"o3":{"draws":7,"losses":29,"wins":32},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":17},"poolside/laguna-s-2.1":{"draws":17,"losses":28,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":16,"wins":12},"qwen/qwen3.7-plus":{"draws":21,"losses":4,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":9,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":25,"losses":50,"wins":31},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":15},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":8},"thinkingmachines/inkling":{"draws":13,"losses":17,"wins":30},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":22},"xiaomi/mimo-v2.5":{"draws":50,"losses":22,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":23,"losses":43,"wins":42},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":56,"losses":47,"wins":95},"claude-fable-5":{"draws":40,"losses":134,"wins":36},"claude-fable-5-1":{"draws":14,"losses":207,"wins":15},"claude-haiku-5-5":{"draws":34,"losses":56,"wins":36},"claude-opus-4-5":{"draws":135,"losses":108,"wins":141},"claude-opus-4-8":{"draws":41,"losses":50,"wins":53},"claude-opus-5":{"draws":49,"losses":202,"wins":53},"claude-opus-5-5":{"draws":5,"losses":126,"wins":13},"claude-sonnet-5":{"draws":104,"losses":76,"wins":136},"claude-sonnet-5-5":{"draws":28,"losses":59,"wins":45},"cohere/north-mini-code":{"draws":13,"losses":11,"wins":34},"deepseek/deepseek-v4-flash":{"draws":74,"losses":65,"wins":131},"deepseek/deepseek-v4-pro":{"draws":47,"losses":59,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":56,"losses":71,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":55,"wins":41},"fireworks/ember-1":{"draws":43,"losses":54,"wins":37},"gemini-3.1-pro-preview":{"draws":34,"losses":40,"wins":62},"google/gemini-3.1-flash-lite":{"draws":24,"losses":10,"wins":58},"google/gemini-3.5-flash":{"draws":83,"losses":89,"wins":78},"google/gemini-3.5-flash-lite":{"draws":210,"losses":126,"wins":298},"google/gemini-3.6-flash":{"draws":183,"losses":244,"wins":207},"google/gemini-3.8-flash":{"draws":57,"losses":111,"wins":48},"google/gemma-4-31b-it":{"draws":27,"losses":13,"wins":34},"gpt-4.1":{"draws":14,"losses":13,"wins":25},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":38,"losses":42,"wins":50},"gpt-5.4":{"draws":63,"losses":169,"wins":72},"gpt-5.4-mini":{"draws":43,"losses":29,"wins":50},"gpt-5.4-nano":{"draws":43,"losses":37,"wins":92},"gpt-5.5":{"draws":50,"losses":47,"wins":59},"gpt-5.6-luna":{"draws":99,"losses":70,"wins":137},"gpt-5.6-sol":{"draws":53,"losses":188,"wins":67},"gpt-5.6-terra":{"draws":63,"losses":65,"wins":80},"gpt-6-astra":{"draws":17,"losses":179,"wins":18},"gpt-6-luna":{"draws":43,"losses":39,"wins":50},"gpt-6-sol":{"draws":14,"losses":96,"wins":24},"gpt-6.1-sol":{"draws":10,"losses":108,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":66,"losses":14,"wins":72},"inclusionai/ling-3.0-flash":{"draws":64,"losses":26,"wins":86},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":92,"losses":45,"wins":151},"meta/muse-glimmer-30b":{"draws":54,"losses":30,"wins":92},"meta/muse-spark-1.2":{"draws":53,"losses":87,"wins":98},"meta/muse-spark-1.3":{"draws":42,"losses":92,"wins":56},"meta/muse-wonder":{"draws":24,"losses":83,"wins":25},"minimax/minimax-m3":{"draws":20,"losses":16,"wins":58},"mistralai/mistral-large-4-0":{"draws":28,"losses":27,"wins":29},"mistralai/mistral-medium-3-5":{"draws":42,"losses":11,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":18,"wins":12},"moonshotai/kimi-k3":{"draws":64,"losses":56,"wins":56},"nex-agi/nex-n2-pro":{"draws":20,"losses":12,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":28,"wins":54},"o3":{"draws":54,"losses":166,"wins":150},"openai/gpt-oss-120b":{"draws":56,"losses":30,"wins":96},"poolside/laguna-s-2.1":{"draws":100,"losses":31,"wins":137},"qwen/qwen3.7-max":{"draws":23,"losses":23,"wins":54},"qwen/qwen3.7-plus":{"draws":33,"losses":22,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":65,"losses":75,"wins":80},"qwen/qwen3.8-27b":{"draws":31,"losses":30,"wins":53},"qwen/qwen3.8-flash":{"draws":51,"losses":43,"wins":52},"qwen/qwen3.8-max":{"draws":58,"losses":77,"wins":78},"qwen/qwen3.8-max-0902":{"draws":36,"losses":66,"wins":32},"stealth/ox-alpha":{"draws":181,"losses":282,"wins":244},"stealth/space-bunny-alpha":{"draws":37,"losses":18,"wins":51},"stepfun/step-3.7-flash":{"draws":22,"losses":15,"wins":57},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":32,"losses":19,"wins":35},"tencent/hy4-preview":{"draws":59,"losses":78,"wins":71},"thinkingmachines/inkling":{"draws":87,"losses":41,"wins":136},"thinkingmachines/inkling-small":{"draws":77,"losses":33,"wins":108},"unbiased/pareto-26.10-preview":{"draws":2,"losses":40,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":91,"losses":131,"wins":100},"x-ai/grok-4.6":{"draws":58,"losses":102,"wins":54},"x-ai/grok-4.7":{"draws":13,"losses":80,"wins":27},"x-ai/grok-build-0.1":{"draws":21,"losses":6,"wins":31},"xiaomi/mimo-v2.5":{"draws":85,"losses":38,"wins":129},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":38,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":31,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":45,"wins":25},"z-ai/glm-5.2":{"draws":122,"losses":88,"wins":134},"z-ai/glm-5.3":{"draws":44,"losses":84,"wins":48},"z-ai/glm-5.3-flash":{"draws":58,"losses":84,"wins":66},"z-ai/glm-5.3-flashx":{"draws":37,"losses":61,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":39,"wins":12},"claude-fable-5":{"draws":15,"losses":56,"wins":1},"claude-fable-5-1":{"draws":4,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":41,"wins":10},"claude-opus-4-5":{"draws":39,"losses":111,"wins":26},"claude-opus-4-8":{"draws":41,"losses":73,"wins":10},"claude-opus-5":{"draws":3,"losses":147,"wins":10},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":29,"losses":44,"wins":11},"claude-sonnet-5-5":{"draws":15,"losses":46,"wins":11},"cohere/north-mini-code":{"draws":21,"losses":23,"wins":26},"deepseek/deepseek-v4-flash":{"draws":39,"losses":74,"wins":49},"deepseek/deepseek-v4-pro":{"draws":21,"losses":38,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":46,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":50,"wins":6},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":21,"losses":40,"wins":11},"google/gemini-3.1-flash-lite":{"draws":18,"losses":33,"wins":49},"google/gemini-3.5-flash":{"draws":29,"losses":52,"wins":21},"google/gemini-3.5-flash-lite":{"draws":56,"losses":64,"wins":40},"google/gemini-3.6-flash":{"draws":40,"losses":103,"wins":21},"google/gemini-3.8-flash":{"draws":15,"losses":52,"wins":7},"google/gemma-4-31b-it":{"draws":13,"losses":16,"wins":11},"gpt-4.1":{"draws":11,"losses":20,"wins":11},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":30,"losses":50,"wins":20},"gpt-5.4":{"draws":20,"losses":36,"wins":14},"gpt-5.4-mini":{"draws":40,"losses":34,"wins":22},"gpt-5.4-nano":{"draws":31,"losses":64,"wins":47},"gpt-5.5":{"draws":33,"losses":76,"wins":11},"gpt-5.6-luna":{"draws":24,"losses":42,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":61,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":43,"wins":8},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":15,"losses":42,"wins":11},"gpt-6-sol":{"draws":7,"losses":61,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":68,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":17,"wins":19},"inclusionai/ling-3.0-flash":{"draws":50,"losses":30,"wins":30},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":65,"wins":41},"meta/muse-glimmer-30b":{"draws":27,"losses":25,"wins":14},"meta/muse-spark-1.2":{"draws":13,"losses":50,"wins":13},"meta/muse-spark-1.3":{"draws":11,"losses":55,"wins":6},"meta/muse-wonder":{"draws":13,"losses":47,"wins":6},"minimax/minimax-m3":{"draws":24,"losses":41,"wins":21},"mistralai/mistral-large-4-0":{"draws":12,"losses":21,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":26,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":17,"wins":1},"moonshotai/kimi-k3":{"draws":20,"losses":56,"wins":12},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":59,"wins":27},"o3":{"draws":16,"losses":93,"wins":21},"openai/gpt-oss-120b":{"draws":21,"losses":24,"wins":21},"poolside/laguna-s-2.1":{"draws":45,"losses":48,"wins":17},"qwen/qwen3.7-max":{"draws":26,"losses":48,"wins":10},"qwen/qwen3.7-plus":{"draws":22,"losses":27,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":48,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":34,"wins":8},"qwen/qwen3.8-flash":{"draws":24,"losses":36,"wins":6},"qwen/qwen3.8-max":{"draws":23,"losses":45,"wins":6},"qwen/qwen3.8-max-0902":{"draws":19,"losses":40,"wins":9},"stealth/ox-alpha":{"draws":63,"losses":168,"wins":31},"stealth/space-bunny-alpha":{"draws":17,"losses":28,"wins":13},"stepfun/step-3.7-flash":{"draws":16,"losses":25,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":35,"losses":17,"wins":20},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":6},"thinkingmachines/inkling":{"draws":33,"losses":43,"wins":32},"thinkingmachines/inkling-small":{"draws":25,"losses":32,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":26,"losses":69,"wins":7},"x-ai/grok-4.6":{"draws":21,"losses":55,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":21,"losses":23,"wins":10},"xiaomi/mimo-v2.5":{"draws":59,"losses":88,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":36,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":31,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":34,"wins":4},"z-ai/glm-5.2":{"draws":85,"losses":83,"wins":24},"z-ai/glm-5.3":{"draws":14,"losses":57,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":49,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":53,"wins":5}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":42,"wins":37},"claude-fable-5":{"draws":27,"losses":89,"wins":12},"claude-fable-5-1":{"draws":7,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":60,"wins":26},"claude-opus-4-5":{"draws":127,"losses":151,"wins":52},"claude-opus-4-8":{"draws":47,"losses":127,"wins":32},"claude-opus-5":{"draws":51,"losses":269,"wins":8},"claude-opus-5-5":{"draws":4,"losses":137,"wins":1},"claude-sonnet-5":{"draws":52,"losses":56,"wins":30},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":22},"cohere/north-mini-code":{"draws":21,"losses":25,"wins":24},"deepseek/deepseek-v4-flash":{"draws":110,"losses":87,"wins":67},"deepseek/deepseek-v4-pro":{"draws":46,"losses":52,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":61,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":58,"wins":22},"fireworks/ember-1":{"draws":49,"losses":58,"wins":19},"gemini-3.1-pro-preview":{"draws":48,"losses":50,"wins":28},"google/gemini-3.1-flash-lite":{"draws":57,"losses":44,"wins":76},"google/gemini-3.5-flash":{"draws":57,"losses":85,"wins":36},"google/gemini-3.5-flash-lite":{"draws":109,"losses":77,"wins":80},"google/gemini-3.6-flash":{"draws":81,"losses":138,"wins":39},"google/gemini-3.8-flash":{"draws":43,"losses":80,"wins":11},"google/gemma-4-31b-it":{"draws":30,"losses":18,"wins":18},"gpt-4.1":{"draws":32,"losses":33,"wins":15},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":4},"gpt-5":{"draws":78,"losses":76,"wins":36},"gpt-5.4":{"draws":46,"losses":71,"wins":7},"gpt-5.4-mini":{"draws":82,"losses":40,"wins":40},"gpt-5.4-nano":{"draws":73,"losses":90,"wins":77},"gpt-5.5":{"draws":94,"losses":96,"wins":14},"gpt-5.6-luna":{"draws":51,"losses":42,"wins":33},"gpt-5.6-sol":{"draws":18,"losses":100,"wins":12},"gpt-5.6-terra":{"draws":48,"losses":60,"wins":22},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":40,"losses":59,"wins":25},"gpt-6-sol":{"draws":12,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":112,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":44,"losses":25,"wins":29},"inclusionai/ling-3.0-flash":{"draws":70,"losses":32,"wins":38},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":84,"losses":56,"wins":64},"meta/muse-glimmer-30b":{"draws":55,"losses":30,"wins":27},"meta/muse-spark-1.2":{"draws":35,"losses":68,"wins":19},"meta/muse-spark-1.3":{"draws":31,"losses":85,"wins":14},"meta/muse-wonder":{"draws":33,"losses":75,"wins":8},"minimax/minimax-m3":{"draws":52,"losses":49,"wins":39},"mistralai/mistral-large-4-0":{"draws":24,"losses":28,"wins":18},"mistralai/mistral-medium-3-5":{"draws":40,"losses":12,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":22,"losses":33,"wins":7},"moonshotai/kimi-k3":{"draws":46,"losses":54,"wins":28},"nex-agi/nex-n2-pro":{"draws":56,"losses":27,"wins":59},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":86,"losses":35,"wins":35},"o3":{"draws":69,"losses":127,"wins":50},"openai/gpt-oss-120b":{"draws":52,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":87,"losses":48,"wins":41},"qwen/qwen3.7-max":{"draws":75,"losses":48,"wins":29},"qwen/qwen3.7-plus":{"draws":51,"losses":41,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":65,"wins":15},"qwen/qwen3.8-27b":{"draws":30,"losses":43,"wins":19},"qwen/qwen3.8-flash":{"draws":41,"losses":33,"wins":18},"qwen/qwen3.8-max":{"draws":48,"losses":60,"wins":22},"qwen/qwen3.8-max-0902":{"draws":45,"losses":63,"wins":12},"stealth/ox-alpha":{"draws":112,"losses":210,"wins":60},"stealth/space-bunny-alpha":{"draws":41,"losses":32,"wins":25},"stepfun/step-3.7-flash":{"draws":40,"losses":44,"wins":38},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":77,"losses":43,"wins":26},"tencent/hy4-preview":{"draws":43,"losses":67,"wins":14},"thinkingmachines/inkling":{"draws":76,"losses":59,"wins":81},"thinkingmachines/inkling-small":{"draws":59,"losses":34,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":14,"wins":13},"x-ai/grok-4.5":{"draws":45,"losses":109,"wins":12},"x-ai/grok-4.6":{"draws":50,"losses":67,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":98,"wins":9},"x-ai/grok-build-0.1":{"draws":56,"losses":20,"wins":18},"xiaomi/mimo-v2.5":{"draws":179,"losses":98,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":45,"losses":54,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":48,"wins":10},"z-ai/glm-5.2":{"draws":160,"losses":116,"wins":68},"z-ai/glm-5.3":{"draws":28,"losses":82,"wins":16},"z-ai/glm-5.3-flash":{"draws":41,"losses":56,"wins":29},"z-ai/glm-5.3-flashx":{"draws":31,"losses":74,"wins":21}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":52,"losses":83,"wins":135},"claude-fable-5":{"draws":27,"losses":205,"wins":44},"claude-fable-5-1":{"draws":5,"losses":275,"wins":14},"claude-haiku-5-5":{"draws":27,"losses":97,"wins":60},"claude-opus-4-5":{"draws":88,"losses":344,"wins":168},"claude-opus-4-8":{"draws":36,"losses":148,"wins":68},"claude-opus-5":{"draws":28,"losses":358,"wins":26},"claude-opus-5-5":{"draws":11,"losses":197,"wins":4},"claude-sonnet-5":{"draws":47,"losses":173,"wins":190},"claude-sonnet-5-5":{"draws":17,"losses":130,"wins":45},"cohere/north-mini-code":{"draws":18,"losses":18,"wins":68},"deepseek/deepseek-v4-flash":{"draws":64,"losses":118,"wins":224},"deepseek/deepseek-v4-pro":{"draws":43,"losses":135,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":44,"losses":138,"wins":76},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":90,"wins":62},"fireworks/ember-1":{"draws":39,"losses":105,"wins":50},"gemini-3.1-pro-preview":{"draws":29,"losses":73,"wins":90},"google/gemini-3.1-flash-lite":{"draws":30,"losses":14,"wins":154},"google/gemini-3.5-flash":{"draws":52,"losses":186,"wins":112},"google/gemini-3.5-flash-lite":{"draws":131,"losses":229,"wins":518},"google/gemini-3.6-flash":{"draws":116,"losses":434,"wins":292},"google/gemini-3.8-flash":{"draws":37,"losses":180,"wins":69},"google/gemma-4-31b-it":{"draws":15,"losses":21,"wins":66},"gpt-4.1":{"draws":17,"losses":30,"wins":35},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":10},"gpt-5":{"draws":43,"losses":112,"wins":79},"gpt-5.4":{"draws":45,"losses":260,"wins":83},"gpt-5.4-mini":{"draws":34,"losses":45,"wins":75},"gpt-5.4-nano":{"draws":25,"losses":116,"wins":131},"gpt-5.5":{"draws":52,"losses":134,"wins":50},"gpt-5.6-luna":{"draws":66,"losses":147,"wins":187},"gpt-5.6-sol":{"draws":25,"losses":297,"wins":70},"gpt-5.6-terra":{"draws":53,"losses":115,"wins":108},"gpt-6-astra":{"draws":8,"losses":262,"wins":2},"gpt-6-luna":{"draws":29,"losses":98,"wins":59},"gpt-6-sol":{"draws":10,"losses":166,"wins":16},"gpt-6.1-sol":{"draws":3,"losses":186,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":23,"wins":133},"inclusionai/ling-3.0-flash":{"draws":35,"losses":35,"wins":150},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":56,"losses":103,"wins":247},"meta/muse-glimmer-30b":{"draws":51,"losses":43,"wins":148},"meta/muse-spark-1.2":{"draws":34,"losses":132,"wins":146},"meta/muse-spark-1.3":{"draws":24,"losses":154,"wins":78},"meta/muse-wonder":{"draws":12,"losses":142,"wins":32},"minimax/minimax-m3":{"draws":26,"losses":30,"wins":84},"mistralai/mistral-large-4-0":{"draws":26,"losses":53,"wins":37},"mistralai/mistral-medium-3-5":{"draws":35,"losses":20,"wins":107},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":32,"wins":29},"moonshotai/kimi-k3":{"draws":54,"losses":150,"wins":166},"nex-agi/nex-n2-pro":{"draws":16,"losses":21,"wins":93},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":69,"losses":50,"wins":127},"o3":{"draws":42,"losses":247,"wins":247},"openai/gpt-oss-120b":{"draws":45,"losses":41,"wins":162},"poolside/laguna-s-2.1":{"draws":69,"losses":86,"wins":163},"qwen/qwen3.7-max":{"draws":37,"losses":51,"wins":66},"qwen/qwen3.7-plus":{"draws":19,"losses":35,"wins":76},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":152,"wins":91},"qwen/qwen3.8-27b":{"draws":17,"losses":91,"wins":68},"qwen/qwen3.8-flash":{"draws":40,"losses":79,"wins":71},"qwen/qwen3.8-max":{"draws":53,"losses":148,"wins":99},"qwen/qwen3.8-max-0902":{"draws":34,"losses":96,"wins":62},"stealth/ox-alpha":{"draws":119,"losses":423,"wins":329},"stealth/space-bunny-alpha":{"draws":26,"losses":56,"wins":76},"stepfun/step-3.7-flash":{"draws":31,"losses":52,"wins":111},"stepfun/step-5-preview":{"draws":6,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":54,"wins":58},"tencent/hy4-preview":{"draws":46,"losses":152,"wins":92},"thinkingmachines/inkling":{"draws":55,"losses":78,"wins":245},"thinkingmachines/inkling-small":{"draws":69,"losses":71,"wins":159},"unbiased/pareto-26.10-preview":{"draws":0,"losses":59,"wins":3},"upstage/solar-mini4":{"draws":10,"losses":13,"wins":39},"x-ai/grok-4.5":{"draws":34,"losses":233,"wins":127},"x-ai/grok-4.6":{"draws":52,"losses":158,"wins":70},"x-ai/grok-4.7":{"draws":11,"losses":127,"wins":36},"x-ai/grok-build-0.1":{"draws":20,"losses":13,"wins":51},"xiaomi/mimo-v2.5":{"draws":85,"losses":61,"wins":230},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":66,"wins":74},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":74,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":85,"wins":26},"z-ai/glm-5.2":{"draws":94,"losses":193,"wins":229},"z-ai/glm-5.3":{"draws":23,"losses":166,"wins":53},"z-ai/glm-5.3-flash":{"draws":44,"losses":130,"wins":112},"z-ai/glm-5.3-flashx":{"draws":19,"losses":118,"wins":57}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":75,"losses":76,"wins":59},"claude-fable-5":{"draws":50,"losses":114,"wins":20},"claude-fable-5-1":{"draws":11,"losses":170,"wins":1},"claude-haiku-5-5":{"draws":26,"losses":74,"wins":12},"claude-opus-4-5":{"draws":81,"losses":147,"wins":40},"claude-opus-4-8":{"draws":38,"losses":68,"wins":10},"claude-opus-5":{"draws":32,"losses":183,"wins":11},"claude-opus-5-5":{"draws":8,"losses":130,"wins":0},"claude-sonnet-5":{"draws":79,"losses":122,"wins":31},"claude-sonnet-5-5":{"draws":26,"losses":82,"wins":18},"cohere/north-mini-code":{"draws":15,"losses":14,"wins":17},"deepseek/deepseek-v4-flash":{"draws":123,"losses":82,"wins":87},"deepseek/deepseek-v4-pro":{"draws":74,"losses":90,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":72,"losses":73,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":61,"wins":23},"fireworks/ember-1":{"draws":48,"losses":64,"wins":14},"gemini-3.1-pro-preview":{"draws":44,"losses":55,"wins":27},"google/gemini-3.1-flash-lite":{"draws":25,"losses":19,"wins":42},"google/gemini-3.5-flash":{"draws":81,"losses":114,"wins":51},"google/gemini-3.5-flash-lite":{"draws":149,"losses":142,"wins":117},"google/gemini-3.6-flash":{"draws":130,"losses":180,"wins":50},"google/gemini-3.8-flash":{"draws":50,"losses":122,"wins":14},"google/gemma-4-31b-it":{"draws":25,"losses":10,"wins":33},"gpt-4.1":{"draws":14,"losses":19,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":40,"losses":53,"wins":21},"gpt-5.4":{"draws":81,"losses":90,"wins":25},"gpt-5.4-mini":{"draws":37,"losses":32,"wins":21},"gpt-5.4-nano":{"draws":39,"losses":43,"wins":50},"gpt-5.5":{"draws":49,"losses":57,"wins":16},"gpt-5.6-luna":{"draws":110,"losses":74,"wins":52},"gpt-5.6-sol":{"draws":29,"losses":148,"wins":13},"gpt-5.6-terra":{"draws":82,"losses":115,"wins":25},"gpt-6-astra":{"draws":13,"losses":145,"wins":0},"gpt-6-luna":{"draws":37,"losses":58,"wins":25},"gpt-6-sol":{"draws":19,"losses":101,"wins":6},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":75,"losses":38,"wins":55},"inclusionai/ling-3.0-flash":{"draws":49,"losses":14,"wins":55},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":68,"losses":73,"wins":45},"meta/muse-glimmer-30b":{"draws":96,"losses":53,"wins":63},"meta/muse-spark-1.2":{"draws":54,"losses":102,"wins":22},"meta/muse-spark-1.3":{"draws":49,"losses":106,"wins":23},"meta/muse-wonder":{"draws":22,"losses":84,"wins":10},"minimax/minimax-m3":{"draws":25,"losses":21,"wins":30},"mistralai/mistral-large-4-0":{"draws":26,"losses":34,"wins":14},"mistralai/mistral-medium-3-5":{"draws":69,"losses":28,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":56,"losses":96,"wins":30},"nex-agi/nex-n2-pro":{"draws":21,"losses":21,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":28,"wins":36},"o3":{"draws":45,"losses":162,"wins":41},"openai/gpt-oss-120b":{"draws":58,"losses":39,"wins":39},"poolside/laguna-s-2.1":{"draws":90,"losses":58,"wins":42},"qwen/qwen3.7-max":{"draws":29,"losses":31,"wins":18},"qwen/qwen3.7-plus":{"draws":23,"losses":19,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":84,"losses":106,"wins":18},"qwen/qwen3.8-27b":{"draws":22,"losses":63,"wins":21},"qwen/qwen3.8-flash":{"draws":56,"losses":50,"wins":36},"qwen/qwen3.8-max":{"draws":81,"losses":112,"wins":17},"qwen/qwen3.8-max-0902":{"draws":41,"losses":70,"wins":13},"stealth/ox-alpha":{"draws":196,"losses":388,"wins":98},"stealth/space-bunny-alpha":{"draws":33,"losses":44,"wins":23},"stepfun/step-3.7-flash":{"draws":29,"losses":36,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":25,"wins":19},"tencent/hy4-preview":{"draws":74,"losses":88,"wins":32},"thinkingmachines/inkling":{"draws":56,"losses":65,"wins":61},"thinkingmachines/inkling-small":{"draws":105,"losses":58,"wins":81},"unbiased/pareto-26.10-preview":{"draws":0,"losses":40,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":57,"losses":108,"wins":19},"x-ai/grok-4.6":{"draws":65,"losses":105,"wins":22},"x-ai/grok-4.7":{"draws":9,"losses":99,"wins":4},"x-ai/grok-build-0.1":{"draws":19,"losses":16,"wins":9},"xiaomi/mimo-v2.5":{"draws":73,"losses":55,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":29,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":52,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":58,"wins":6},"z-ai/glm-5.2":{"draws":145,"losses":141,"wins":74},"z-ai/glm-5.3":{"draws":53,"losses":103,"wins":8},"z-ai/glm-5.3-flash":{"draws":61,"losses":112,"wins":19},"z-ai/glm-5.3-flashx":{"draws":37,"losses":76,"wins":13}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":81,"losses":61,"wins":52},"claude-fable-5":{"draws":43,"losses":108,"wins":29},"claude-fable-5-1":{"draws":10,"losses":178,"wins":2},"claude-haiku-5-5":{"draws":30,"losses":55,"wins":35},"claude-opus-4-5":{"draws":148,"losses":192,"wins":52},"claude-opus-4-8":{"draws":58,"losses":102,"wins":24},"claude-opus-5":{"draws":34,"losses":325,"wins":27},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":93,"losses":138,"wins":35},"claude-sonnet-5-5":{"draws":25,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":27,"losses":28,"wins":19},"deepseek/deepseek-v4-flash":{"draws":136,"losses":89,"wins":93},"deepseek/deepseek-v4-pro":{"draws":67,"losses":72,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":71,"losses":66,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":58,"losses":57,"wins":23},"fireworks/ember-1":{"draws":53,"losses":63,"wins":22},"gemini-3.1-pro-preview":{"draws":47,"losses":59,"wins":32},"google/gemini-3.1-flash-lite":{"draws":35,"losses":33,"wins":64},"google/gemini-3.5-flash":{"draws":75,"losses":115,"wins":46},"google/gemini-3.5-flash-lite":{"draws":257,"losses":165,"wins":206},"google/gemini-3.6-flash":{"draws":219,"losses":264,"wins":97},"google/gemini-3.8-flash":{"draws":46,"losses":117,"wins":21},"google/gemma-4-31b-it":{"draws":21,"losses":20,"wins":25},"gpt-4.1":{"draws":24,"losses":30,"wins":20},"gpt-4.1-nano":{"draws":13,"losses":3,"wins":2},"gpt-5":{"draws":67,"losses":57,"wins":58},"gpt-5.4":{"draws":93,"losses":131,"wins":22},"gpt-5.4-mini":{"draws":71,"losses":49,"wins":34},"gpt-5.4-nano":{"draws":74,"losses":73,"wins":85},"gpt-5.5":{"draws":78,"losses":79,"wins":41},"gpt-5.6-luna":{"draws":111,"losses":94,"wins":73},"gpt-5.6-sol":{"draws":47,"losses":211,"wins":10},"gpt-5.6-terra":{"draws":77,"losses":86,"wins":21},"gpt-6-astra":{"draws":18,"losses":156,"wins":0},"gpt-6-luna":{"draws":37,"losses":59,"wins":34},"gpt-6-sol":{"draws":22,"losses":105,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":128,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":64,"losses":34,"wins":40},"inclusionai/ling-3.0-flash":{"draws":102,"losses":30,"wins":76},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":128,"losses":99,"wins":105},"meta/muse-glimmer-30b":{"draws":90,"losses":43,"wins":59},"meta/muse-spark-1.2":{"draws":58,"losses":129,"wins":31},"meta/muse-spark-1.3":{"draws":46,"losses":89,"wins":35},"meta/muse-wonder":{"draws":22,"losses":99,"wins":11},"minimax/minimax-m3":{"draws":46,"losses":38,"wins":48},"mistralai/mistral-large-4-0":{"draws":29,"losses":35,"wins":20},"mistralai/mistral-medium-3-5":{"draws":57,"losses":26,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":17,"wins":28},"moonshotai/kimi-k3":{"draws":100,"losses":137,"wins":31},"nex-agi/nex-n2-pro":{"draws":45,"losses":17,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":87,"losses":41,"wins":48},"o3":{"draws":69,"losses":163,"wins":86},"openai/gpt-oss-120b":{"draws":90,"losses":42,"wins":58},"poolside/laguna-s-2.1":{"draws":110,"losses":71,"wins":71},"qwen/qwen3.7-max":{"draws":50,"losses":48,"wins":32},"qwen/qwen3.7-plus":{"draws":46,"losses":19,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":70,"losses":102,"wins":20},"qwen/qwen3.8-27b":{"draws":29,"losses":54,"wins":23},"qwen/qwen3.8-flash":{"draws":58,"losses":48,"wins":26},"qwen/qwen3.8-max":{"draws":77,"losses":74,"wins":44},"qwen/qwen3.8-max-0902":{"draws":44,"losses":69,"wins":23},"stealth/ox-alpha":{"draws":194,"losses":348,"wins":115},"stealth/space-bunny-alpha":{"draws":33,"losses":40,"wins":33},"stepfun/step-3.7-flash":{"draws":29,"losses":34,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":38,"wins":32},"tencent/hy4-preview":{"draws":68,"losses":93,"wins":35},"thinkingmachines/inkling":{"draws":100,"losses":79,"wins":123},"thinkingmachines/inkling-small":{"draws":97,"losses":29,"wins":87},"unbiased/pareto-26.10-preview":{"draws":0,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":14,"wins":8},"x-ai/grok-4.5":{"draws":95,"losses":184,"wins":51},"x-ai/grok-4.6":{"draws":60,"losses":107,"wins":21},"x-ai/grok-4.7":{"draws":11,"losses":99,"wins":14},"x-ai/grok-build-0.1":{"draws":37,"losses":27,"wins":18},"xiaomi/mimo-v2.5":{"draws":110,"losses":81,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":37,"losses":49,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":51,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":58,"wins":18},"z-ai/glm-5.2":{"draws":192,"losses":130,"wins":98},"z-ai/glm-5.3":{"draws":41,"losses":103,"wins":20},"z-ai/glm-5.3-flash":{"draws":67,"losses":94,"wins":29},"z-ai/glm-5.3-flashx":{"draws":40,"losses":75,"wins":23}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":26,"wins":30},"claude-fable-5":{"draws":15,"losses":58,"wins":13},"claude-fable-5-1":{"draws":3,"losses":90,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":33,"wins":20},"claude-opus-4-5":{"draws":82,"losses":108,"wins":54},"claude-opus-4-8":{"draws":48,"losses":63,"wins":40},"claude-opus-5":{"draws":30,"losses":192,"wins":24},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":28,"losses":44,"wins":18},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":20,"losses":8,"wins":24},"deepseek/deepseek-v4-flash":{"draws":75,"losses":34,"wins":61},"deepseek/deepseek-v4-pro":{"draws":27,"losses":39,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":35,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":34,"wins":19},"fireworks/ember-1":{"draws":26,"losses":39,"wins":19},"gemini-3.1-pro-preview":{"draws":26,"losses":29,"wins":29},"google/gemini-3.1-flash-lite":{"draws":33,"losses":18,"wins":55},"google/gemini-3.5-flash":{"draws":37,"losses":43,"wins":40},"google/gemini-3.5-flash-lite":{"draws":52,"losses":55,"wins":67},"google/gemini-3.6-flash":{"draws":48,"losses":98,"wins":40},"google/gemini-3.8-flash":{"draws":29,"losses":37,"wins":24},"google/gemma-4-31b-it":{"draws":13,"losses":13,"wins":20},"gpt-4.1":{"draws":26,"losses":5,"wins":15},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":54,"losses":48,"wins":26},"gpt-5.4":{"draws":18,"losses":43,"wins":21},"gpt-5.4-mini":{"draws":37,"losses":26,"wins":45},"gpt-5.4-nano":{"draws":51,"losses":54,"wins":71},"gpt-5.5":{"draws":55,"losses":58,"wins":29},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":13,"losses":60,"wins":15},"gpt-5.6-terra":{"draws":29,"losses":47,"wins":18},"gpt-6-astra":{"draws":7,"losses":78,"wins":1},"gpt-6-luna":{"draws":18,"losses":35,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":7,"losses":75,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":15,"wins":26},"inclusionai/ling-3.0-flash":{"draws":56,"losses":13,"wins":43},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":53,"losses":24,"wins":68},"meta/muse-glimmer-30b":{"draws":30,"losses":19,"wins":29},"meta/muse-spark-1.2":{"draws":11,"losses":59,"wins":20},"meta/muse-spark-1.3":{"draws":18,"losses":46,"wins":22},"meta/muse-wonder":{"draws":11,"losses":57,"wins":12},"minimax/minimax-m3":{"draws":41,"losses":20,"wins":45},"mistralai/mistral-large-4-0":{"draws":17,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":26,"losses":4,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":16},"moonshotai/kimi-k3":{"draws":23,"losses":54,"wins":23},"nex-agi/nex-n2-pro":{"draws":26,"losses":10,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":75,"losses":29,"wins":48},"o3":{"draws":37,"losses":66,"wins":51},"openai/gpt-oss-120b":{"draws":29,"losses":18,"wins":31},"poolside/laguna-s-2.1":{"draws":50,"losses":32,"wins":48},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":15},"qwen/qwen3.7-plus":{"draws":33,"losses":24,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":42,"wins":18},"qwen/qwen3.8-27b":{"draws":16,"losses":30,"wins":20},"qwen/qwen3.8-flash":{"draws":27,"losses":26,"wins":25},"qwen/qwen3.8-max":{"draws":38,"losses":30,"wins":24},"qwen/qwen3.8-max-0902":{"draws":25,"losses":40,"wins":17},"stealth/ox-alpha":{"draws":69,"losses":145,"wins":62},"stealth/space-bunny-alpha":{"draws":21,"losses":22,"wins":23},"stepfun/step-3.7-flash":{"draws":18,"losses":13,"wins":41},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":44,"losses":19,"wins":33},"tencent/hy4-preview":{"draws":18,"losses":50,"wins":18},"thinkingmachines/inkling":{"draws":45,"losses":21,"wins":74},"thinkingmachines/inkling-small":{"draws":32,"losses":17,"wins":39},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":14},"x-ai/grok-4.5":{"draws":34,"losses":56,"wins":28},"x-ai/grok-4.6":{"draws":21,"losses":47,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":51,"wins":15},"x-ai/grok-build-0.1":{"draws":27,"losses":22,"wins":15},"xiaomi/mimo-v2.5":{"draws":105,"losses":53,"wins":104},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":23,"wins":47},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":28,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":32,"wins":13},"z-ai/glm-5.2":{"draws":79,"losses":92,"wins":71},"z-ai/glm-5.3":{"draws":21,"losses":44,"wins":15},"z-ai/glm-5.3-flash":{"draws":27,"losses":38,"wins":19},"z-ai/glm-5.3-flashx":{"draws":22,"losses":42,"wins":20}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":24,"wins":20},"claude-fable-5":{"draws":13,"losses":51,"wins":8},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":75,"losses":75,"wins":44},"claude-opus-4-8":{"draws":31,"losses":77,"wins":24},"claude-opus-5":{"draws":24,"losses":129,"wins":15},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":22,"losses":42,"wins":18},"claude-sonnet-5-5":{"draws":17,"losses":43,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":17,"wins":23},"deepseek/deepseek-v4-flash":{"draws":48,"losses":59,"wins":51},"deepseek/deepseek-v4-pro":{"draws":18,"losses":36,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":30,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":40,"wins":7},"fireworks/ember-1":{"draws":23,"losses":38,"wins":11},"gemini-3.1-pro-preview":{"draws":23,"losses":35,"wins":14},"google/gemini-3.1-flash-lite":{"draws":28,"losses":25,"wins":59},"google/gemini-3.5-flash":{"draws":27,"losses":53,"wins":18},"google/gemini-3.5-flash-lite":{"draws":53,"losses":50,"wins":51},"google/gemini-3.6-flash":{"draws":53,"losses":93,"wins":26},"google/gemini-3.8-flash":{"draws":21,"losses":48,"wins":7},"google/gemma-4-31b-it":{"draws":14,"losses":13,"wins":15},"gpt-4.1":{"draws":18,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":30,"losses":43,"wins":17},"gpt-5.4":{"draws":14,"losses":50,"wins":8},"gpt-5.4-mini":{"draws":32,"losses":26,"wins":40},"gpt-5.4-nano":{"draws":36,"losses":63,"wins":65},"gpt-5.5":{"draws":53,"losses":59,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":29,"wins":21},"gpt-5.6-sol":{"draws":15,"losses":53,"wins":8},"gpt-5.6-terra":{"draws":27,"losses":33,"wins":12},"gpt-6-astra":{"draws":3,"losses":71,"wins":0},"gpt-6-luna":{"draws":23,"losses":35,"wins":12},"gpt-6-sol":{"draws":10,"losses":55,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":66,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":12,"wins":28},"inclusionai/ling-3.0-flash":{"draws":42,"losses":27,"wins":31},"meituan/longcat-2.0":{"draws":32,"losses":45,"wins":43},"meta/muse-glimmer-30b":{"draws":29,"losses":23,"wins":16},"meta/muse-spark-1.2":{"draws":16,"losses":53,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":47,"wins":16},"meta/muse-wonder":{"draws":15,"losses":55,"wins":2},"minimax/minimax-m3":{"draws":24,"losses":33,"wins":33},"mistralai/mistral-large-4-0":{"draws":10,"losses":28,"wins":2},"mistralai/mistral-medium-3-5":{"draws":19,"losses":11,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":27,"wins":4},"moonshotai/kimi-k3":{"draws":33,"losses":41,"wins":22},"nex-agi/nex-n2-pro":{"draws":22,"losses":23,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":40,"wins":41},"o3":{"draws":19,"losses":76,"wins":35},"openai/gpt-oss-120b":{"draws":23,"losses":22,"wins":19},"poolside/laguna-s-2.1":{"draws":46,"losses":47,"wins":19},"qwen/qwen3.7-max":{"draws":33,"losses":41,"wins":24},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":38,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":31,"wins":17},"qwen/qwen3.8-flash":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":16},"qwen/qwen3.8-max-0902":{"draws":26,"losses":37,"wins":9},"stealth/ox-alpha":{"draws":47,"losses":142,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":25,"wins":31},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":29,"wins":21},"tencent/hy4-preview":{"draws":18,"losses":41,"wins":11},"thinkingmachines/inkling":{"draws":32,"losses":40,"wins":48},"thinkingmachines/inkling-small":{"draws":28,"losses":24,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":2},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":26,"losses":65,"wins":11},"x-ai/grok-4.6":{"draws":21,"losses":45,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":53,"wins":7},"x-ai/grok-build-0.1":{"draws":17,"losses":13,"wins":22},"xiaomi/mimo-v2.5":{"draws":88,"losses":69,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":42,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":29,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":73,"losses":101,"wins":40},"z-ai/glm-5.3":{"draws":15,"losses":46,"wins":6},"z-ai/glm-5.3-flash":{"draws":23,"losses":45,"wins":10},"z-ai/glm-5.3-flashx":{"draws":17,"losses":45,"wins":10}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":73,"losses":49,"wins":100},"claude-fable-5":{"draws":68,"losses":123,"wins":64},"claude-fable-5-1":{"draws":27,"losses":250,"wins":13},"claude-haiku-5-5":{"draws":34,"losses":55,"wins":43},"claude-opus-4-5":{"draws":117,"losses":82,"wins":117},"claude-opus-4-8":{"draws":48,"losses":46,"wins":54},"claude-opus-5":{"draws":35,"losses":199,"wins":46},"claude-opus-5-5":{"draws":11,"losses":127,"wins":18},"claude-sonnet-5":{"draws":94,"losses":66,"wins":102},"claude-sonnet-5-5":{"draws":32,"losses":63,"wins":49},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":41},"deepseek/deepseek-v4-flash":{"draws":103,"losses":56,"wins":159},"deepseek/deepseek-v4-pro":{"draws":72,"losses":64,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":67,"losses":75,"wins":88},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":58,"wins":50},"fireworks/ember-1":{"draws":50,"losses":47,"wins":47},"gemini-3.1-pro-preview":{"draws":36,"losses":46,"wins":62},"google/gemini-3.1-flash-lite":{"draws":29,"losses":3,"wins":70},"google/gemini-3.5-flash":{"draws":79,"losses":96,"wins":117},"google/gemini-3.5-flash-lite":{"draws":145,"losses":78,"wins":207},"google/gemini-3.6-flash":{"draws":118,"losses":166,"wins":148},"google/gemini-3.8-flash":{"draws":63,"losses":116,"wins":79},"google/gemma-4-31b-it":{"draws":27,"losses":10,"wins":41},"gpt-4.1":{"draws":20,"losses":6,"wins":24},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":40,"losses":36,"wins":58},"gpt-5.4":{"draws":57,"losses":93,"wins":96},"gpt-5.4-mini":{"draws":34,"losses":13,"wins":51},"gpt-5.4-nano":{"draws":41,"losses":32,"wins":89},"gpt-5.5":{"draws":44,"losses":49,"wins":45},"gpt-5.6-luna":{"draws":95,"losses":49,"wins":98},"gpt-5.6-sol":{"draws":48,"losses":149,"wins":67},"gpt-5.6-terra":{"draws":94,"losses":53,"wins":109},"gpt-6-astra":{"draws":14,"losses":227,"wins":13},"gpt-6-luna":{"draws":36,"losses":48,"wins":54},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":11,"losses":113,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":67,"losses":13,"wins":84},"inclusionai/ling-3.0-flash":{"draws":48,"losses":7,"wins":75},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":54,"losses":30,"wins":122},"meta/muse-glimmer-30b":{"draws":87,"losses":27,"wins":98},"meta/muse-spark-1.2":{"draws":55,"losses":64,"wins":83},"meta/muse-spark-1.3":{"draws":58,"losses":85,"wins":81},"meta/muse-wonder":{"draws":26,"losses":72,"wins":38},"minimax/minimax-m3":{"draws":22,"losses":9,"wins":53},"mistralai/mistral-large-4-0":{"draws":20,"losses":26,"wins":36},"mistralai/mistral-medium-3-5":{"draws":48,"losses":6,"wins":94},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":9,"wins":16},"moonshotai/kimi-k3":{"draws":65,"losses":80,"wins":75},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":15,"wins":65},"o3":{"draws":43,"losses":91,"wins":152},"openai/gpt-oss-120b":{"draws":84,"losses":18,"wins":106},"poolside/laguna-s-2.1":{"draws":70,"losses":20,"wins":102},"qwen/qwen3.7-max":{"draws":32,"losses":18,"wins":42},"qwen/qwen3.7-plus":{"draws":29,"losses":11,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":58,"wins":58},"qwen/qwen3.8-27b":{"draws":47,"losses":33,"wins":48},"qwen/qwen3.8-flash":{"draws":49,"losses":52,"wins":69},"qwen/qwen3.8-max":{"draws":84,"losses":83,"wins":87},"qwen/qwen3.8-max-0902":{"draws":45,"losses":53,"wins":42},"stealth/ox-alpha":{"draws":228,"losses":312,"wins":292},"stealth/space-bunny-alpha":{"draws":40,"losses":27,"wins":47},"stepfun/step-3.7-flash":{"draws":18,"losses":15,"wins":67},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":30,"losses":18,"wins":36},"tencent/hy4-preview":{"draws":72,"losses":97,"wins":75},"thinkingmachines/inkling":{"draws":67,"losses":29,"wins":110},"thinkingmachines/inkling-small":{"draws":86,"losses":31,"wins":139},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":58,"losses":90,"wins":74},"x-ai/grok-4.6":{"draws":67,"losses":104,"wins":87},"x-ai/grok-4.7":{"draws":10,"losses":86,"wins":30},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":93,"losses":29,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":39,"wins":29},"z-ai/glm-5.2":{"draws":146,"losses":97,"wins":151},"z-ai/glm-5.3":{"draws":50,"losses":113,"wins":45},"z-ai/glm-5.3-flash":{"draws":60,"losses":97,"wins":87},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":29,"wins":60},"claude-fable-5":{"draws":23,"losses":83,"wins":26},"claude-fable-5-1":{"draws":7,"losses":139,"wins":2},"claude-haiku-5-5":{"draws":21,"losses":45,"wins":28},"claude-opus-4-5":{"draws":54,"losses":55,"wins":81},"claude-opus-4-8":{"draws":21,"losses":42,"wins":31},"claude-opus-5":{"draws":28,"losses":131,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":30,"losses":47,"wins":53},"claude-sonnet-5-5":{"draws":17,"losses":60,"wins":25},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":24},"deepseek/deepseek-v4-flash":{"draws":41,"losses":45,"wins":94},"deepseek/deepseek-v4-pro":{"draws":27,"losses":41,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":40,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":49,"wins":29},"fireworks/ember-1":{"draws":29,"losses":35,"wins":38},"gemini-3.1-pro-preview":{"draws":23,"losses":32,"wins":47},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":48},"google/gemini-3.5-flash":{"draws":29,"losses":60,"wins":61},"google/gemini-3.5-flash-lite":{"draws":40,"losses":50,"wins":130},"google/gemini-3.6-flash":{"draws":43,"losses":100,"wins":79},"google/gemini-3.8-flash":{"draws":21,"losses":73,"wins":36},"google/gemma-4-31b-it":{"draws":17,"losses":10,"wins":27},"gpt-4.1":{"draws":9,"losses":13,"wins":14},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":6},"gpt-5":{"draws":18,"losses":34,"wins":42},"gpt-5.4":{"draws":27,"losses":70,"wins":29},"gpt-5.4-mini":{"draws":17,"losses":19,"wins":32},"gpt-5.4-nano":{"draws":23,"losses":34,"wins":49},"gpt-5.5":{"draws":28,"losses":44,"wins":26},"gpt-5.6-luna":{"draws":37,"losses":32,"wins":55},"gpt-5.6-sol":{"draws":20,"losses":85,"wins":31},"gpt-5.6-terra":{"draws":44,"losses":41,"wins":41},"gpt-6-astra":{"draws":4,"losses":129,"wins":1},"gpt-6-luna":{"draws":26,"losses":41,"wins":35},"gpt-6-sol":{"draws":17,"losses":71,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":23,"losses":8,"wins":55},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":54},"meituan/longcat-2.0":{"draws":23,"losses":21,"wins":78},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":24,"losses":39,"wins":51},"meta/muse-spark-1.3":{"draws":21,"losses":55,"wins":42},"meta/muse-wonder":{"draws":18,"losses":68,"wins":14},"minimax/minimax-m3":{"draws":14,"losses":8,"wins":32},"mistralai/mistral-large-4-0":{"draws":17,"losses":22,"wins":21},"mistralai/mistral-medium-3-5":{"draws":21,"losses":5,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":13},"moonshotai/kimi-k3":{"draws":31,"losses":53,"wins":30},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":19,"wins":43},"o3":{"draws":17,"losses":68,"wins":91},"openai/gpt-oss-120b":{"draws":22,"losses":21,"wins":63},"poolside/laguna-s-2.1":{"draws":29,"losses":23,"wins":54},"qwen/qwen3.7-max":{"draws":16,"losses":20,"wins":30},"qwen/qwen3.7-plus":{"draws":12,"losses":17,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":48,"wins":33},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":21,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":39,"losses":45,"wins":44},"qwen/qwen3.8-max-0902":{"draws":26,"losses":49,"wins":27},"stealth/ox-alpha":{"draws":89,"losses":180,"wins":149},"stealth/space-bunny-alpha":{"draws":21,"losses":20,"wins":39},"stepfun/step-3.7-flash":{"draws":13,"losses":26,"wins":37},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":32},"tencent/hy4-preview":{"draws":30,"losses":56,"wins":38},"thinkingmachines/inkling":{"draws":28,"losses":26,"wins":74},"thinkingmachines/inkling-small":{"draws":33,"losses":17,"wins":80},"unbiased/pareto-26.10-preview":{"draws":0,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":24,"losses":68,"wins":30},"x-ai/grok-4.6":{"draws":32,"losses":64,"wins":38},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":20},"xiaomi/mimo-v2.5":{"draws":46,"losses":29,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":22,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":26,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":34,"wins":20},"z-ai/glm-5.2":{"draws":72,"losses":77,"wins":81},"z-ai/glm-5.3":{"draws":30,"losses":70,"wins":18},"z-ai/glm-5.3-flash":{"draws":27,"losses":60,"wins":47},"z-ai/glm-5.3-flashx":{"draws":24,"losses":53,"wins":25}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":36,"wins":65},"claude-fable-5":{"draws":45,"losses":85,"wins":28},"claude-fable-5-1":{"draws":10,"losses":157,"wins":7},"claude-haiku-5-5":{"draws":24,"losses":45,"wins":19},"claude-opus-4-5":{"draws":73,"losses":72,"wins":63},"claude-opus-4-8":{"draws":34,"losses":42,"wins":20},"claude-opus-5":{"draws":28,"losses":136,"wins":16},"claude-opus-5-5":{"draws":9,"losses":92,"wins":3},"claude-sonnet-5":{"draws":58,"losses":59,"wins":53},"claude-sonnet-5-5":{"draws":17,"losses":49,"wins":30},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":18},"deepseek/deepseek-v4-flash":{"draws":77,"losses":46,"wins":89},"deepseek/deepseek-v4-pro":{"draws":46,"losses":51,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":59,"losses":45,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":41,"wins":19},"fireworks/ember-1":{"draws":34,"losses":35,"wins":27},"gemini-3.1-pro-preview":{"draws":36,"losses":30,"wins":30},"google/gemini-3.1-flash-lite":{"draws":28,"losses":10,"wins":34},"google/gemini-3.5-flash":{"draws":66,"losses":78,"wins":54},"google/gemini-3.5-flash-lite":{"draws":112,"losses":49,"wins":125},"google/gemini-3.6-flash":{"draws":112,"losses":112,"wins":68},"google/gemini-3.8-flash":{"draws":42,"losses":81,"wins":43},"google/gemma-4-31b-it":{"draws":25,"losses":6,"wins":23},"gpt-4.1":{"draws":12,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":31,"losses":32,"wins":31},"gpt-5.4":{"draws":44,"losses":65,"wins":45},"gpt-5.4-mini":{"draws":25,"losses":13,"wins":26},"gpt-5.4-nano":{"draws":31,"losses":29,"wins":46},"gpt-5.5":{"draws":37,"losses":42,"wins":21},"gpt-5.6-luna":{"draws":60,"losses":50,"wins":62},"gpt-5.6-sol":{"draws":35,"losses":94,"wins":35},"gpt-5.6-terra":{"draws":52,"losses":52,"wins":50},"gpt-6-astra":{"draws":22,"losses":131,"wins":5},"gpt-6-luna":{"draws":26,"losses":35,"wins":33},"gpt-6-sol":{"draws":9,"losses":69,"wins":18},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":60,"losses":12,"wins":52},"inclusionai/ling-3.0-flash":{"draws":35,"losses":11,"wins":50},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":56,"losses":28,"wins":60},"meta/muse-glimmer-30b":{"draws":67,"losses":39,"wins":38},"meta/muse-spark-1.2":{"draws":40,"losses":56,"wins":44},"meta/muse-spark-1.3":{"draws":41,"losses":65,"wins":42},"meta/muse-wonder":{"draws":24,"losses":57,"wins":11},"minimax/minimax-m3":{"draws":17,"losses":19,"wins":28},"mistralai/mistral-large-4-0":{"draws":17,"losses":20,"wins":17},"mistralai/mistral-medium-3-5":{"draws":39,"losses":11,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":10,"wins":11},"moonshotai/kimi-k3":{"draws":51,"losses":52,"wins":43},"nex-agi/nex-n2-pro":{"draws":24,"losses":6,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":18,"wins":33},"o3":{"draws":40,"losses":71,"wins":79},"openai/gpt-oss-120b":{"draws":56,"losses":36,"wins":50},"poolside/laguna-s-2.1":{"draws":58,"losses":26,"wins":48},"qwen/qwen3.7-max":{"draws":27,"losses":25,"wins":26},"qwen/qwen3.7-plus":{"draws":21,"losses":22,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":69,"wins":52},"qwen/qwen3.8-27b":{"draws":21,"losses":31,"wins":32},"qwen/qwen3.8-flash":{"draws":32,"losses":10,"wins":10},"qwen/qwen3.8-max":{"draws":63,"losses":55,"wins":46},"qwen/qwen3.8-max-0902":{"draws":32,"losses":33,"wins":29},"stealth/ox-alpha":{"draws":157,"losses":205,"wins":173},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":30},"stepfun/step-3.7-flash":{"draws":16,"losses":13,"wins":41},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":15,"wins":24},"tencent/hy4-preview":{"draws":45,"losses":66,"wins":49},"thinkingmachines/inkling":{"draws":46,"losses":27,"wins":65},"thinkingmachines/inkling-small":{"draws":81,"losses":30,"wins":61},"unbiased/pareto-26.10-preview":{"draws":2,"losses":26,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":35,"losses":63,"wins":36},"x-ai/grok-4.6":{"draws":63,"losses":71,"wins":32},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":65,"losses":30,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":18,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":22,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":31,"wins":16},"z-ai/glm-5.2":{"draws":101,"losses":69,"wins":86},"z-ai/glm-5.3":{"draws":44,"losses":71,"wins":25},"z-ai/glm-5.3-flash":{"draws":52,"losses":58,"wins":54},"z-ai/glm-5.3-flashx":{"draws":32,"losses":42,"wins":22}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":84,"losses":67,"wins":87},"claude-fable-5":{"draws":41,"losses":131,"wins":70},"claude-fable-5-1":{"draws":14,"losses":246,"wins":8},"claude-haiku-5-5":{"draws":32,"losses":63,"wins":35},"claude-opus-4-5":{"draws":101,"losses":88,"wins":140},"claude-opus-4-8":{"draws":30,"losses":65,"wins":49},"claude-opus-5":{"draws":39,"losses":195,"wins":32},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":81,"losses":82,"wins":102},"claude-sonnet-5-5":{"draws":23,"losses":80,"wins":41},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":40},"deepseek/deepseek-v4-flash":{"draws":109,"losses":58,"wins":151},"deepseek/deepseek-v4-pro":{"draws":67,"losses":65,"wins":102},"deepseek/deepseek-v4-pro-0813":{"draws":79,"losses":69,"wins":86},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":55,"wins":48},"fireworks/ember-1":{"draws":46,"losses":57,"wins":41},"gemini-3.1-pro-preview":{"draws":43,"losses":47,"wins":54},"google/gemini-3.1-flash-lite":{"draws":29,"losses":1,"wins":66},"google/gemini-3.5-flash":{"draws":90,"losses":101,"wins":87},"google/gemini-3.5-flash-lite":{"draws":152,"losses":95,"wins":190},"google/gemini-3.6-flash":{"draws":125,"losses":171,"wins":155},"google/gemini-3.8-flash":{"draws":68,"losses":101,"wins":81},"google/gemma-4-31b-it":{"draws":27,"losses":8,"wins":41},"gpt-4.1":{"draws":23,"losses":13,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":43,"losses":29,"wins":56},"gpt-5.4":{"draws":76,"losses":92,"wins":84},"gpt-5.4-mini":{"draws":47,"losses":19,"wins":40},"gpt-5.4-nano":{"draws":36,"losses":37,"wins":77},"gpt-5.5":{"draws":44,"losses":51,"wins":43},"gpt-5.6-luna":{"draws":90,"losses":54,"wins":106},"gpt-5.6-sol":{"draws":50,"losses":146,"wins":61},"gpt-5.6-terra":{"draws":106,"losses":66,"wins":80},"gpt-6-astra":{"draws":26,"losses":210,"wins":4},"gpt-6-luna":{"draws":36,"losses":50,"wins":52},"gpt-6-sol":{"draws":17,"losses":99,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":124,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":80,"losses":16,"wins":78},"inclusionai/ling-3.0-flash":{"draws":54,"losses":21,"wins":62},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":70,"losses":39,"wins":108},"meta/muse-glimmer-30b":{"draws":69,"losses":47,"wins":90},"meta/muse-spark-1.2":{"draws":58,"losses":65,"wins":82},"meta/muse-spark-1.3":{"draws":54,"losses":102,"wins":56},"meta/muse-wonder":{"draws":28,"losses":76,"wins":28},"minimax/minimax-m3":{"draws":25,"losses":14,"wins":41},"mistralai/mistral-large-4-0":{"draws":23,"losses":30,"wins":27},"mistralai/mistral-medium-3-5":{"draws":50,"losses":17,"wins":79},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":58,"losses":78,"wins":77},"nex-agi/nex-n2-pro":{"draws":23,"losses":6,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":60},"o3":{"draws":53,"losses":99,"wins":148},"openai/gpt-oss-120b":{"draws":81,"losses":17,"wins":112},"poolside/laguna-s-2.1":{"draws":77,"losses":44,"wins":74},"qwen/qwen3.7-max":{"draws":38,"losses":24,"wins":30},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":84,"losses":87,"wins":83},"qwen/qwen3.8-27b":{"draws":39,"losses":44,"wins":45},"qwen/qwen3.8-flash":{"draws":63,"losses":46,"wins":55},"qwen/qwen3.8-max":{"draws":76,"losses":88,"wins":88},"qwen/qwen3.8-max-0902":{"draws":32,"losses":63,"wins":43},"stealth/ox-alpha":{"draws":224,"losses":320,"wins":281},"stealth/space-bunny-alpha":{"draws":37,"losses":31,"wins":46},"stepfun/step-3.7-flash":{"draws":27,"losses":17,"wins":58},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":30,"losses":13,"wins":35},"tencent/hy4-preview":{"draws":61,"losses":105,"wins":76},"thinkingmachines/inkling":{"draws":65,"losses":34,"wins":101},"thinkingmachines/inkling-small":{"draws":136,"losses":102,"wins":153},"unbiased/pareto-26.10-preview":{"draws":1,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":22},"x-ai/grok-4.5":{"draws":60,"losses":99,"wins":74},"x-ai/grok-4.6":{"draws":72,"losses":113,"wins":77},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":21,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":86,"losses":43,"wins":105},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":23,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":38,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":49,"wins":18},"z-ai/glm-5.2":{"draws":139,"losses":104,"wins":149},"z-ai/glm-5.3":{"draws":51,"losses":104,"wins":53},"z-ai/glm-5.3-flash":{"draws":70,"losses":87,"wins":89},"z-ai/glm-5.3-flashx":{"draws":40,"losses":56,"wins":48}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":18,"wins":73},"claude-fable-5":{"draws":28,"losses":80,"wins":34},"claude-fable-5-1":{"draws":5,"losses":139,"wins":16},"claude-haiku-5-5":{"draws":39,"losses":48,"wins":47},"claude-opus-4-5":{"draws":65,"losses":77,"wins":90},"claude-opus-4-8":{"draws":34,"losses":46,"wins":46},"claude-opus-5":{"draws":35,"losses":165,"wins":42},"claude-opus-5-5":{"draws":16,"losses":123,"wins":11},"claude-sonnet-5":{"draws":38,"losses":34,"wins":66},"claude-sonnet-5-5":{"draws":24,"losses":63,"wins":51},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":38},"deepseek/deepseek-v4-flash":{"draws":58,"losses":28,"wins":122},"deepseek/deepseek-v4-pro":{"draws":35,"losses":32,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":38,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":50,"wins":45},"fireworks/ember-1":{"draws":44,"losses":43,"wins":57},"gemini-3.1-pro-preview":{"draws":37,"losses":35,"wins":66},"google/gemini-3.1-flash-lite":{"draws":27,"losses":2,"wins":63},"google/gemini-3.5-flash":{"draws":48,"losses":45,"wins":83},"google/gemini-3.5-flash-lite":{"draws":73,"losses":35,"wins":134},"google/gemini-3.6-flash":{"draws":59,"losses":88,"wins":95},"google/gemini-3.8-flash":{"draws":36,"losses":59,"wins":45},"google/gemma-4-31b-it":{"draws":25,"losses":9,"wins":46},"gpt-4.1":{"draws":18,"losses":7,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":32,"losses":30,"wins":58},"gpt-5.4":{"draws":32,"losses":58,"wins":44},"gpt-5.4-mini":{"draws":36,"losses":14,"wins":44},"gpt-5.4-nano":{"draws":38,"losses":31,"wins":69},"gpt-5.5":{"draws":44,"losses":41,"wins":43},"gpt-5.6-luna":{"draws":49,"losses":32,"wins":61},"gpt-5.6-sol":{"draws":21,"losses":84,"wins":34},"gpt-5.6-terra":{"draws":46,"losses":37,"wins":53},"gpt-6-astra":{"draws":9,"losses":127,"wins":6},"gpt-6-luna":{"draws":38,"losses":44,"wins":54},"gpt-6-sol":{"draws":16,"losses":96,"wins":28},"gpt-6.1-sol":{"draws":12,"losses":119,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":40,"losses":10,"wins":48},"inclusionai/ling-3.0-flash":{"draws":35,"losses":9,"wins":52},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":23,"wins":95},"meta/muse-glimmer-30b":{"draws":46,"losses":12,"wins":66},"meta/muse-spark-1.2":{"draws":29,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":36,"losses":49,"wins":53},"meta/muse-wonder":{"draws":31,"losses":71,"wins":32},"minimax/minimax-m3":{"draws":20,"losses":8,"wins":46},"mistralai/mistral-large-4-0":{"draws":30,"losses":18,"wins":40},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":32,"wins":66},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":12,"wins":63},"o3":{"draws":34,"losses":62,"wins":96},"openai/gpt-oss-120b":{"draws":41,"losses":13,"wins":70},"poolside/laguna-s-2.1":{"draws":44,"losses":23,"wins":69},"qwen/qwen3.7-max":{"draws":25,"losses":17,"wins":40},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":42,"wins":53},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":49},"qwen/qwen3.8-flash":{"draws":32,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":32,"losses":43,"wins":63},"qwen/qwen3.8-max-0902":{"draws":18,"losses":35,"wins":35},"stealth/ox-alpha":{"draws":108,"losses":169,"wins":181},"stealth/space-bunny-alpha":{"draws":32,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":24,"losses":19,"wins":55},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":25,"losses":13,"wins":36},"tencent/hy4-preview":{"draws":32,"losses":52,"wins":50},"thinkingmachines/inkling":{"draws":43,"losses":19,"wins":98},"thinkingmachines/inkling-small":{"draws":47,"losses":15,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":59,"wins":52},"x-ai/grok-4.6":{"draws":41,"losses":63,"wins":34},"x-ai/grok-4.7":{"draws":18,"losses":77,"wins":27},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":79,"losses":27,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":39,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":46,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":55,"wins":133},"z-ai/glm-5.3":{"draws":33,"losses":69,"wins":30},"z-ai/glm-5.3-flash":{"draws":39,"losses":52,"wins":49},"z-ai/glm-5.3-flashx":{"draws":33,"losses":57,"wins":50}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":176,"losses":154,"wins":400},"claude-fable-5":{"draws":172,"losses":469,"wins":185},"claude-fable-5-1":{"draws":78,"losses":849,"wins":49},"claude-haiku-5-5":{"draws":94,"losses":165,"wins":153},"claude-opus-4-5":{"draws":292,"losses":302,"wins":441},"claude-opus-4-8":{"draws":100,"losses":157,"wins":167},"claude-opus-5":{"draws":137,"losses":642,"wins":134},"claude-opus-5-5":{"draws":49,"losses":421,"wins":30},"claude-sonnet-5":{"draws":203,"losses":242,"wins":410},"claude-sonnet-5-5":{"draws":85,"losses":222,"wins":161},"cohere/north-mini-code":{"draws":31,"losses":22,"wins":121},"deepseek/deepseek-v4-flash":{"draws":275,"losses":195,"wins":535},"deepseek/deepseek-v4-pro":{"draws":210,"losses":231,"wins":317},"deepseek/deepseek-v4-pro-0813":{"draws":204,"losses":259,"wins":295},"deepseek/deepseek-v4.1-flash":{"draws":111,"losses":178,"wins":179},"fireworks/ember-1":{"draws":126,"losses":167,"wins":175},"gemini-3.1-pro-preview":{"draws":107,"losses":144,"wins":217},"google/gemini-3.1-flash-lite":{"draws":56,"losses":31,"wins":196},"google/gemini-3.5-flash":{"draws":203,"losses":328,"wins":390},"google/gemini-3.5-flash-lite":{"draws":338,"losses":290,"wins":755},"google/gemini-3.6-flash":{"draws":299,"losses":550,"wins":531},"google/gemini-3.8-flash":{"draws":185,"losses":391,"wins":274},"google/gemma-4-31b-it":{"draws":52,"losses":40,"wins":144},"gpt-4.1":{"draws":49,"losses":36,"wins":77},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":32},"gpt-5":{"draws":107,"losses":128,"wins":205},"gpt-5.4":{"draws":246,"losses":311,"wins":250},"gpt-5.4-mini":{"draws":95,"losses":65,"wins":164},"gpt-5.4-nano":{"draws":85,"losses":120,"wins":245},"gpt-5.5":{"draws":129,"losses":159,"wins":168},"gpt-5.6-luna":{"draws":260,"losses":185,"wins":350},"gpt-5.6-sol":{"draws":128,"losses":508,"wins":217},"gpt-5.6-terra":{"draws":248,"losses":221,"wins":317},"gpt-6-astra":{"draws":93,"losses":703,"wins":44},"gpt-6-luna":{"draws":109,"losses":151,"wins":202},"gpt-6-sol":{"draws":62,"losses":334,"wins":72},"gpt-6.1-sol":{"draws":43,"losses":395,"wins":30},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":170,"losses":62,"wins":271},"inclusionai/ling-3.0-flash":{"draws":105,"losses":39,"wins":246},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":160,"losses":95,"wins":401},"meta/muse-glimmer-30b":{"draws":191,"losses":102,"wins":393},"meta/muse-spark-1.2":{"draws":162,"losses":204,"wins":309},"meta/muse-spark-1.3":{"draws":146,"losses":294,"wins":256},"meta/muse-wonder":{"draws":91,"losses":237,"wins":118},"minimax/minimax-m3":{"draws":64,"losses":41,"wins":153},"mistralai/mistral-large-4-0":{"draws":84,"losses":80,"wins":106},"mistralai/mistral-medium-3-5":{"draws":130,"losses":68,"wins":256},"moonshotai/kimi-k2.7-code":{"draws":25,"losses":31,"wins":50},"moonshotai/kimi-k3":{"draws":181,"losses":244,"wins":282},"nex-agi/nex-n2-pro":{"draws":63,"losses":31,"wins":168},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":112,"losses":60,"wins":210},"o3":{"draws":119,"losses":329,"wins":423},"openai/gpt-oss-120b":{"draws":196,"losses":98,"wins":388},"poolside/laguna-s-2.1":{"draws":194,"losses":115,"wins":348},"qwen/qwen3.7-max":{"draws":69,"losses":62,"wins":145},"qwen/qwen3.7-plus":{"draws":47,"losses":27,"wins":142},"qwen/qwen3.8-2.4t-a95b":{"draws":228,"losses":292,"wins":312},"qwen/qwen3.8-27b":{"draws":89,"losses":149,"wins":180},"qwen/qwen3.8-flash":{"draws":157,"losses":173,"wins":205},"qwen/qwen3.8-max":{"draws":224,"losses":281,"wins":320},"qwen/qwen3.8-max-0902":{"draws":108,"losses":181,"wins":169},"stealth/ox-alpha":{"draws":630,"losses":1220,"wins":1220},"stealth/space-bunny-alpha":{"draws":99,"losses":83,"wins":184},"stepfun/step-3.7-flash":{"draws":51,"losses":58,"wins":217},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":81,"losses":52,"wins":121},"tencent/hy4-preview":{"draws":195,"losses":338,"wins":266},"thinkingmachines/inkling":{"draws":176,"losses":113,"wins":405},"thinkingmachines/inkling-small":{"draws":255,"losses":123,"wins":436},"unbiased/pareto-26.10-preview":{"draws":9,"losses":131,"wins":6},"upstage/solar-mini4":{"draws":13,"losses":15,"wins":74},"x-ai/grok-4.5":{"draws":157,"losses":315,"wins":238},"x-ai/grok-4.6":{"draws":245,"losses":343,"wins":262},"x-ai/grok-4.7":{"draws":48,"losses":279,"wins":69},"x-ai/grok-build-0.1":{"draws":44,"losses":19,"wins":105},"xiaomi/mimo-v2.5":{"draws":179,"losses":96,"wins":403},"xiaomi/mimo-v2.5-pro":{"draws":51,"losses":69,"wins":144},"xiaomi/mimo-v2.6-flash":{"draws":57,"losses":107,"wins":130},"xiaomi/mimo-v2.6-pro":{"draws":57,"losses":143,"wins":102},"z-ai/glm-5.2":{"draws":364,"losses":301,"wins":615},"z-ai/glm-5.3":{"draws":141,"losses":354,"wins":191},"z-ai/glm-5.3-flash":{"draws":181,"losses":349,"wins":309},"z-ai/glm-5.3-flashx":{"draws":85,"losses":216,"wins":167}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":31,"wins":38},"claude-fable-5":{"draws":31,"losses":68,"wins":15},"claude-fable-5-1":{"draws":6,"losses":121,"wins":3},"claude-haiku-5-5":{"draws":30,"losses":49,"wins":23},"claude-opus-4-5":{"draws":58,"losses":79,"wins":49},"claude-opus-4-8":{"draws":30,"losses":52,"wins":24},"claude-opus-5":{"draws":29,"losses":153,"wins":14},"claude-opus-5-5":{"draws":5,"losses":116,"wins":1},"claude-sonnet-5":{"draws":30,"losses":47,"wins":37},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":24},"cohere/north-mini-code":{"draws":9,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":60,"losses":38,"wins":70},"deepseek/deepseek-v4-pro":{"draws":31,"losses":47,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":47,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":53,"wins":25},"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":21,"losses":12,"wins":47},"google/gemini-3.5-flash":{"draws":43,"losses":68,"wins":33},"google/gemini-3.5-flash-lite":{"draws":58,"losses":60,"wins":84},"google/gemini-3.6-flash":{"draws":55,"losses":106,"wins":41},"google/gemini-3.8-flash":{"draws":31,"losses":66,"wins":17},"google/gemma-4-31b-it":{"draws":22,"losses":14,"wins":26},"gpt-4.1":{"draws":15,"losses":10,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":26,"losses":39,"wins":35},"gpt-5.4":{"draws":34,"losses":60,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":39,"wins":47},"gpt-5.5":{"draws":41,"losses":46,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":31,"wins":40},"gpt-5.6-sol":{"draws":20,"losses":80,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":37,"losses":50,"wins":23},"gpt-6-sol":{"draws":16,"losses":87,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":37,"losses":10,"wins":35},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":31},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":29,"wins":56},"meta/muse-glimmer-30b":{"draws":39,"losses":27,"wins":36},"meta/muse-spark-1.2":{"draws":31,"losses":51,"wins":26},"meta/muse-spark-1.3":{"draws":24,"losses":69,"wins":21},"meta/muse-wonder":{"draws":27,"losses":61,"wins":18},"minimax/minimax-m3":{"draws":18,"losses":13,"wins":31},"mistralai/mistral-large-4-0":{"draws":23,"losses":31,"wins":14},"mistralai/mistral-medium-3-5":{"draws":24,"losses":12,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":37,"losses":51,"wins":18},"nex-agi/nex-n2-pro":{"draws":17,"losses":13,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":25,"wins":32},"o3":{"draws":26,"losses":76,"wins":56},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":44},"poolside/laguna-s-2.1":{"draws":33,"losses":33,"wins":40},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.7-plus":{"draws":18,"losses":9,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":27},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":28,"losses":30,"wins":18},"qwen/qwen3.8-max":{"draws":37,"losses":46,"wins":31},"qwen/qwen3.8-max-0902":{"draws":32,"losses":59,"wins":19},"stealth/ox-alpha":{"draws":99,"losses":184,"wins":83},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":18},"stepfun/step-3.7-flash":{"draws":21,"losses":23,"wins":36},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":21},"tencent/hy4-preview":{"draws":33,"losses":51,"wins":26},"thinkingmachines/inkling":{"draws":44,"losses":34,"wins":54},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":47},"unbiased/pareto-26.10-preview":{"draws":1,"losses":35,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":16},"x-ai/grok-4.5":{"draws":31,"losses":63,"wins":20},"x-ai/grok-4.6":{"draws":36,"losses":59,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":16},"xiaomi/mimo-v2.5":{"draws":71,"losses":38,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":36,"wins":19},"z-ai/glm-5.2":{"draws":89,"losses":74,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":72,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":67,"wins":17},"z-ai/glm-5.3-flashx":{"draws":33,"losses":59,"wins":22}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":42,"wins":33},"claude-fable-5":{"draws":15,"losses":79,"wins":8},"claude-fable-5-1":{"draws":3,"losses":109,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":66,"wins":16},"claude-opus-4-5":{"draws":36,"losses":111,"wins":45},"claude-opus-4-8":{"draws":16,"losses":72,"wins":22},"claude-opus-5":{"draws":14,"losses":153,"wins":7},"claude-opus-5-5":{"draws":4,"losses":98,"wins":0},"claude-sonnet-5":{"draws":24,"losses":49,"wins":31},"claude-sonnet-5-5":{"draws":11,"losses":61,"wins":26},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":25},"deepseek/deepseek-v4-flash":{"draws":43,"losses":64,"wins":69},"deepseek/deepseek-v4-pro":{"draws":21,"losses":50,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":51,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":58,"wins":16},"fireworks/ember-1":{"draws":21,"losses":59,"wins":18},"gemini-3.1-pro-preview":{"draws":23,"losses":45,"wins":32},"google/gemini-3.1-flash-lite":{"draws":18,"losses":13,"wins":69},"google/gemini-3.5-flash":{"draws":24,"losses":78,"wins":28},"google/gemini-3.5-flash-lite":{"draws":53,"losses":76,"wins":63},"google/gemini-3.6-flash":{"draws":40,"losses":128,"wins":29},"google/gemini-3.8-flash":{"draws":19,"losses":72,"wins":9},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":27},"gpt-4.1":{"draws":11,"losses":25,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":31,"losses":64,"wins":19},"gpt-5.4":{"draws":24,"losses":61,"wins":15},"gpt-5.4-mini":{"draws":28,"losses":23,"wins":25},"gpt-5.4-nano":{"draws":20,"losses":65,"wins":43},"gpt-5.5":{"draws":26,"losses":69,"wins":15},"gpt-5.6-luna":{"draws":26,"losses":41,"wins":33},"gpt-5.6-sol":{"draws":11,"losses":81,"wins":8},"gpt-5.6-terra":{"draws":28,"losses":50,"wins":20},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":18,"losses":55,"wins":23},"gpt-6-sol":{"draws":13,"losses":81,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":97,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":8,"wins":40},"inclusionai/ling-3.0-flash":{"draws":28,"losses":18,"wins":36},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":44,"wins":53},"meta/muse-glimmer-30b":{"draws":22,"losses":41,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":58,"wins":23},"meta/muse-spark-1.3":{"draws":12,"losses":83,"wins":13},"meta/muse-wonder":{"draws":12,"losses":78,"wins":10},"minimax/minimax-m3":{"draws":12,"losses":30,"wins":18},"mistralai/mistral-large-4-0":{"draws":18,"losses":33,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":12,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":15,"wins":7},"moonshotai/kimi-k3":{"draws":22,"losses":57,"wins":15},"nex-agi/nex-n2-pro":{"draws":16,"losses":19,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":38,"wins":44},"o3":{"draws":31,"losses":111,"wins":52},"openai/gpt-oss-120b":{"draws":29,"losses":19,"wins":36},"poolside/laguna-s-2.1":{"draws":29,"losses":33,"wins":34},"qwen/qwen3.7-max":{"draws":18,"losses":41,"wins":13},"qwen/qwen3.7-plus":{"draws":12,"losses":31,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":67,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":37,"wins":26},"qwen/qwen3.8-flash":{"draws":16,"losses":41,"wins":13},"qwen/qwen3.8-max":{"draws":27,"losses":58,"wins":17},"qwen/qwen3.8-max-0902":{"draws":24,"losses":55,"wins":19},"stealth/ox-alpha":{"draws":51,"losses":217,"wins":58},"stealth/space-bunny-alpha":{"draws":21,"losses":36,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":19},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":30,"wins":19},"tencent/hy4-preview":{"draws":20,"losses":59,"wins":17},"thinkingmachines/inkling":{"draws":40,"losses":29,"wins":73},"thinkingmachines/inkling-small":{"draws":30,"losses":33,"wins":37},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":9,"wins":19},"x-ai/grok-4.5":{"draws":12,"losses":78,"wins":20},"x-ai/grok-4.6":{"draws":22,"losses":62,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":73,"wins":10},"x-ai/grok-build-0.1":{"draws":14,"losses":14,"wins":18},"xiaomi/mimo-v2.5":{"draws":52,"losses":67,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":38,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":44,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":52,"wins":8},"z-ai/glm-5.2":{"draws":52,"losses":106,"wins":56},"z-ai/glm-5.3":{"draws":13,"losses":74,"wins":3},"z-ai/glm-5.3-flash":{"draws":25,"losses":65,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":70,"wins":14}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":0},"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-fable-5-1":{"draws":0,"losses":2,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":2,"losses":0,"wins":10},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":3,"wins":3},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":1,"losses":3,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":2},"fireworks/ember-1":{"draws":0,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":6,"losses":3,"wins":5},"google/gemini-3.8-flash":{"draws":1,"losses":1,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":1,"losses":0,"wins":3},"gpt-5.4":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":3},"gpt-5.5":{"draws":6,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":6},"gpt-6-astra":{"draws":0,"losses":5,"wins":1},"gpt-6-luna":{"draws":3,"losses":2,"wins":3},"gpt-6-sol":{"draws":1,"losses":3,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":2},"meta/muse-spark-1.3":{"draws":2,"losses":3,"wins":3},"meta/muse-wonder":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":6,"losses":0,"wins":8},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":2,"losses":3,"wins":3},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":0,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":6}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":24,"wins":23},"claude-fable-5":{"draws":22,"losses":47,"wins":11},"claude-fable-5-1":{"draws":8,"losses":74,"wins":4},"claude-haiku-5-5":{"draws":24,"losses":29,"wins":19},"claude-opus-4-5":{"draws":74,"losses":81,"wins":41},"claude-opus-4-8":{"draws":41,"losses":63,"wins":28},"claude-opus-5":{"draws":45,"losses":179,"wins":20},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":32,"losses":33,"wins":25},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":11,"losses":10,"wins":19},"deepseek/deepseek-v4-flash":{"draws":50,"losses":49,"wins":61},"deepseek/deepseek-v4-pro":{"draws":26,"losses":30,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":26,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":36,"wins":15},"fireworks/ember-1":{"draws":30,"losses":36,"wins":12},"gemini-3.1-pro-preview":{"draws":24,"losses":33,"wins":21},"google/gemini-3.1-flash-lite":{"draws":34,"losses":24,"wins":40},"google/gemini-3.5-flash":{"draws":32,"losses":43,"wins":29},"google/gemini-3.5-flash-lite":{"draws":66,"losses":32,"wins":64},"google/gemini-3.6-flash":{"draws":58,"losses":81,"wins":45},"google/gemini-3.8-flash":{"draws":38,"losses":39,"wins":9},"google/gemma-4-31b-it":{"draws":17,"losses":9,"wins":14},"gpt-4.1":{"draws":30,"losses":20,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":42,"losses":39,"wins":43},"gpt-5.4":{"draws":32,"losses":33,"wins":15},"gpt-5.4-mini":{"draws":36,"losses":22,"wins":28},"gpt-5.4-nano":{"draws":36,"losses":31,"wins":61},"gpt-5.5":{"draws":67,"losses":52,"wins":17},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":58,"wins":10},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":16},"gpt-6-astra":{"draws":11,"losses":67,"wins":0},"gpt-6-luna":{"draws":25,"losses":31,"wins":20},"gpt-6-sol":{"draws":15,"losses":58,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":68,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":15,"wins":17},"inclusionai/ling-3.0-flash":{"draws":35,"losses":11,"wins":42},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":47,"losses":39,"wins":46},"meta/muse-glimmer-30b":{"draws":30,"losses":12,"wins":30},"meta/muse-spark-1.2":{"draws":23,"losses":45,"wins":16},"meta/muse-spark-1.3":{"draws":14,"losses":56,"wins":16},"meta/muse-wonder":{"draws":13,"losses":47,"wins":12},"minimax/minimax-m3":{"draws":34,"losses":22,"wins":40},"mistralai/mistral-large-4-0":{"draws":20,"losses":13,"wins":15},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":14,"wins":10},"moonshotai/kimi-k3":{"draws":32,"losses":35,"wins":19},"nex-agi/nex-n2-pro":{"draws":35,"losses":20,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":77,"losses":26,"wins":43},"o3":{"draws":34,"losses":58,"wins":54},"openai/gpt-oss-120b":{"draws":30,"losses":19,"wins":25},"poolside/laguna-s-2.1":{"draws":36,"losses":32,"wins":38},"qwen/qwen3.7-max":{"draws":44,"losses":33,"wins":19},"qwen/qwen3.7-plus":{"draws":34,"losses":21,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":36,"wins":18},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":15},"qwen/qwen3.8-flash":{"draws":27,"losses":24,"wins":15},"qwen/qwen3.8-max":{"draws":30,"losses":35,"wins":13},"qwen/qwen3.8-max-0902":{"draws":25,"losses":36,"wins":13},"stealth/ox-alpha":{"draws":81,"losses":121,"wins":52},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":17},"stepfun/step-3.7-flash":{"draws":19,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":28,"losses":36,"wins":20},"thinkingmachines/inkling":{"draws":42,"losses":36,"wins":50},"thinkingmachines/inkling-small":{"draws":36,"losses":16,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":20,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":29,"losses":69,"wins":12},"x-ai/grok-4.6":{"draws":31,"losses":46,"wins":13},"x-ai/grok-4.7":{"draws":12,"losses":55,"wins":3},"x-ai/grok-build-0.1":{"draws":13,"losses":8,"wins":21},"xiaomi/mimo-v2.5":{"draws":87,"losses":59,"wins":78},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":26,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":22,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":31,"wins":10},"z-ai/glm-5.2":{"draws":85,"losses":72,"wins":65},"z-ai/glm-5.3":{"draws":15,"losses":48,"wins":11},"z-ai/glm-5.3-flash":{"draws":25,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":46,"wins":14}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":30,"wins":122},"claude-fable-5":{"draws":42,"losses":141,"wins":57},"claude-fable-5-1":{"draws":12,"losses":229,"wins":25},"claude-haiku-5-5":{"draws":28,"losses":46,"wins":52},"claude-opus-4-5":{"draws":86,"losses":83,"wins":141},"claude-opus-4-8":{"draws":34,"losses":51,"wins":61},"claude-opus-5":{"draws":29,"losses":199,"wins":36},"claude-opus-5-5":{"draws":12,"losses":125,"wins":13},"claude-sonnet-5":{"draws":78,"losses":64,"wins":116},"claude-sonnet-5-5":{"draws":24,"losses":67,"wins":47},"cohere/north-mini-code":{"draws":13,"losses":3,"wins":34},"deepseek/deepseek-v4-flash":{"draws":87,"losses":58,"wins":157},"deepseek/deepseek-v4-pro":{"draws":67,"losses":65,"wins":100},"deepseek/deepseek-v4-pro-0813":{"draws":59,"losses":72,"wins":97},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":41,"wins":56},"fireworks/ember-1":{"draws":42,"losses":42,"wins":54},"gemini-3.1-pro-preview":{"draws":33,"losses":40,"wins":65},"google/gemini-3.1-flash-lite":{"draws":23,"losses":3,"wins":74},"google/gemini-3.5-flash":{"draws":63,"losses":74,"wins":143},"google/gemini-3.5-flash-lite":{"draws":126,"losses":84,"wins":218},"google/gemini-3.6-flash":{"draws":101,"losses":164,"wins":171},"google/gemini-3.8-flash":{"draws":55,"losses":90,"wins":91},"google/gemma-4-31b-it":{"draws":24,"losses":11,"wins":39},"gpt-4.1":{"draws":13,"losses":11,"wins":28},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":11},"gpt-5":{"draws":42,"losses":36,"wins":52},"gpt-5.4":{"draws":61,"losses":102,"wins":79},"gpt-5.4-mini":{"draws":35,"losses":13,"wins":48},"gpt-5.4-nano":{"draws":23,"losses":32,"wins":91},"gpt-5.5":{"draws":46,"losses":41,"wins":47},"gpt-5.6-luna":{"draws":77,"losses":46,"wins":111},"gpt-5.6-sol":{"draws":35,"losses":132,"wins":83},"gpt-5.6-terra":{"draws":61,"losses":65,"wins":100},"gpt-6-astra":{"draws":20,"losses":210,"wins":14},"gpt-6-luna":{"draws":38,"losses":34,"wins":64},"gpt-6-sol":{"draws":19,"losses":92,"wins":27},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":71,"losses":15,"wins":78},"inclusionai/ling-3.0-flash":{"draws":39,"losses":9,"wins":74},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":55,"losses":27,"wins":116},"meta/muse-glimmer-30b":{"draws":81,"losses":20,"wins":105},"meta/muse-spark-1.2":{"draws":35,"losses":71,"wins":90},"meta/muse-spark-1.3":{"draws":45,"losses":80,"wins":77},"meta/muse-wonder":{"draws":26,"losses":67,"wins":35},"minimax/minimax-m3":{"draws":19,"losses":7,"wins":52},"mistralai/mistral-large-4-0":{"draws":16,"losses":28,"wins":36},"mistralai/mistral-medium-3-5":{"draws":50,"losses":11,"wins":75},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":20},"moonshotai/kimi-k3":{"draws":59,"losses":71,"wins":78},"nex-agi/nex-n2-pro":{"draws":19,"losses":6,"wins":51},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":14,"wins":67},"o3":{"draws":46,"losses":92,"wins":152},"openai/gpt-oss-120b":{"draws":74,"losses":32,"wins":88},"poolside/laguna-s-2.1":{"draws":68,"losses":35,"wins":93},"qwen/qwen3.7-max":{"draws":18,"losses":18,"wins":50},"qwen/qwen3.7-plus":{"draws":18,"losses":11,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":72,"losses":75,"wins":97},"qwen/qwen3.8-27b":{"draws":30,"losses":38,"wins":56},"qwen/qwen3.8-flash":{"draws":45,"losses":49,"wins":66},"qwen/qwen3.8-max":{"draws":61,"losses":76,"wins":105},"qwen/qwen3.8-max-0902":{"draws":32,"losses":50,"wins":52},"stealth/ox-alpha":{"draws":195,"losses":266,"wins":338},"stealth/space-bunny-alpha":{"draws":33,"losses":26,"wins":51},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":59},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":36},"tencent/hy4-preview":{"draws":30,"losses":55,"wins":55},"thinkingmachines/inkling":{"draws":66,"losses":26,"wins":112},"thinkingmachines/inkling-small":{"draws":85,"losses":27,"wins":136},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":46,"losses":83,"wins":85},"x-ai/grok-4.6":{"draws":74,"losses":102,"wins":66},"x-ai/grok-4.7":{"draws":12,"losses":73,"wins":35},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":72,"losses":19,"wins":135},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":16,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":38,"wins":32},"z-ai/glm-5.2":{"draws":105,"losses":79,"wins":186},"z-ai/glm-5.3":{"draws":39,"losses":119,"wins":42},"z-ai/glm-5.3-flash":{"draws":55,"losses":100,"wins":81},"z-ai/glm-5.3-flashx":{"draws":32,"losses":49,"wins":57}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":69,"losses":82,"wins":51},"claude-fable-5":{"draws":45,"losses":141,"wins":6},"claude-fable-5-1":{"draws":13,"losses":195,"wins":0},"claude-haiku-5-5":{"draws":36,"losses":93,"wins":17},"claude-opus-4-5":{"draws":144,"losses":223,"wins":67},"claude-opus-4-8":{"draws":50,"losses":131,"wins":25},"claude-opus-5":{"draws":50,"losses":291,"wins":41},"claude-opus-5-5":{"draws":13,"losses":157,"wins":0},"claude-sonnet-5":{"draws":79,"losses":152,"wins":37},"claude-sonnet-5-5":{"draws":33,"losses":93,"wins":36},"cohere/north-mini-code":{"draws":19,"losses":27,"wins":24},"deepseek/deepseek-v4-flash":{"draws":113,"losses":114,"wins":95},"deepseek/deepseek-v4-pro":{"draws":71,"losses":105,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":65,"losses":84,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":86,"wins":22},"fireworks/ember-1":{"draws":50,"losses":89,"wins":23},"gemini-3.1-pro-preview":{"draws":47,"losses":74,"wins":41},"google/gemini-3.1-flash-lite":{"draws":48,"losses":49,"wins":75},"google/gemini-3.5-flash":{"draws":63,"losses":142,"wins":51},"google/gemini-3.5-flash-lite":{"draws":186,"losses":237,"wins":179},"google/gemini-3.6-flash":{"draws":167,"losses":330,"wins":75},"google/gemini-3.8-flash":{"draws":56,"losses":122,"wins":14},"google/gemma-4-31b-it":{"draws":32,"losses":30,"wins":26},"gpt-4.1":{"draws":20,"losses":30,"wins":32},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":56,"losses":104,"wins":40},"gpt-5.4":{"draws":65,"losses":139,"wins":42},"gpt-5.4-mini":{"draws":62,"losses":50,"wins":42},"gpt-5.4-nano":{"draws":42,"losses":91,"wins":69},"gpt-5.5":{"draws":69,"losses":116,"wins":39},"gpt-5.6-luna":{"draws":99,"losses":114,"wins":53},"gpt-5.6-sol":{"draws":43,"losses":184,"wins":21},"gpt-5.6-terra":{"draws":61,"losses":103,"wins":32},"gpt-6-astra":{"draws":9,"losses":171,"wins":2},"gpt-6-luna":{"draws":50,"losses":83,"wins":27},"gpt-6-sol":{"draws":21,"losses":132,"wins":9},"gpt-6.1-sol":{"draws":12,"losses":144,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":65,"losses":38,"wins":45},"inclusionai/ling-3.0-flash":{"draws":89,"losses":55,"wins":74},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":80,"losses":105,"wins":123},"meta/muse-glimmer-30b":{"draws":73,"losses":71,"wins":52},"meta/muse-spark-1.2":{"draws":72,"losses":116,"wins":34},"meta/muse-spark-1.3":{"draws":36,"losses":138,"wins":16},"meta/muse-wonder":{"draws":36,"losses":104,"wins":16},"minimax/minimax-m3":{"draws":31,"losses":45,"wins":48},"mistralai/mistral-large-4-0":{"draws":33,"losses":53,"wins":10},"mistralai/mistral-medium-3-5":{"draws":46,"losses":28,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":30,"wins":17},"moonshotai/kimi-k3":{"draws":87,"losses":136,"wins":41},"nex-agi/nex-n2-pro":{"draws":33,"losses":32,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":76,"losses":81,"wins":59},"o3":{"draws":55,"losses":245,"wins":78},"openai/gpt-oss-120b":{"draws":56,"losses":61,"wins":65},"poolside/laguna-s-2.1":{"draws":100,"losses":123,"wins":79},"qwen/qwen3.7-max":{"draws":45,"losses":74,"wins":21},"qwen/qwen3.7-plus":{"draws":32,"losses":48,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":110,"wins":29},"qwen/qwen3.8-27b":{"draws":28,"losses":74,"wins":26},"qwen/qwen3.8-flash":{"draws":46,"losses":65,"wins":27},"qwen/qwen3.8-max":{"draws":65,"losses":101,"wins":34},"qwen/qwen3.8-max-0902":{"draws":43,"losses":98,"wins":19},"stealth/ox-alpha":{"draws":176,"losses":405,"wins":113},"stealth/space-bunny-alpha":{"draws":44,"losses":54,"wins":34},"stepfun/step-3.7-flash":{"draws":40,"losses":73,"wins":29},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":42,"losses":50,"wins":36},"tencent/hy4-preview":{"draws":66,"losses":112,"wins":26},"thinkingmachines/inkling":{"draws":70,"losses":63,"wins":63},"thinkingmachines/inkling-small":{"draws":79,"losses":54,"wins":83},"unbiased/pareto-26.10-preview":{"draws":0,"losses":53,"wins":1},"upstage/solar-mini4":{"draws":11,"losses":20,"wins":13},"x-ai/grok-4.5":{"draws":88,"losses":167,"wins":41},"x-ai/grok-4.6":{"draws":69,"losses":100,"wins":21},"x-ai/grok-4.7":{"draws":16,"losses":113,"wins":11},"x-ai/grok-build-0.1":{"draws":28,"losses":30,"wins":18},"xiaomi/mimo-v2.5":{"draws":119,"losses":152,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":67,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":24,"losses":61,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":23,"losses":71,"wins":10},"z-ai/glm-5.2":{"draws":141,"losses":195,"wins":96},"z-ai/glm-5.3":{"draws":37,"losses":123,"wins":20},"z-ai/glm-5.3-flash":{"draws":50,"losses":125,"wins":29},"z-ai/glm-5.3-flashx":{"draws":37,"losses":110,"wins":15}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":96,"losses":100,"wins":56},"claude-fable-5":{"draws":51,"losses":141,"wins":26},"claude-fable-5-1":{"draws":14,"losses":221,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":86,"wins":13},"claude-opus-4-5":{"draws":106,"losses":169,"wins":46},"claude-opus-4-8":{"draws":42,"losses":80,"wins":12},"claude-opus-5":{"draws":35,"losses":204,"wins":13},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":80,"losses":133,"wins":47},"claude-sonnet-5-5":{"draws":32,"losses":91,"wins":21},"cohere/north-mini-code":{"draws":17,"losses":13,"wins":24},"deepseek/deepseek-v4-flash":{"draws":151,"losses":127,"wins":66},"deepseek/deepseek-v4-pro":{"draws":98,"losses":118,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":79,"losses":110,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":72,"wins":25},"fireworks/ember-1":{"draws":50,"losses":77,"wins":17},"gemini-3.1-pro-preview":{"draws":45,"losses":70,"wins":29},"google/gemini-3.1-flash-lite":{"draws":34,"losses":30,"wins":40},"google/gemini-3.5-flash":{"draws":83,"losses":138,"wins":51},"google/gemini-3.5-flash-lite":{"draws":176,"losses":177,"wins":143},"google/gemini-3.6-flash":{"draws":135,"losses":205,"wins":82},"google/gemini-3.8-flash":{"draws":79,"losses":121,"wins":30},"google/gemma-4-31b-it":{"draws":29,"losses":24,"wins":25},"gpt-4.1":{"draws":17,"losses":18,"wins":13},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":53,"losses":55,"wins":20},"gpt-5.4":{"draws":98,"losses":101,"wins":24},"gpt-5.4-mini":{"draws":45,"losses":29,"wins":26},"gpt-5.4-nano":{"draws":53,"losses":56,"wins":45},"gpt-5.5":{"draws":50,"losses":64,"wins":18},"gpt-5.6-luna":{"draws":115,"losses":85,"wins":78},"gpt-5.6-sol":{"draws":35,"losses":171,"wins":25},"gpt-5.6-terra":{"draws":83,"losses":121,"wins":42},"gpt-6-astra":{"draws":15,"losses":187,"wins":0},"gpt-6-luna":{"draws":34,"losses":72,"wins":32},"gpt-6-sol":{"draws":18,"losses":118,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":138,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":95,"losses":44,"wins":63},"inclusionai/ling-3.0-flash":{"draws":59,"losses":28,"wins":50},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":69,"losses":81,"wins":68},"meta/muse-glimmer-30b":{"draws":115,"losses":83,"wins":46},"meta/muse-spark-1.2":{"draws":63,"losses":102,"wins":43},"meta/muse-spark-1.3":{"draws":63,"losses":124,"wins":23},"meta/muse-wonder":{"draws":30,"losses":91,"wins":15},"minimax/minimax-m3":{"draws":25,"losses":34,"wins":21},"mistralai/mistral-large-4-0":{"draws":26,"losses":44,"wins":14},"mistralai/mistral-medium-3-5":{"draws":79,"losses":30,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":77,"losses":108,"wins":33},"nex-agi/nex-n2-pro":{"draws":25,"losses":17,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":59,"losses":35,"wins":34},"o3":{"draws":69,"losses":159,"wins":71},"openai/gpt-oss-120b":{"draws":105,"losses":81,"wins":58},"poolside/laguna-s-2.1":{"draws":97,"losses":87,"wins":29},"qwen/qwen3.7-max":{"draws":32,"losses":39,"wins":17},"qwen/qwen3.7-plus":{"draws":28,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":86,"losses":139,"wins":31},"qwen/qwen3.8-27b":{"draws":33,"losses":80,"wins":17},"qwen/qwen3.8-flash":{"draws":81,"losses":61,"wins":30},"qwen/qwen3.8-max":{"draws":136,"losses":153,"wins":102},"qwen/qwen3.8-max-0902":{"draws":47,"losses":80,"wins":15},"stealth/ox-alpha":{"draws":255,"losses":436,"wins":123},"stealth/space-bunny-alpha":{"draws":38,"losses":47,"wins":29},"stepfun/step-3.7-flash":{"draws":30,"losses":37,"wins":33},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":30,"wins":16},"tencent/hy4-preview":{"draws":85,"losses":136,"wins":27},"thinkingmachines/inkling":{"draws":79,"losses":83,"wins":54},"thinkingmachines/inkling-small":{"draws":110,"losses":85,"wins":85},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.5":{"draws":58,"losses":131,"wins":34},"x-ai/grok-4.6":{"draws":81,"losses":128,"wins":31},"x-ai/grok-4.7":{"draws":15,"losses":109,"wins":2},"x-ai/grok-build-0.1":{"draws":22,"losses":14,"wins":14},"xiaomi/mimo-v2.5":{"draws":98,"losses":67,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":32,"losses":36,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":54,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":69,"wins":12},"z-ai/glm-5.2":{"draws":160,"losses":166,"wins":88},"z-ai/glm-5.3":{"draws":43,"losses":134,"wins":21},"z-ai/glm-5.3-flash":{"draws":81,"losses":128,"wins":39},"z-ai/glm-5.3-flashx":{"draws":36,"losses":85,"wins":23}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":41},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":20,"wins":27},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":74},"claude-opus-4-8":{"draws":2,"losses":1,"wins":39},"claude-opus-5":{"draws":3,"losses":29,"wins":46},"claude-opus-5-5":{"draws":1,"losses":24,"wins":21},"claude-sonnet-5":{"draws":0,"losses":0,"wins":42},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"fireworks/ember-1":{"draws":1,"losses":1,"wins":44},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":44},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":47},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":75},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":66},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":40},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":38},"gpt-5.4":{"draws":2,"losses":6,"wins":34},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":41},"gpt-5.5":{"draws":1,"losses":4,"wins":33},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":39},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":35},"gpt-6-astra":{"draws":6,"losses":21,"wins":19},"gpt-6-luna":{"draws":2,"losses":1,"wins":41},"gpt-6-sol":{"draws":5,"losses":7,"wins":32},"gpt-6.1-sol":{"draws":2,"losses":17,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":30},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":42},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":38},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":40},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":38},"meta/muse-wonder":{"draws":4,"losses":9,"wins":33},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":33},"o3":{"draws":0,"losses":3,"wins":59},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":37},"stealth/ox-alpha":{"draws":9,"losses":6,"wins":131},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":20},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":53},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":38},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":38},"x-ai/grok-4.7":{"draws":3,"losses":6,"wins":29},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":80},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":37},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":38}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":27,"wins":4},"claude-opus-4-5":{"draws":9,"losses":39,"wins":12},"claude-opus-4-8":{"draws":6,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":40,"wins":1},"claude-opus-5-5":{"draws":2,"losses":34,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":26,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":28,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":4},"fireworks/ember-1":{"draws":5,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":19},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":12},"google/gemini-3.5-flash-lite":{"draws":20,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":14,"losses":47,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":11},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":4,"losses":23,"wins":3},"gpt-5.4":{"draws":3,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":15},"gpt-5.5":{"draws":5,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":32,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":25,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":1,"losses":25,"wins":10},"gpt-6-sol":{"draws":1,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":7,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":26,"wins":8},"meta/muse-wonder":{"draws":3,"losses":32,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":24,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":14},"o3":{"draws":10,"losses":39,"wins":13},"openai/gpt-oss-120b":{"draws":6,"losses":11,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":26,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":22,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":29,"wins":5},"stealth/ox-alpha":{"draws":13,"losses":74,"wins":15},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":26,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":20},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":6,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":48,"wins":16},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":22,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":29,"wins":120},"claude-fable-5":{"draws":31,"losses":114,"wins":77},"claude-fable-5-1":{"draws":8,"losses":213,"wins":19},"claude-haiku-5-5":{"draws":30,"losses":45,"wins":51},"claude-opus-4-5":{"draws":139,"losses":124,"wins":203},"claude-opus-4-8":{"draws":58,"losses":71,"wins":81},"claude-opus-5":{"draws":59,"losses":280,"wins":79},"claude-opus-5-5":{"draws":18,"losses":123,"wins":15},"claude-sonnet-5":{"draws":103,"losses":66,"wins":157},"claude-sonnet-5-5":{"draws":32,"losses":63,"wins":49},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":52},"deepseek/deepseek-v4-flash":{"draws":62,"losses":55,"wins":187},"deepseek/deepseek-v4-pro":{"draws":54,"losses":70,"wins":84},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":69,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":49,"wins":64},"fireworks/ember-1":{"draws":34,"losses":39,"wins":71},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":73},"google/gemini-3.1-flash-lite":{"draws":27,"losses":4,"wins":95},"google/gemini-3.5-flash":{"draws":55,"losses":86,"wins":121},"google/gemini-3.5-flash-lite":{"draws":175,"losses":132,"wins":369},"google/gemini-3.6-flash":{"draws":140,"losses":281,"wins":275},"google/gemini-3.8-flash":{"draws":40,"losses":76,"wins":104},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":47},"gpt-4.1":{"draws":18,"losses":12,"wins":36},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":35,"losses":44,"wins":93},"gpt-5.4":{"draws":68,"losses":143,"wins":104},"gpt-5.4-mini":{"draws":47,"losses":16,"wins":69},"gpt-5.4-nano":{"draws":36,"losses":49,"wins":113},"gpt-5.5":{"draws":57,"losses":66,"wins":79},"gpt-5.6-luna":{"draws":80,"losses":95,"wins":133},"gpt-5.6-sol":{"draws":41,"losses":181,"wins":106},"gpt-5.6-terra":{"draws":60,"losses":53,"wins":115},"gpt-6-astra":{"draws":10,"losses":184,"wins":22},"gpt-6-luna":{"draws":35,"losses":43,"wins":62},"gpt-6-sol":{"draws":21,"losses":93,"wins":30},"gpt-6.1-sol":{"draws":10,"losses":118,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":56,"losses":7,"wins":91},"inclusionai/ling-3.0-flash":{"draws":62,"losses":19,"wins":143},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":75,"losses":59,"wins":220},"meta/muse-glimmer-30b":{"draws":51,"losses":24,"wins":107},"meta/muse-spark-1.2":{"draws":59,"losses":65,"wins":124},"meta/muse-spark-1.3":{"draws":28,"losses":87,"wins":83},"meta/muse-wonder":{"draws":29,"losses":77,"wins":30},"minimax/minimax-m3":{"draws":20,"losses":8,"wins":80},"mistralai/mistral-large-4-0":{"draws":20,"losses":29,"wins":31},"mistralai/mistral-medium-3-5":{"draws":32,"losses":14,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":5,"wins":29},"moonshotai/kimi-k3":{"draws":91,"losses":100,"wins":131},"nex-agi/nex-n2-pro":{"draws":26,"losses":7,"wins":69},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":12,"wins":109},"o3":{"draws":34,"losses":127,"wins":233},"openai/gpt-oss-120b":{"draws":57,"losses":19,"wins":108},"poolside/laguna-s-2.1":{"draws":95,"losses":51,"wins":184},"qwen/qwen3.7-max":{"draws":34,"losses":28,"wins":56},"qwen/qwen3.7-plus":{"draws":26,"losses":11,"wins":65},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":74,"wins":90},"qwen/qwen3.8-27b":{"draws":24,"losses":30,"wins":68},"qwen/qwen3.8-flash":{"draws":35,"losses":36,"wins":63},"qwen/qwen3.8-max":{"draws":60,"losses":74,"wins":99},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":59},"stealth/ox-alpha":{"draws":157,"losses":238,"wins":315},"stealth/space-bunny-alpha":{"draws":31,"losses":20,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":20,"wins":78},"tencent/hy3-preview":{"draws":29,"losses":12,"wins":69},"tencent/hy4-preview":{"draws":46,"losses":85,"wins":83},"thinkingmachines/inkling":{"draws":88,"losses":41,"wins":167},"thinkingmachines/inkling-small":{"draws":58,"losses":34,"wins":131},"unbiased/pareto-26.10-preview":{"draws":1,"losses":38,"wins":5},"upstage/solar-mini4":{"draws":5,"losses":6,"wins":25},"x-ai/grok-4.5":{"draws":76,"losses":74,"wins":74},"x-ai/grok-4.6":{"draws":63,"losses":84,"wins":81},"x-ai/grok-4.7":{"draws":17,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":23,"losses":5,"wins":46},"xiaomi/mimo-v2.5":{"draws":91,"losses":26,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":42,"wins":68},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":31,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":101,"losses":88,"wins":199},"z-ai/glm-5.3":{"draws":38,"losses":103,"wins":47},"z-ai/glm-5.3-flash":{"draws":33,"losses":89,"wins":84},"z-ai/glm-5.3-flashx":{"draws":25,"losses":60,"wins":59}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":62,"losses":31,"wins":121},"claude-fable-5":{"draws":64,"losses":116,"wins":90},"claude-fable-5-1":{"draws":18,"losses":246,"wins":44},"claude-haiku-5-5":{"draws":36,"losses":37,"wins":57},"claude-opus-4-5":{"draws":85,"losses":69,"wins":166},"claude-opus-4-8":{"draws":37,"losses":47,"wins":60},"claude-opus-5":{"draws":39,"losses":177,"wins":59},"claude-opus-5-5":{"draws":18,"losses":123,"wins":15},"claude-sonnet-5":{"draws":71,"losses":60,"wins":129},"claude-sonnet-5-5":{"draws":24,"losses":61,"wins":59},"cohere/north-mini-code":{"draws":13,"losses":2,"wins":39},"deepseek/deepseek-v4-flash":{"draws":92,"losses":34,"wins":188},"deepseek/deepseek-v4-pro":{"draws":62,"losses":52,"wins":122},"deepseek/deepseek-v4-pro-0813":{"draws":79,"losses":54,"wins":101},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":40,"losses":42,"wins":62},"gemini-3.1-pro-preview":{"draws":40,"losses":28,"wins":76},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":72},"google/gemini-3.5-flash":{"draws":83,"losses":55,"wins":154},"google/gemini-3.5-flash-lite":{"draws":119,"losses":57,"wins":232},"google/gemini-3.6-flash":{"draws":105,"losses":138,"wins":177},"google/gemini-3.8-flash":{"draws":76,"losses":87,"wins":99},"google/gemma-4-31b-it":{"draws":21,"losses":6,"wins":53},"gpt-4.1":{"draws":20,"losses":6,"wins":24},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":42,"losses":21,"wins":73},"gpt-5.4":{"draws":81,"losses":92,"wins":87},"gpt-5.4-mini":{"draws":34,"losses":16,"wins":50},"gpt-5.4-nano":{"draws":24,"losses":24,"wins":96},"gpt-5.5":{"draws":47,"losses":39,"wins":58},"gpt-5.6-luna":{"draws":67,"losses":42,"wins":131},"gpt-5.6-sol":{"draws":53,"losses":118,"wins":105},"gpt-5.6-terra":{"draws":82,"losses":44,"wins":136},"gpt-6-astra":{"draws":22,"losses":224,"wins":28},"gpt-6-luna":{"draws":36,"losses":23,"wins":79},"gpt-6-sol":{"draws":21,"losses":93,"wins":30},"gpt-6.1-sol":{"draws":16,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":52,"losses":17,"wins":89},"inclusionai/ling-3.0-flash":{"draws":42,"losses":7,"wins":71},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":61,"losses":30,"wins":116},"meta/muse-glimmer-30b":{"draws":69,"losses":20,"wins":107},"meta/muse-spark-1.2":{"draws":49,"losses":43,"wins":112},"meta/muse-spark-1.3":{"draws":46,"losses":73,"wins":91},"meta/muse-wonder":{"draws":38,"losses":58,"wins":36},"minimax/minimax-m3":{"draws":24,"losses":4,"wins":56},"mistralai/mistral-large-4-0":{"draws":27,"losses":17,"wins":42},"mistralai/mistral-medium-3-5":{"draws":49,"losses":10,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":8,"wins":18},"moonshotai/kimi-k3":{"draws":58,"losses":54,"wins":102},"nex-agi/nex-n2-pro":{"draws":21,"losses":4,"wins":55},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":13,"wins":67},"o3":{"draws":52,"losses":70,"wins":158},"openai/gpt-oss-120b":{"draws":65,"losses":22,"wins":105},"poolside/laguna-s-2.1":{"draws":60,"losses":21,"wins":107},"qwen/qwen3.7-max":{"draws":21,"losses":16,"wins":47},"qwen/qwen3.7-plus":{"draws":21,"losses":6,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":87,"wins":104},"qwen/qwen3.8-27b":{"draws":32,"losses":38,"wins":64},"qwen/qwen3.8-flash":{"draws":63,"losses":32,"wins":71},"qwen/qwen3.8-max":{"draws":72,"losses":77,"wins":113},"qwen/qwen3.8-max-0902":{"draws":41,"losses":34,"wins":63},"stealth/ox-alpha":{"draws":245,"losses":262,"wins":343},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":22,"losses":14,"wins":62},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":13,"wins":46},"tencent/hy4-preview":{"draws":74,"losses":66,"wins":102},"thinkingmachines/inkling":{"draws":69,"losses":21,"wins":100},"thinkingmachines/inkling-small":{"draws":81,"losses":31,"wins":128},"unbiased/pareto-26.10-preview":{"draws":4,"losses":38,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":63,"losses":81,"wins":84},"x-ai/grok-4.6":{"draws":64,"losses":56,"wins":56},"x-ai/grok-4.7":{"draws":16,"losses":79,"wins":31},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":82,"losses":19,"wins":127},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":13,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":32,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":37,"wins":34},"z-ai/glm-5.2":{"draws":115,"losses":69,"wins":216},"z-ai/glm-5.3":{"draws":49,"losses":92,"wins":75},"z-ai/glm-5.3-flash":{"draws":63,"losses":94,"wins":97},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":17,"wins":91},"claude-fable-5":{"draws":7,"losses":43,"wins":76},"claude-fable-5-1":{"draws":6,"losses":95,"wins":39},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":83},"claude-opus-4-5":{"draws":17,"losses":34,"wins":155},"claude-opus-4-8":{"draws":16,"losses":29,"wins":73},"claude-opus-5":{"draws":21,"losses":100,"wins":99},"claude-opus-5-5":{"draws":11,"losses":96,"wins":31},"claude-sonnet-5":{"draws":12,"losses":24,"wins":90},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":64},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":41},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":157},"deepseek/deepseek-v4-pro":{"draws":10,"losses":21,"wins":85},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":83},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":33,"wins":82},"fireworks/ember-1":{"draws":11,"losses":26,"wins":89},"gemini-3.1-pro-preview":{"draws":14,"losses":23,"wins":89},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":79},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":118},"google/gemini-3.5-flash-lite":{"draws":20,"losses":28,"wins":170},"google/gemini-3.6-flash":{"draws":8,"losses":53,"wins":157},"google/gemini-3.8-flash":{"draws":14,"losses":27,"wins":85},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":54},"gpt-4.1":{"draws":4,"losses":4,"wins":34},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":10},"gpt-5":{"draws":10,"losses":18,"wins":84},"gpt-5.4":{"draws":13,"losses":28,"wins":79},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":66},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":104},"gpt-5.5":{"draws":11,"losses":36,"wins":69},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":96},"gpt-5.6-sol":{"draws":16,"losses":44,"wins":66},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":86},"gpt-6-astra":{"draws":12,"losses":92,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":90},"gpt-6-sol":{"draws":13,"losses":50,"wins":63},"gpt-6.1-sol":{"draws":6,"losses":79,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":73},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":120},"meta/muse-glimmer-30b":{"draws":6,"losses":13,"wins":93},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":82},"meta/muse-spark-1.3":{"draws":11,"losses":30,"wins":79},"meta/muse-wonder":{"draws":16,"losses":36,"wins":60},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":61},"mistralai/mistral-large-4-0":{"draws":14,"losses":16,"wins":38},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":24},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":80},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":54},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":98},"o3":{"draws":11,"losses":36,"wins":127},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":99},"poolside/laguna-s-2.1":{"draws":11,"losses":14,"wins":99},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":51},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":30,"wins":86},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":58},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":63},"qwen/qwen3.8-max":{"draws":12,"losses":26,"wins":88},"qwen/qwen3.8-max-0902":{"draws":18,"losses":27,"wins":77},"stealth/ox-alpha":{"draws":48,"losses":69,"wins":279},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":73},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":73},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":55},"tencent/hy4-preview":{"draws":12,"losses":35,"wins":73},"thinkingmachines/inkling":{"draws":16,"losses":11,"wins":113},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":109},"unbiased/pareto-26.10-preview":{"draws":3,"losses":29,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":23},"x-ai/grok-4.5":{"draws":17,"losses":27,"wins":82},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":79},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":35},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":35},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":55},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":54},"z-ai/glm-5.2":{"draws":29,"losses":34,"wins":189},"z-ai/glm-5.3":{"draws":16,"losses":32,"wins":72},"z-ai/glm-5.3-flash":{"draws":15,"losses":34,"wins":77},"z-ai/glm-5.3-flashx":{"draws":15,"losses":27,"wins":84}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":8},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":27,"wins":4},"claude-opus-4-5":{"draws":47,"losses":65,"wins":18},"claude-opus-4-8":{"draws":24,"losses":50,"wins":14},"claude-opus-5":{"draws":22,"losses":84,"wins":8},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":21,"losses":28,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":40,"losses":38,"wins":26},"deepseek/deepseek-v4-pro":{"draws":18,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":38},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":10},"google/gemini-3.5-flash-lite":{"draws":47,"losses":30,"wins":34},"google/gemini-3.6-flash":{"draws":31,"losses":62,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":9},"gpt-4.1":{"draws":14,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":27,"losses":33,"wins":16},"gpt-5.4":{"draws":12,"losses":29,"wins":7},"gpt-5.4-mini":{"draws":28,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":20,"losses":51,"wins":27},"gpt-5.5":{"draws":51,"losses":21,"wins":14},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":26,"wins":7},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":24,"losses":4,"wins":36},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":28,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":33,"wins":11},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":20,"losses":17,"wins":25},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":16,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":22,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":31,"wins":6},"nex-agi/nex-n2-pro":{"draws":21,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":18,"wins":20},"o3":{"draws":20,"losses":51,"wins":13},"openai/gpt-oss-120b":{"draws":19,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":37,"losses":18,"wins":27},"qwen/qwen3.7-max":{"draws":27,"losses":15,"wins":22},"qwen/qwen3.7-plus":{"draws":17,"losses":22,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":19,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":21,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":44,"losses":105,"wins":19},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":21,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":28,"losses":18,"wins":30},"thinkingmachines/inkling-small":{"draws":22,"losses":14,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":23,"losses":46,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":69,"losses":37,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":26,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":47,"losses":48,"wins":23},"z-ai/glm-5.3":{"draws":13,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":28,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":82,"losses":82,"wins":52},"claude-fable-5":{"draws":45,"losses":174,"wins":5},"claude-fable-5-1":{"draws":12,"losses":229,"wins":3},"claude-haiku-5-5":{"draws":52,"losses":121,"wins":31},"claude-opus-4-5":{"draws":251,"losses":282,"wins":103},"claude-opus-4-8":{"draws":123,"losses":224,"wins":39},"claude-opus-5":{"draws":87,"losses":426,"wins":35},"claude-opus-5-5":{"draws":11,"losses":227,"wins":4},"claude-sonnet-5":{"draws":88,"losses":113,"wins":37},"claude-sonnet-5-5":{"draws":49,"losses":147,"wins":26},"cohere/north-mini-code":{"draws":45,"losses":40,"wins":41},"deepseek/deepseek-v4-flash":{"draws":177,"losses":140,"wins":161},"deepseek/deepseek-v4-pro":{"draws":83,"losses":99,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":91,"losses":101,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":80,"losses":116,"wins":26},"fireworks/ember-1":{"draws":83,"losses":110,"wins":29},"gemini-3.1-pro-preview":{"draws":74,"losses":99,"wins":49},"google/gemini-3.1-flash-lite":{"draws":111,"losses":76,"wins":133},"google/gemini-3.5-flash":{"draws":98,"losses":153,"wins":57},"google/gemini-3.5-flash-lite":{"draws":163,"losses":162,"wins":135},"google/gemini-3.6-flash":{"draws":169,"losses":247,"wins":60},"google/gemini-3.8-flash":{"draws":70,"losses":138,"wins":20},"google/gemma-4-31b-it":{"draws":50,"losses":31,"wins":41},"gpt-4.1":{"draws":60,"losses":50,"wins":30},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":129,"losses":128,"wins":63},"gpt-5.4":{"draws":67,"losses":138,"wins":13},"gpt-5.4-mini":{"draws":126,"losses":88,"wins":76},"gpt-5.4-nano":{"draws":118,"losses":198,"wins":160},"gpt-5.5":{"draws":164,"losses":156,"wins":34},"gpt-5.6-luna":{"draws":93,"losses":88,"wins":47},"gpt-5.6-sol":{"draws":41,"losses":173,"wins":16},"gpt-5.6-terra":{"draws":86,"losses":127,"wins":15},"gpt-6-astra":{"draws":13,"losses":209,"wins":2},"gpt-6-luna":{"draws":80,"losses":109,"wins":29},"gpt-6-sol":{"draws":36,"losses":170,"wins":16},"gpt-6.1-sol":{"draws":19,"losses":195,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":81,"losses":23,"wins":66},"inclusionai/ling-3.0-flash":{"draws":112,"losses":54,"wins":90},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":128,"losses":132,"wins":115},"meta/muse-glimmer-30b":{"draws":85,"losses":67,"wins":50},"meta/muse-spark-1.2":{"draws":66,"losses":124,"wins":28},"meta/muse-spark-1.3":{"draws":57,"losses":152,"wins":21},"meta/muse-wonder":{"draws":43,"losses":146,"wins":17},"minimax/minimax-m3":{"draws":92,"losses":82,"wins":80},"mistralai/mistral-large-4-0":{"draws":45,"losses":57,"wins":18},"mistralai/mistral-medium-3-5":{"draws":58,"losses":27,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":50,"losses":62,"wins":22},"moonshotai/kimi-k3":{"draws":85,"losses":129,"wins":38},"nex-agi/nex-n2-pro":{"draws":59,"losses":51,"wins":88},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":179,"losses":117,"wins":98},"o3":{"draws":85,"losses":230,"wins":61},"openai/gpt-oss-120b":{"draws":73,"losses":64,"wins":55},"poolside/laguna-s-2.1":{"draws":110,"losses":117,"wins":81},"qwen/qwen3.7-max":{"draws":105,"losses":104,"wins":53},"qwen/qwen3.7-plus":{"draws":88,"losses":79,"wins":69},"qwen/qwen3.8-2.4t-a95b":{"draws":93,"losses":114,"wins":29},"qwen/qwen3.8-27b":{"draws":46,"losses":87,"wins":29},"qwen/qwen3.8-flash":{"draws":65,"losses":57,"wins":30},"qwen/qwen3.8-max":{"draws":86,"losses":105,"wins":43},"qwen/qwen3.8-max-0902":{"draws":79,"losses":110,"wins":27},"stealth/ox-alpha":{"draws":179,"losses":403,"wins":96},"stealth/space-bunny-alpha":{"draws":71,"losses":69,"wins":38},"stepfun/step-3.7-flash":{"draws":52,"losses":63,"wins":67},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":87,"losses":78,"wins":59},"tencent/hy4-preview":{"draws":72,"losses":135,"wins":19},"thinkingmachines/inkling":{"draws":119,"losses":87,"wins":152},"thinkingmachines/inkling-small":{"draws":98,"losses":61,"wins":67},"unbiased/pareto-26.10-preview":{"draws":4,"losses":64,"wins":0},"upstage/solar-mini4":{"draws":16,"losses":30,"wins":16},"x-ai/grok-4.5":{"draws":91,"losses":177,"wins":26},"x-ai/grok-4.6":{"draws":82,"losses":127,"wins":19},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":69,"losses":50,"wins":37},"xiaomi/mimo-v2.5":{"draws":286,"losses":173,"wins":173},"xiaomi/mimo-v2.5-pro":{"draws":79,"losses":108,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":81,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":37,"losses":96,"wins":13},"z-ai/glm-5.2":{"draws":249,"losses":260,"wins":129},"z-ai/glm-5.3":{"draws":51,"losses":159,"wins":4},"z-ai/glm-5.3-flash":{"draws":67,"losses":126,"wins":35},"z-ai/glm-5.3-flashx":{"draws":73,"losses":133,"wins":16}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":26,"wins":27},"claude-fable-5":{"draws":9,"losses":71,"wins":4},"claude-fable-5-1":{"draws":2,"losses":90,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":39,"wins":18},"claude-opus-4-5":{"draws":50,"losses":90,"wins":74},"claude-opus-4-8":{"draws":33,"losses":72,"wins":33},"claude-opus-5":{"draws":27,"losses":169,"wins":8},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":13,"losses":50,"wins":29},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":16,"losses":11,"wins":23},"deepseek/deepseek-v4-flash":{"draws":55,"losses":52,"wins":63},"deepseek/deepseek-v4-pro":{"draws":17,"losses":42,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":42,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":20},"fireworks/ember-1":{"draws":25,"losses":35,"wins":18},"gemini-3.1-pro-preview":{"draws":20,"losses":34,"wins":24},"google/gemini-3.1-flash-lite":{"draws":23,"losses":6,"wins":79},"google/gemini-3.5-flash":{"draws":25,"losses":49,"wins":40},"google/gemini-3.5-flash-lite":{"draws":52,"losses":61,"wins":73},"google/gemini-3.6-flash":{"draws":44,"losses":102,"wins":40},"google/gemini-3.8-flash":{"draws":20,"losses":49,"wins":15},"google/gemma-4-31b-it":{"draws":15,"losses":5,"wins":22},"gpt-4.1":{"draws":12,"losses":28,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":36,"losses":44,"wins":30},"gpt-5.4":{"draws":15,"losses":61,"wins":12},"gpt-5.4-mini":{"draws":24,"losses":37,"wins":29},"gpt-5.4-nano":{"draws":38,"losses":55,"wins":75},"gpt-5.5":{"draws":39,"losses":58,"wins":27},"gpt-5.6-luna":{"draws":28,"losses":26,"wins":34},"gpt-5.6-sol":{"draws":14,"losses":59,"wins":21},"gpt-5.6-terra":{"draws":19,"losses":51,"wins":14},"gpt-6-astra":{"draws":4,"losses":80,"wins":2},"gpt-6-luna":{"draws":19,"losses":39,"wins":18},"gpt-6-sol":{"draws":6,"losses":63,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":70,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":16,"wins":27},"inclusionai/ling-3.0-flash":{"draws":35,"losses":20,"wins":49},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":40,"wins":65},"meta/muse-glimmer-30b":{"draws":27,"losses":18,"wins":31},"meta/muse-spark-1.2":{"draws":11,"losses":52,"wins":29},"meta/muse-spark-1.3":{"draws":10,"losses":61,"wins":15},"meta/muse-wonder":{"draws":7,"losses":48,"wins":15},"minimax/minimax-m3":{"draws":23,"losses":30,"wins":39},"mistralai/mistral-large-4-0":{"draws":9,"losses":24,"wins":11},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":21,"wins":5},"moonshotai/kimi-k3":{"draws":26,"losses":42,"wins":38},"nex-agi/nex-n2-pro":{"draws":22,"losses":20,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":27,"wins":54},"o3":{"draws":26,"losses":74,"wins":66},"openai/gpt-oss-120b":{"draws":23,"losses":20,"wins":29},"poolside/laguna-s-2.1":{"draws":37,"losses":40,"wins":49},"qwen/qwen3.7-max":{"draws":30,"losses":47,"wins":23},"qwen/qwen3.7-plus":{"draws":31,"losses":15,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":45,"wins":22},"qwen/qwen3.8-27b":{"draws":12,"losses":28,"wins":22},"qwen/qwen3.8-flash":{"draws":16,"losses":34,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":45,"wins":23},"qwen/qwen3.8-max-0902":{"draws":15,"losses":39,"wins":20},"stealth/ox-alpha":{"draws":51,"losses":144,"wins":69},"stealth/space-bunny-alpha":{"draws":24,"losses":23,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":18,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":32,"wins":26},"tencent/hy4-preview":{"draws":18,"losses":46,"wins":16},"thinkingmachines/inkling":{"draws":26,"losses":27,"wins":67},"thinkingmachines/inkling-small":{"draws":32,"losses":18,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":21,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":18,"losses":68,"wins":42},"x-ai/grok-4.6":{"draws":23,"losses":58,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":7},"x-ai/grok-build-0.1":{"draws":20,"losses":6,"wins":26},"xiaomi/mimo-v2.5":{"draws":79,"losses":51,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":11,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":27,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":25,"wins":16},"z-ai/glm-5.2":{"draws":79,"losses":79,"wins":70},"z-ai/glm-5.3":{"draws":16,"losses":58,"wins":6},"z-ai/glm-5.3-flash":{"draws":18,"losses":52,"wins":16},"z-ai/glm-5.3-flashx":{"draws":24,"losses":39,"wins":15}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":49},"claude-fable-5":{"draws":18,"losses":50,"wins":22},"claude-fable-5-1":{"draws":5,"losses":85,"wins":10},"claude-haiku-5-5":{"draws":18,"losses":35,"wins":27},"claude-opus-4-5":{"draws":33,"losses":45,"wins":68},"claude-opus-4-8":{"draws":16,"losses":28,"wins":38},"claude-opus-5":{"draws":16,"losses":119,"wins":17},"claude-opus-5-5":{"draws":9,"losses":87,"wins":2},"claude-sonnet-5":{"draws":17,"losses":23,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":46,"wins":34},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":33,"losses":26,"wins":79},"deepseek/deepseek-v4-pro":{"draws":22,"losses":28,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":33,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":33,"wins":32},"fireworks/ember-1":{"draws":18,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":17,"losses":31,"wins":42},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":44},"google/gemini-3.5-flash":{"draws":21,"losses":39,"wins":52},"google/gemini-3.5-flash-lite":{"draws":28,"losses":25,"wins":103},"google/gemini-3.6-flash":{"draws":24,"losses":66,"wins":66},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":28},"google/gemma-4-31b-it":{"draws":9,"losses":9,"wins":32},"gpt-4.1":{"draws":10,"losses":3,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":18,"losses":29,"wins":33},"gpt-5.4":{"draws":23,"losses":36,"wins":27},"gpt-5.4-mini":{"draws":16,"losses":13,"wins":31},"gpt-5.4-nano":{"draws":25,"losses":19,"wins":50},"gpt-5.5":{"draws":26,"losses":33,"wins":23},"gpt-5.6-luna":{"draws":22,"losses":25,"wins":43},"gpt-5.6-sol":{"draws":9,"losses":62,"wins":19},"gpt-5.6-terra":{"draws":20,"losses":34,"wins":31},"gpt-6-astra":{"draws":3,"losses":81,"wins":6},"gpt-6-luna":{"draws":20,"losses":33,"wins":35},"gpt-6-sol":{"draws":10,"losses":62,"wins":18},"gpt-6.1-sol":{"draws":4,"losses":79,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":41},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":41},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":54},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":43},"meta/muse-spark-1.2":{"draws":11,"losses":48,"wins":27},"meta/muse-spark-1.3":{"draws":13,"losses":50,"wins":25},"meta/muse-wonder":{"draws":5,"losses":57,"wins":22},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":28},"mistralai/mistral-large-4-0":{"draws":13,"losses":19,"wins":20},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":11},"moonshotai/kimi-k3":{"draws":20,"losses":31,"wins":31},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":15,"wins":43},"o3":{"draws":17,"losses":35,"wins":74},"openai/gpt-oss-120b":{"draws":22,"losses":6,"wins":52},"poolside/laguna-s-2.1":{"draws":25,"losses":14,"wins":51},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":28},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":33,"wins":35},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":16,"losses":22,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":31,"wins":38},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":39},"stealth/ox-alpha":{"draws":57,"losses":130,"wins":107},"stealth/space-bunny-alpha":{"draws":18,"losses":16,"wins":36},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":44},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":13,"wins":22},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":61},"thinkingmachines/inkling-small":{"draws":27,"losses":9,"wins":54},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":13,"losses":46,"wins":31},"x-ai/grok-4.6":{"draws":19,"losses":39,"wins":32},"x-ai/grok-4.7":{"draws":7,"losses":55,"wins":18},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":39,"losses":16,"wins":81},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":9,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":28,"wins":17},"z-ai/glm-5.2":{"draws":39,"losses":50,"wins":91},"z-ai/glm-5.3":{"draws":14,"losses":50,"wins":16},"z-ai/glm-5.3-flash":{"draws":22,"losses":41,"wins":27},"z-ai/glm-5.3-flashx":{"draws":21,"losses":35,"wins":34}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":55},"claude-fable-5":{"draws":8,"losses":45,"wins":39},"claude-fable-5-1":{"draws":14,"losses":80,"wins":10},"claude-haiku-5-5":{"draws":17,"losses":32,"wins":39},"claude-opus-4-5":{"draws":39,"losses":33,"wins":78},"claude-opus-4-8":{"draws":11,"losses":34,"wins":39},"claude-opus-5":{"draws":26,"losses":96,"wins":36},"claude-opus-5-5":{"draws":10,"losses":76,"wins":10},"claude-sonnet-5":{"draws":15,"losses":24,"wins":51},"claude-sonnet-5-5":{"draws":13,"losses":46,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":27},"deepseek/deepseek-v4-flash":{"draws":25,"losses":23,"wins":90},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":26,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":30,"wins":41},"fireworks/ember-1":{"draws":21,"losses":30,"wins":41},"gemini-3.1-pro-preview":{"draws":16,"losses":22,"wins":52},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":46},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":58},"google/gemini-3.5-flash-lite":{"draws":21,"losses":29,"wins":114},"google/gemini-3.6-flash":{"draws":35,"losses":55,"wins":72},"google/gemini-3.8-flash":{"draws":20,"losses":26,"wins":44},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":39},"gpt-4.1":{"draws":6,"losses":7,"wins":17},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":8},"gpt-5":{"draws":11,"losses":22,"wins":49},"gpt-5.4":{"draws":17,"losses":37,"wins":36},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":36},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":64},"gpt-5.5":{"draws":20,"losses":30,"wins":34},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":58},"gpt-5.6-sol":{"draws":18,"losses":41,"wins":31},"gpt-5.6-terra":{"draws":24,"losses":24,"wins":40},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":19,"losses":27,"wins":48},"gpt-6-sol":{"draws":18,"losses":53,"wins":23},"gpt-6.1-sol":{"draws":14,"losses":61,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":46},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":47},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":19,"losses":9,"wins":72},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":52},"meta/muse-spark-1.2":{"draws":12,"losses":27,"wins":49},"meta/muse-spark-1.3":{"draws":15,"losses":33,"wins":44},"meta/muse-wonder":{"draws":17,"losses":43,"wins":36},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":35},"mistralai/mistral-large-4-0":{"draws":13,"losses":19,"wins":26},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":14},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":45},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":48},"o3":{"draws":11,"losses":26,"wins":85},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":58},"poolside/laguna-s-2.1":{"draws":10,"losses":18,"wins":58},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":32},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":29,"wins":39},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":34},"qwen/qwen3.8-flash":{"draws":13,"losses":16,"wins":31},"qwen/qwen3.8-max":{"draws":25,"losses":18,"wins":49},"qwen/qwen3.8-max-0902":{"draws":14,"losses":30,"wins":46},"stealth/ox-alpha":{"draws":57,"losses":102,"wins":143},"stealth/space-bunny-alpha":{"draws":19,"losses":19,"wins":36},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":52},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":31},"tencent/hy4-preview":{"draws":16,"losses":32,"wins":38},"thinkingmachines/inkling":{"draws":23,"losses":10,"wins":71},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":69},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":16},"x-ai/grok-4.5":{"draws":17,"losses":32,"wins":43},"x-ai/grok-4.6":{"draws":21,"losses":34,"wins":37},"x-ai/grok-4.7":{"draws":6,"losses":54,"wins":18},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":22},"xiaomi/mimo-v2.5":{"draws":37,"losses":13,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":49,"losses":37,"wins":98},"z-ai/glm-5.3":{"draws":15,"losses":42,"wins":29},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":35,"wins":40}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":143,"losses":103,"wins":128},"claude-fable-5":{"draws":88,"losses":221,"wins":61},"claude-fable-5-1":{"draws":29,"losses":359,"wins":10},"claude-haiku-5-5":{"draws":58,"losses":139,"wins":61},"claude-opus-4-5":{"draws":216,"losses":283,"wins":205},"claude-opus-4-8":{"draws":121,"losses":194,"wins":85},"claude-opus-5":{"draws":111,"losses":492,"wins":49},"claude-opus-5-5":{"draws":18,"losses":283,"wins":11},"claude-sonnet-5":{"draws":121,"losses":169,"wins":126},"claude-sonnet-5-5":{"draws":55,"losses":168,"wins":65},"cohere/north-mini-code":{"draws":36,"losses":19,"wins":65},"deepseek/deepseek-v4-flash":{"draws":223,"losses":139,"wins":246},"deepseek/deepseek-v4-pro":{"draws":138,"losses":136,"wins":110},"deepseek/deepseek-v4-pro-0813":{"draws":140,"losses":132,"wins":108},"deepseek/deepseek-v4.1-flash":{"draws":103,"losses":122,"wins":62},"fireworks/ember-1":{"draws":94,"losses":128,"wins":66},"gemini-3.1-pro-preview":{"draws":85,"losses":109,"wins":94},"google/gemini-3.1-flash-lite":{"draws":67,"losses":35,"wins":168},"google/gemini-3.5-flash":{"draws":138,"losses":193,"wins":149},"google/gemini-3.5-flash-lite":{"draws":268,"losses":202,"wins":270},"google/gemini-3.6-flash":{"draws":200,"losses":288,"wins":198},"google/gemini-3.8-flash":{"draws":103,"losses":203,"wins":86},"google/gemma-4-31b-it":{"draws":60,"losses":28,"wins":68},"gpt-4.1":{"draws":49,"losses":37,"wins":54},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":123,"losses":126,"wins":109},"gpt-5.4":{"draws":123,"losses":172,"wins":79},"gpt-5.4-mini":{"draws":140,"losses":46,"wins":96},"gpt-5.4-nano":{"draws":113,"losses":138,"wins":163},"gpt-5.5":{"draws":148,"losses":157,"wins":75},"gpt-5.6-luna":{"draws":154,"losses":93,"wins":153},"gpt-5.6-sol":{"draws":48,"losses":268,"wins":62},"gpt-5.6-terra":{"draws":176,"losses":145,"wins":87},"gpt-6-astra":{"draws":27,"losses":312,"wins":13},"gpt-6-luna":{"draws":101,"losses":111,"wins":72},"gpt-6-sol":{"draws":45,"losses":212,"wins":31},"gpt-6.1-sol":{"draws":30,"losses":246,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":126,"losses":31,"wins":135},"inclusionai/ling-3.0-flash":{"draws":139,"losses":41,"wins":94},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":137,"losses":110,"wins":195},"meta/muse-glimmer-30b":{"draws":167,"losses":63,"wins":128},"meta/muse-spark-1.2":{"draws":84,"losses":158,"wins":102},"meta/muse-spark-1.3":{"draws":79,"losses":177,"wins":84},"meta/muse-wonder":{"draws":65,"losses":166,"wins":43},"minimax/minimax-m3":{"draws":72,"losses":46,"wins":88},"mistralai/mistral-large-4-0":{"draws":62,"losses":67,"wins":33},"mistralai/mistral-medium-3-5":{"draws":106,"losses":31,"wins":103},"moonshotai/kimi-k2.7-code":{"draws":23,"losses":42,"wins":43},"moonshotai/kimi-k3":{"draws":122,"losses":134,"wins":88},"nex-agi/nex-n2-pro":{"draws":85,"losses":24,"wins":83},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":160,"losses":68,"wins":116},"o3":{"draws":94,"losses":229,"wins":193},"openai/gpt-oss-120b":{"draws":145,"losses":74,"wins":141},"poolside/laguna-s-2.1":{"draws":192,"losses":98,"wins":130},"qwen/qwen3.7-max":{"draws":79,"losses":71,"wins":92},"qwen/qwen3.7-plus":{"draws":73,"losses":40,"wins":101},"qwen/qwen3.8-2.4t-a95b":{"draws":146,"losses":151,"wins":97},"qwen/qwen3.8-27b":{"draws":72,"losses":81,"wins":77},"qwen/qwen3.8-flash":{"draws":101,"losses":86,"wins":69},"qwen/qwen3.8-max":{"draws":139,"losses":149,"wins":104},"qwen/qwen3.8-max-0902":{"draws":94,"losses":133,"wins":55},"stealth/ox-alpha":{"draws":364,"losses":615,"wins":301},"stealth/space-bunny-alpha":{"draws":89,"losses":65,"wins":74},"stepfun/step-3.7-flash":{"draws":52,"losses":56,"wins":106},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":85,"losses":65,"wins":72},"tencent/hy4-preview":{"draws":105,"losses":186,"wins":79},"thinkingmachines/inkling":{"draws":141,"losses":96,"wins":195},"thinkingmachines/inkling-small":{"draws":160,"losses":88,"wins":166},"unbiased/pareto-26.10-preview":{"draws":4,"losses":80,"wins":4},"upstage/solar-mini4":{"draws":8,"losses":16,"wins":48},"x-ai/grok-4.5":{"draws":101,"losses":199,"wins":88},"x-ai/grok-4.6":{"draws":115,"losses":216,"wins":69},"x-ai/grok-4.7":{"draws":29,"losses":189,"wins":34},"x-ai/grok-build-0.1":{"draws":47,"losses":23,"wins":48},"xiaomi/mimo-v2.5":{"draws":249,"losses":129,"wins":260},"xiaomi/mimo-v2.5-pro":{"draws":79,"losses":70,"wins":79},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":91,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":49,"losses":98,"wins":37},"z-ai/glm-5.2":{"draws":260,"losses":206,"wins":206},"z-ai/glm-5.3":{"draws":90,"losses":186,"wins":58},"z-ai/glm-5.3-flash":{"draws":126,"losses":193,"wins":79},"z-ai/glm-5.3-flashx":{"draws":82,"losses":142,"wins":64}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":29,"wins":108},"claude-fable-5":{"draws":35,"losses":87,"wins":94},"claude-fable-5-1":{"draws":16,"losses":192,"wins":38},"claude-haiku-5-5":{"draws":23,"losses":29,"wins":74},"claude-opus-4-5":{"draws":66,"losses":48,"wins":162},"claude-opus-4-8":{"draws":24,"losses":34,"wins":72},"claude-opus-5":{"draws":33,"losses":148,"wins":57},"claude-opus-5-5":{"draws":8,"losses":112,"wins":22},"claude-sonnet-5":{"draws":46,"losses":31,"wins":129},"claude-sonnet-5-5":{"draws":25,"losses":49,"wins":58},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":41},"deepseek/deepseek-v4-flash":{"draws":68,"losses":16,"wins":176},"deepseek/deepseek-v4-pro":{"draws":43,"losses":42,"wins":107},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":47,"wins":98},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":27,"wins":79},"fireworks/ember-1":{"draws":26,"losses":27,"wins":81},"gemini-3.1-pro-preview":{"draws":25,"losses":31,"wins":76},"google/gemini-3.1-flash-lite":{"draws":17,"losses":1,"wins":76},"google/gemini-3.5-flash":{"draws":52,"losses":59,"wins":135},"google/gemini-3.5-flash-lite":{"draws":73,"losses":30,"wins":249},"google/gemini-3.6-flash":{"draws":67,"losses":89,"wins":192},"google/gemini-3.8-flash":{"draws":46,"losses":67,"wins":103},"google/gemma-4-31b-it":{"draws":21,"losses":6,"wins":53},"gpt-4.1":{"draws":8,"losses":8,"wins":30},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":19,"losses":22,"wins":81},"gpt-5.4":{"draws":43,"losses":72,"wins":93},"gpt-5.4-mini":{"draws":23,"losses":9,"wins":58},"gpt-5.4-nano":{"draws":20,"losses":25,"wins":93},"gpt-5.5":{"draws":33,"losses":26,"wins":67},"gpt-5.6-luna":{"draws":47,"losses":29,"wins":122},"gpt-5.6-sol":{"draws":39,"losses":105,"wins":74},"gpt-5.6-terra":{"draws":63,"losses":35,"wins":104},"gpt-6-astra":{"draws":34,"losses":172,"wins":14},"gpt-6-luna":{"draws":26,"losses":25,"wins":79},"gpt-6-sol":{"draws":21,"losses":70,"wins":43},"gpt-6.1-sol":{"draws":22,"losses":91,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":48,"losses":7,"wins":79},"inclusionai/ling-3.0-flash":{"draws":28,"losses":3,"wins":77},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":16,"wins":120},"meta/muse-glimmer-30b":{"draws":37,"losses":20,"wins":107},"meta/muse-spark-1.2":{"draws":29,"losses":57,"wins":84},"meta/muse-spark-1.3":{"draws":36,"losses":54,"wins":92},"meta/muse-wonder":{"draws":17,"losses":62,"wins":59},"minimax/minimax-m3":{"draws":17,"losses":6,"wins":51},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":49},"mistralai/mistral-medium-3-5":{"draws":27,"losses":8,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":19},"moonshotai/kimi-k3":{"draws":44,"losses":48,"wins":84},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":57},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":16,"wins":82},"o3":{"draws":23,"losses":53,"wins":166},"openai/gpt-oss-120b":{"draws":53,"losses":8,"wins":103},"poolside/laguna-s-2.1":{"draws":41,"losses":20,"wins":103},"qwen/qwen3.7-max":{"draws":21,"losses":15,"wins":44},"qwen/qwen3.7-plus":{"draws":15,"losses":6,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":45,"wins":113},"qwen/qwen3.8-27b":{"draws":30,"losses":18,"wins":70},"qwen/qwen3.8-flash":{"draws":44,"losses":25,"wins":71},"qwen/qwen3.8-max":{"draws":51,"losses":53,"wins":104},"qwen/qwen3.8-max-0902":{"draws":33,"losses":30,"wins":69},"stealth/ox-alpha":{"draws":141,"losses":191,"wins":354},"stealth/space-bunny-alpha":{"draws":25,"losses":9,"wins":72},"stepfun/step-3.7-flash":{"draws":13,"losses":3,"wins":74},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":48},"tencent/hy4-preview":{"draws":39,"losses":42,"wins":119},"thinkingmachines/inkling":{"draws":37,"losses":20,"wins":123},"thinkingmachines/inkling-small":{"draws":43,"losses":21,"wins":134},"unbiased/pareto-26.10-preview":{"draws":4,"losses":37,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":32},"x-ai/grok-4.5":{"draws":38,"losses":47,"wins":103},"x-ai/grok-4.6":{"draws":49,"losses":75,"wins":92},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":32},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":32},"xiaomi/mimo-v2.5":{"draws":51,"losses":4,"wins":159},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":6,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":16,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":29,"wins":42},"z-ai/glm-5.2":{"draws":90,"losses":58,"wins":186},"z-ai/glm-5.3":{"draws":26,"losses":41,"wins":41},"z-ai/glm-5.3-flash":{"draws":53,"losses":57,"wins":100},"z-ai/glm-5.3-flashx":{"draws":27,"losses":33,"wins":72}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":66,"losses":37,"wins":111},"claude-fable-5":{"draws":44,"losses":124,"wins":80},"claude-fable-5-1":{"draws":24,"losses":238,"wins":30},"claude-haiku-5-5":{"draws":22,"losses":53,"wins":57},"claude-opus-4-5":{"draws":77,"losses":78,"wins":163},"claude-opus-4-8":{"draws":22,"losses":58,"wins":62},"claude-opus-5":{"draws":35,"losses":196,"wins":61},"claude-opus-5-5":{"draws":13,"losses":132,"wins":11},"claude-sonnet-5":{"draws":55,"losses":69,"wins":132},"claude-sonnet-5-5":{"draws":20,"losses":69,"wins":55},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":36},"deepseek/deepseek-v4-flash":{"draws":97,"losses":49,"wins":154},"deepseek/deepseek-v4-pro":{"draws":58,"losses":65,"wins":105},"deepseek/deepseek-v4-pro-0813":{"draws":55,"losses":59,"wins":112},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":47,"wins":59},"fireworks/ember-1":{"draws":32,"losses":45,"wins":67},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":66},"google/gemini-3.1-flash-lite":{"draws":25,"losses":11,"wins":64},"google/gemini-3.5-flash":{"draws":67,"losses":96,"wins":127},"google/gemini-3.5-flash-lite":{"draws":122,"losses":69,"wins":235},"google/gemini-3.6-flash":{"draws":91,"losses":135,"wins":190},"google/gemini-3.8-flash":{"draws":53,"losses":114,"wins":91},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":45},"gpt-4.1":{"draws":8,"losses":12,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":38,"losses":30,"wins":68},"gpt-5.4":{"draws":51,"losses":105,"wins":90},"gpt-5.4-mini":{"draws":35,"losses":16,"wins":51},"gpt-5.4-nano":{"draws":29,"losses":36,"wins":79},"gpt-5.5":{"draws":33,"losses":45,"wins":60},"gpt-5.6-luna":{"draws":75,"losses":52,"wins":113},"gpt-5.6-sol":{"draws":46,"losses":132,"wins":90},"gpt-5.6-terra":{"draws":66,"losses":72,"wins":104},"gpt-6-astra":{"draws":32,"losses":209,"wins":15},"gpt-6-luna":{"draws":39,"losses":33,"wins":70},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":56,"losses":17,"wins":87},"inclusionai/ling-3.0-flash":{"draws":34,"losses":9,"wins":71},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":49,"losses":41,"wins":114},"meta/muse-glimmer-30b":{"draws":67,"losses":23,"wins":116},"meta/muse-spark-1.2":{"draws":33,"losses":76,"wins":93},"meta/muse-spark-1.3":{"draws":45,"losses":74,"wins":95},"meta/muse-wonder":{"draws":28,"losses":67,"wins":43},"minimax/minimax-m3":{"draws":20,"losses":14,"wins":44},"mistralai/mistral-large-4-0":{"draws":20,"losses":22,"wins":42},"mistralai/mistral-medium-3-5":{"draws":45,"losses":21,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":58,"losses":66,"wins":84},"nex-agi/nex-n2-pro":{"draws":19,"losses":6,"wins":49},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":29,"wins":56},"o3":{"draws":44,"losses":112,"wins":130},"openai/gpt-oss-120b":{"draws":61,"losses":19,"wins":112},"poolside/laguna-s-2.1":{"draws":67,"losses":29,"wins":94},"qwen/qwen3.7-max":{"draws":27,"losses":19,"wins":38},"qwen/qwen3.7-plus":{"draws":23,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":60,"losses":87,"wins":97},"qwen/qwen3.8-27b":{"draws":27,"losses":47,"wins":60},"qwen/qwen3.8-flash":{"draws":52,"losses":54,"wins":58},"qwen/qwen3.8-max":{"draws":70,"losses":89,"wins":87},"qwen/qwen3.8-max-0902":{"draws":39,"losses":49,"wins":52},"stealth/ox-alpha":{"draws":181,"losses":309,"wins":349},"stealth/space-bunny-alpha":{"draws":30,"losses":17,"wins":67},"stepfun/step-3.7-flash":{"draws":25,"losses":18,"wins":65},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":25,"losses":15,"wins":46},"tencent/hy4-preview":{"draws":55,"losses":81,"wins":100},"thinkingmachines/inkling":{"draws":50,"losses":29,"wins":125},"thinkingmachines/inkling-small":{"draws":81,"losses":39,"wins":128},"unbiased/pareto-26.10-preview":{"draws":3,"losses":37,"wins":6},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":33,"losses":84,"wins":89},"x-ai/grok-4.6":{"draws":63,"losses":97,"wins":94},"x-ai/grok-4.7":{"draws":15,"losses":77,"wins":34},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":28},"xiaomi/mimo-v2.5":{"draws":67,"losses":35,"wins":126},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":16,"wins":52},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":27,"wins":41},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":46,"wins":30},"z-ai/glm-5.2":{"draws":126,"losses":79,"wins":193},"z-ai/glm-5.3":{"draws":53,"losses":100,"wins":57},"z-ai/glm-5.3-flash":{"draws":48,"losses":62,"wins":62},"z-ai/glm-5.3-flashx":{"draws":40,"losses":50,"wins":54}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":83},"claude-fable-5":{"draws":29,"losses":73,"wins":42},"claude-fable-5-1":{"draws":15,"losses":134,"wins":13},"claude-haiku-5-5":{"draws":24,"losses":55,"wins":51},"claude-opus-4-5":{"draws":53,"losses":55,"wins":126},"claude-opus-4-8":{"draws":25,"losses":58,"wins":49},"claude-opus-5":{"draws":36,"losses":166,"wins":44},"claude-opus-5-5":{"draws":15,"losses":131,"wins":10},"claude-sonnet-5":{"draws":39,"losses":33,"wins":72},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":54},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":38},"deepseek/deepseek-v4-flash":{"draws":58,"losses":32,"wins":126},"deepseek/deepseek-v4-pro":{"draws":32,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":37,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":35,"losses":51,"wins":58},"gemini-3.1-pro-preview":{"draws":35,"losses":34,"wins":75},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":64},"google/gemini-3.5-flash":{"draws":48,"losses":43,"wins":87},"google/gemini-3.5-flash-lite":{"draws":67,"losses":47,"wins":137},"google/gemini-3.6-flash":{"draws":62,"losses":91,"wins":99},"google/gemini-3.8-flash":{"draws":29,"losses":64,"wins":51},"google/gemma-4-31b-it":{"draws":25,"losses":6,"wins":45},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":38,"losses":32,"wins":56},"gpt-5.4":{"draws":34,"losses":50,"wins":54},"gpt-5.4-mini":{"draws":27,"losses":13,"wins":56},"gpt-5.4-nano":{"draws":28,"losses":33,"wins":81},"gpt-5.5":{"draws":42,"losses":44,"wins":46},"gpt-5.6-luna":{"draws":42,"losses":29,"wins":73},"gpt-5.6-sol":{"draws":23,"losses":80,"wins":41},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":63},"gpt-6-astra":{"draws":14,"losses":121,"wins":9},"gpt-6-luna":{"draws":30,"losses":40,"wins":72},"gpt-6-sol":{"draws":20,"losses":87,"wins":37},"gpt-6.1-sol":{"draws":19,"losses":107,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":5,"wins":68},"inclusionai/ling-3.0-flash":{"draws":31,"losses":8,"wins":59},"meituan/longcat-2.0":{"draws":36,"losses":19,"wins":100},"meta/muse-glimmer-30b":{"draws":36,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":29,"losses":47,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":56,"wins":55},"meta/muse-wonder":{"draws":32,"losses":65,"wins":37},"minimax/minimax-m3":{"draws":20,"losses":12,"wins":46},"mistralai/mistral-large-4-0":{"draws":23,"losses":25,"wins":34},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":12},"moonshotai/kimi-k3":{"draws":37,"losses":34,"wins":61},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":21,"wins":74},"o3":{"draws":19,"losses":57,"wins":118},"openai/gpt-oss-120b":{"draws":37,"losses":13,"wins":76},"poolside/laguna-s-2.1":{"draws":40,"losses":23,"wins":75},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":45,"wins":61},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":32,"losses":22,"wins":42},"qwen/qwen3.8-max":{"draws":40,"losses":48,"wins":56},"qwen/qwen3.8-max-0902":{"draws":33,"losses":50,"wins":57},"stealth/ox-alpha":{"draws":85,"losses":167,"wins":216},"stealth/space-bunny-alpha":{"draws":33,"losses":22,"wins":59},"stepfun/step-3.7-flash":{"draws":12,"losses":14,"wins":70},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":14,"wins":46},"tencent/hy4-preview":{"draws":32,"losses":57,"wins":49},"thinkingmachines/inkling":{"draws":37,"losses":15,"wins":110},"thinkingmachines/inkling-small":{"draws":36,"losses":23,"wins":85},"unbiased/pareto-26.10-preview":{"draws":3,"losses":38,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":25,"losses":59,"wins":60},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":52},"x-ai/grok-4.7":{"draws":15,"losses":84,"wins":27},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":30},"xiaomi/mimo-v2.5":{"draws":73,"losses":16,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":34,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":40,"wins":35},"z-ai/glm-5.2":{"draws":82,"losses":64,"wins":142},"z-ai/glm-5.3":{"draws":27,"losses":72,"wins":33},"z-ai/glm-5.3-flash":{"draws":40,"losses":54,"wins":50},"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":21,"losses":16,"wins":19},"claude-fable-5":{"draws":15,"losses":55,"wins":8},"claude-fable-5-1":{"draws":5,"losses":77,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":43,"losses":45,"wins":20},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":66,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":30,"losses":40,"wins":16},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":40,"losses":31,"wins":41},"deepseek/deepseek-v4-pro":{"draws":17,"losses":36,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":29,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":17},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":35,"losses":42,"wins":21},"google/gemini-3.5-flash-lite":{"draws":74,"losses":35,"wins":51},"google/gemini-3.6-flash":{"draws":44,"losses":59,"wins":33},"google/gemini-3.8-flash":{"draws":25,"losses":41,"wins":12},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":21,"losses":16,"wins":11},"gpt-5.4":{"draws":22,"losses":37,"wins":15},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":15,"losses":16,"wins":17},"gpt-5.5":{"draws":26,"losses":15,"wins":11},"gpt-5.6-luna":{"draws":42,"losses":22,"wins":26},"gpt-5.6-sol":{"draws":14,"losses":50,"wins":14},"gpt-5.6-terra":{"draws":29,"losses":34,"wins":19},"gpt-6-astra":{"draws":4,"losses":65,"wins":3},"gpt-6-luna":{"draws":15,"losses":17,"wins":14},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":14,"wins":22},"inclusionai/ling-3.0-flash":{"draws":23,"losses":5,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":13,"wins":31},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":26},"meta/muse-spark-1.2":{"draws":22,"losses":25,"wins":21},"meta/muse-spark-1.3":{"draws":24,"losses":35,"wins":10},"meta/muse-wonder":{"draws":11,"losses":28,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":8,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":26,"losses":34,"wins":12},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":14,"wins":15},"o3":{"draws":21,"losses":41,"wins":36},"openai/gpt-oss-120b":{"draws":35,"losses":13,"wins":32},"poolside/laguna-s-2.1":{"draws":38,"losses":11,"wins":21},"qwen/qwen3.7-max":{"draws":12,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":29,"wins":23},"qwen/qwen3.8-27b":{"draws":10,"losses":24,"wins":8},"qwen/qwen3.8-flash":{"draws":24,"losses":22,"wins":10},"qwen/qwen3.8-max":{"draws":33,"losses":29,"wins":28},"qwen/qwen3.8-max-0902":{"draws":16,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":76,"losses":140,"wins":58},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":17},"tencent/hy3-preview":{"draws":12,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":32,"losses":45,"wins":11},"thinkingmachines/inkling":{"draws":31,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":42,"losses":18,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":23,"losses":43,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":54,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":32,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":58,"losses":44,"wins":44},"z-ai/glm-5.3":{"draws":18,"losses":41,"wins":7},"z-ai/glm-5.3-flash":{"draws":29,"losses":42,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":50},"claude-fable-5":{"draws":3,"losses":25,"wins":30},"claude-fable-5-1":{"draws":10,"losses":76,"wins":22},"claude-haiku-5-5":{"draws":6,"losses":14,"wins":24},"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},"claude-sonnet-5-5":{"draws":1,"losses":19,"wins":28},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"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},"fireworks/ember-1":{"draws":6,"losses":5,"wins":37},"gemini-3.1-pro-preview":{"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":0,"wins":24},"gpt-4.1":{"draws":2,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":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":8,"losses":11,"wins":27},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":38},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":30},"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":2,"losses":12,"wins":52},"meta/muse-spark-1.3":{"draws":9,"losses":14,"wins":45},"meta/muse-wonder":{"draws":5,"losses":14,"wins":27},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-large-4-0":{"draws":1,"losses":4,"wins":21},"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":8,"losses":14,"wins":48},"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":9,"losses":18,"wins":63},"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":2,"losses":5,"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":5,"losses":10,"wins":31},"stealth/ox-alpha":{"draws":43,"losses":39,"wins":196},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":28},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":17,"wins":49},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":54},"thinkingmachines/inkling-small":{"draws":11,"losses":2,"wins":55},"unbiased/pareto-26.10-preview":{"draws":3,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":18,"wins":51},"x-ai/grok-4.6":{"draws":20,"losses":26,"wins":46},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":17},"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":3,"losses":7,"wins":20},"z-ai/glm-5.2":{"draws":19,"losses":13,"wins":86},"z-ai/glm-5.3":{"draws":15,"losses":16,"wins":43},"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":86},"claude-fable-5":{"draws":3,"losses":8,"wins":111},"claude-fable-5-1":{"draws":10,"losses":22,"wins":80},"claude-haiku-5-5":{"draws":4,"losses":0,"wins":58},"claude-opus-4-5":{"draws":2,"losses":4,"wins":138},"claude-opus-4-8":{"draws":0,"losses":3,"wins":55},"claude-opus-5":{"draws":8,"losses":20,"wins":88},"claude-opus-5-5":{"draws":8,"losses":32,"wins":30},"claude-sonnet-5":{"draws":0,"losses":2,"wins":117},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":52},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":122},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":95},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":101},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":59},"fireworks/ember-1":{"draws":0,"losses":1,"wins":65},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":63},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":41},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":122},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":169},"google/gemini-3.6-flash":{"draws":8,"losses":7,"wins":169},"google/gemini-3.8-flash":{"draws":8,"losses":6,"wins":110},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":35},"gpt-4.1":{"draws":0,"losses":0,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":58},"gpt-5.4":{"draws":1,"losses":6,"wins":107},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":58},"gpt-5.5":{"draws":0,"losses":3,"wins":59},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":95},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":114},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":110},"gpt-6-astra":{"draws":7,"losses":51,"wins":74},"gpt-6-luna":{"draws":1,"losses":1,"wins":62},"gpt-6-sol":{"draws":2,"losses":11,"wins":53},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":60},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":46},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":79},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":74},"meta/muse-spark-1.2":{"draws":1,"losses":7,"wins":84},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":90},"meta/muse-wonder":{"draws":4,"losses":7,"wins":53},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":33},"mistralai/mistral-large-4-0":{"draws":0,"losses":4,"wins":36},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":90},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":50},"o3":{"draws":0,"losses":1,"wins":113},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":69},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":73},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":110},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":60},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":66},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":106},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":61},"stealth/ox-alpha":{"draws":22,"losses":9,"wins":383},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":53},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":31},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":101},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":86},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":97},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":10},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":91},"x-ai/grok-4.6":{"draws":3,"losses":13,"wins":108},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":49},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":37},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":157},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":90},"z-ai/glm-5.3-flash":{"draws":3,"losses":11,"wins":106},"z-ai/glm-5.3-flashx":{"draws":6,"losses":1,"wins":59}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":33},"claude-fable-5":{"draws":5,"losses":10,"wins":25},"claude-fable-5-1":{"draws":4,"losses":39,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":18},"claude-opus-4-5":{"draws":12,"losses":5,"wins":45},"claude-opus-4-8":{"draws":7,"losses":10,"wins":21},"claude-opus-5":{"draws":10,"losses":35,"wins":21},"claude-opus-5-5":{"draws":6,"losses":28,"wins":6},"claude-sonnet-5":{"draws":5,"losses":4,"wins":31},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":44},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":21},"fireworks/ember-1":{"draws":5,"losses":8,"wins":27},"gemini-3.1-pro-preview":{"draws":4,"losses":8,"wins":26},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":34},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":59},"google/gemini-3.6-flash":{"draws":8,"losses":18,"wins":42},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":22},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":23},"gpt-4.1":{"draws":1,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":4,"wins":23},"gpt-5.4":{"draws":2,"losses":9,"wins":25},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":33},"gpt-5.5":{"draws":5,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":32},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":19},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":24},"gpt-6-astra":{"draws":4,"losses":27,"wins":5},"gpt-6-luna":{"draws":6,"losses":6,"wins":28},"gpt-6-sol":{"draws":12,"losses":12,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":26,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":33},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":24},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":30},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":32},"meta/muse-wonder":{"draws":9,"losses":16,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":17},"mistralai/mistral-large-4-0":{"draws":4,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":27},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":26},"o3":{"draws":2,"losses":11,"wins":45},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":27},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":24},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":6,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":27},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":17,"losses":20,"wins":73},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":19},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":4,"losses":7,"wins":25},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":35},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":6},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":22},"x-ai/grok-4.6":{"draws":4,"losses":10,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":8,"wins":63},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":17},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":3,"losses":9,"wins":28}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":10,"wins":50},"claude-fable-5":{"draws":17,"losses":64,"wins":15},"claude-fable-5-1":{"draws":6,"losses":92,"wins":6},"claude-haiku-5-5":{"draws":11,"losses":15,"wins":16},"claude-opus-4-5":{"draws":32,"losses":39,"wins":35},"claude-opus-4-8":{"draws":15,"losses":29,"wins":16},"claude-opus-5":{"draws":19,"losses":136,"wins":11},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":61,"losses":26,"wins":55},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":32,"losses":19,"wins":59},"deepseek/deepseek-v4-pro":{"draws":24,"losses":27,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":32,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":13},"fireworks/ember-1":{"draws":16,"losses":16,"wins":16},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":28},"google/gemini-3.5-flash":{"draws":23,"losses":42,"wins":35},"google/gemini-3.5-flash-lite":{"draws":103,"losses":65,"wins":122},"google/gemini-3.6-flash":{"draws":73,"losses":122,"wins":77},"google/gemini-3.8-flash":{"draws":27,"losses":55,"wins":12},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":14},"gpt-4.1":{"draws":11,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":19,"losses":19,"wins":22},"gpt-5.4":{"draws":42,"losses":68,"wins":26},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":20},"gpt-5.5":{"draws":20,"losses":28,"wins":14},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":59},"gpt-5.6-sol":{"draws":18,"losses":91,"wins":33},"gpt-5.6-terra":{"draws":28,"losses":20,"wins":34},"gpt-6-astra":{"draws":2,"losses":87,"wins":3},"gpt-6-luna":{"draws":13,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":4,"wins":32},"inclusionai/ling-3.0-flash":{"draws":18,"losses":17,"wins":29},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":25,"losses":26,"wins":61},"meta/muse-glimmer-30b":{"draws":32,"losses":6,"wins":40},"meta/muse-spark-1.2":{"draws":25,"losses":47,"wins":28},"meta/muse-spark-1.3":{"draws":16,"losses":37,"wins":19},"meta/muse-wonder":{"draws":8,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":33,"losses":49,"wins":40},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":5,"wins":28},"o3":{"draws":29,"losses":41,"wins":110},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":47},"poolside/laguna-s-2.1":{"draws":48,"losses":11,"wins":55},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":34,"wins":21},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":18},"qwen/qwen3.8-flash":{"draws":16,"losses":23,"wins":19},"qwen/qwen3.8-max":{"draws":27,"losses":41,"wins":24},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":81,"losses":120,"wins":103},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":14},"tencent/hy4-preview":{"draws":26,"losses":38,"wins":26},"thinkingmachines/inkling":{"draws":30,"losses":8,"wins":64},"thinkingmachines/inkling-small":{"draws":41,"losses":18,"wins":37},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":46,"losses":65,"wins":33},"x-ai/grok-4.6":{"draws":26,"losses":50,"wins":16},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":32,"losses":12,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":13,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":45,"losses":36,"wins":61},"z-ai/glm-5.3":{"draws":17,"losses":45,"wins":14},"z-ai/glm-5.3-flash":{"draws":21,"losses":45,"wins":22},"z-ai/glm-5.3-flashx":{"draws":17,"losses":19,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":31},"claude-fable-5":{"draws":7,"losses":15,"wins":22},"claude-fable-5-1":{"draws":3,"losses":34,"wins":9},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":24},"claude-opus-4-5":{"draws":19,"losses":22,"wins":91},"claude-opus-4-8":{"draws":4,"losses":9,"wins":37},"claude-opus-5":{"draws":37,"losses":90,"wins":55},"claude-opus-5-5":{"draws":9,"losses":28,"wins":9},"claude-sonnet-5":{"draws":8,"losses":5,"wins":29},"claude-sonnet-5-5":{"draws":10,"losses":11,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":60},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":24},"fireworks/ember-1":{"draws":10,"losses":6,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":28},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":46},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":45},"google/gemini-3.5-flash-lite":{"draws":8,"losses":6,"wins":78},"google/gemini-3.6-flash":{"draws":14,"losses":37,"wins":55},"google/gemini-3.8-flash":{"draws":8,"losses":13,"wins":27},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":19},"gpt-4.1":{"draws":4,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":12,"wins":58},"gpt-5.4":{"draws":4,"losses":16,"wins":26},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":31},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":61},"gpt-5.5":{"draws":16,"losses":34,"wins":32},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":29},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":33},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":32},"gpt-6-astra":{"draws":7,"losses":33,"wins":4},"gpt-6-luna":{"draws":9,"losses":4,"wins":29},"gpt-6-sol":{"draws":8,"losses":19,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":28,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":25},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":30},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":22},"meta/muse-wonder":{"draws":7,"losses":13,"wins":18},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":34},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":21},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":61},"o3":{"draws":6,"losses":14,"wins":78},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":43},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":25},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":23},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":19},"qwen/qwen3.8-max":{"draws":1,"losses":11,"wins":34},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":18},"stealth/ox-alpha":{"draws":29,"losses":24,"wins":73},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":1,"losses":6,"wins":35},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":10,"wins":32},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":29},"thinkingmachines/inkling":{"draws":10,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":15,"wins":39},"x-ai/grok-4.6":{"draws":8,"losses":15,"wins":23},"x-ai/grok-4.7":{"draws":7,"losses":19,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":5,"wins":17},"xiaomi/mimo-v2.5":{"draws":20,"losses":4,"wins":86},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":16},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":92},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":21},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":29},"z-ai/glm-5.3-flashx":{"draws":8,"losses":4,"wins":30}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":7,"wins":64},"claude-fable-5":{"draws":4,"losses":19,"wins":69},"claude-fable-5-1":{"draws":13,"losses":38,"wins":45},"claude-haiku-5-5":{"draws":1,"losses":11,"wins":58},"claude-opus-4-5":{"draws":11,"losses":19,"wins":190},"claude-opus-4-8":{"draws":9,"losses":31,"wins":98},"claude-opus-5":{"draws":31,"losses":108,"wins":209},"claude-opus-5-5":{"draws":5,"losses":44,"wins":37},"claude-sonnet-5":{"draws":3,"losses":6,"wins":69},"claude-sonnet-5-5":{"draws":3,"losses":17,"wins":58},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":27},"deepseek/deepseek-v4-flash":{"draws":3,"losses":9,"wins":112},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":68},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":7,"wins":62},"fireworks/ember-1":{"draws":3,"losses":14,"wins":61},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":69},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":66},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":86},"google/gemini-3.5-flash-lite":{"draws":7,"losses":8,"wins":161},"google/gemini-3.6-flash":{"draws":13,"losses":28,"wins":149},"google/gemini-3.8-flash":{"draws":4,"losses":17,"wins":75},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":38},"gpt-4.1":{"draws":1,"losses":2,"wins":37},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":2,"losses":8,"wins":96},"gpt-5.4":{"draws":3,"losses":8,"wins":67},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":57},"gpt-5.4-nano":{"draws":3,"losses":11,"wins":86},"gpt-5.5":{"draws":6,"losses":19,"wins":101},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":72},"gpt-5.6-sol":{"draws":12,"losses":15,"wins":73},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":68},"gpt-6-astra":{"draws":13,"losses":45,"wins":30},"gpt-6-luna":{"draws":11,"losses":4,"wins":59},"gpt-6-sol":{"draws":7,"losses":24,"wins":47},"gpt-6.1-sol":{"draws":11,"losses":38,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":47},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":41},"meituan/longcat-2.0":{"draws":3,"losses":11,"wins":74},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":69},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":69},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":65},"meta/muse-wonder":{"draws":5,"losses":15,"wins":52},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":55},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":38},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":34},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":68},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":6,"wins":97},"o3":{"draws":2,"losses":9,"wins":131},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":59},"poolside/laguna-s-2.1":{"draws":1,"losses":7,"wins":92},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":49},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":73},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":50},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":53},"qwen/qwen3.8-max":{"draws":3,"losses":6,"wins":73},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":65},"stealth/ox-alpha":{"draws":22,"losses":24,"wins":256},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":57},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":56},"tencent/hy3-preview":{"draws":4,"losses":5,"wins":63},"tencent/hy4-preview":{"draws":6,"losses":7,"wins":73},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":117},"thinkingmachines/inkling-small":{"draws":2,"losses":6,"wins":72},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":99},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":70},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":45},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":31},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":38},"z-ai/glm-5.2":{"draws":12,"losses":13,"wins":155},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":67},"z-ai/glm-5.3-flash":{"draws":7,"losses":12,"wins":77},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":64}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":2,"losses":3,"wins":43},"claude-fable-5-1":{"draws":4,"losses":8,"wins":42},"claude-haiku-5-5":{"draws":2,"losses":1,"wins":39},"claude-opus-4-5":{"draws":0,"losses":0,"wins":78},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":5,"losses":9,"wins":68},"claude-opus-5-5":{"draws":3,"losses":7,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":4,"losses":5,"wins":39},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":45},"fireworks/ember-1":{"draws":0,"losses":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":58},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":83},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":80},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":45},"google/gemma-4-31b-it":{"draws":0,"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":0,"losses":0,"wins":42},"gpt-5.4":{"draws":0,"losses":4,"wins":42},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":45},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":44},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":4,"losses":15,"wins":29},"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":7,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":2,"wins":43},"meta/muse-wonder":{"draws":1,"losses":4,"wins":41},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":1,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":41},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":43},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":31},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":41},"stealth/ox-alpha":{"draws":2,"losses":1,"wins":153},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":32},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":45},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":53},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":3,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":44},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":1,"losses":1,"wins":42},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":43}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":7,"wins":45},"claude-fable-5":{"draws":14,"losses":45,"wins":23},"claude-fable-5-1":{"draws":4,"losses":89,"wins":3},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":21},"claude-opus-4-5":{"draws":45,"losses":44,"wins":51},"claude-opus-4-8":{"draws":10,"losses":14,"wins":20},"claude-opus-5":{"draws":10,"losses":67,"wins":17},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":26,"losses":11,"wins":55},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":15},"deepseek/deepseek-v4-flash":{"draws":30,"losses":12,"wins":62},"deepseek/deepseek-v4-pro":{"draws":16,"losses":21,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":26,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":35,"wins":38},"google/gemini-3.5-flash-lite":{"draws":44,"losses":31,"wins":137},"google/gemini-3.6-flash":{"draws":32,"losses":76,"wins":106},"google/gemini-3.8-flash":{"draws":18,"losses":33,"wins":35},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":15},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":32,"losses":52,"wins":42},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":31},"gpt-5.5":{"draws":12,"losses":23,"wins":15},"gpt-5.6-luna":{"draws":35,"losses":36,"wins":53},"gpt-5.6-sol":{"draws":22,"losses":95,"wins":27},"gpt-5.6-terra":{"draws":18,"losses":21,"wins":41},"gpt-6-astra":{"draws":3,"losses":73,"wins":10},"gpt-6-luna":{"draws":10,"losses":19,"wins":17},"gpt-6-sol":{"draws":8,"losses":31,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":3,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":32},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":64},"meta/muse-glimmer-30b":{"draws":14,"losses":9,"wins":39},"meta/muse-spark-1.2":{"draws":32,"losses":23,"wins":45},"meta/muse-spark-1.3":{"draws":13,"losses":28,"wins":27},"meta/muse-wonder":{"draws":11,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":12,"losses":9,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":26,"losses":42,"wins":34},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":21},"o3":{"draws":7,"losses":54,"wins":73},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":40},"poolside/laguna-s-2.1":{"draws":20,"losses":3,"wins":57},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":17},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":30,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":24},"qwen/qwen3.8-flash":{"draws":16,"losses":14,"wins":22},"qwen/qwen3.8-max":{"draws":13,"losses":28,"wins":45},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":15},"stealth/ox-alpha":{"draws":66,"losses":104,"wins":109},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":15},"tencent/hy4-preview":{"draws":13,"losses":33,"wins":36},"thinkingmachines/inkling":{"draws":23,"losses":13,"wins":48},"thinkingmachines/inkling-small":{"draws":21,"losses":13,"wins":48},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":39,"losses":44,"wins":23},"x-ai/grok-4.6":{"draws":18,"losses":38,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":26,"losses":36,"wins":62},"z-ai/glm-5.3":{"draws":14,"losses":38,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":47,"wins":27},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":0,"wins":37},"claude-fable-5":{"draws":5,"losses":2,"wins":41},"claude-fable-5-1":{"draws":7,"losses":16,"wins":31},"claude-haiku-5-5":{"draws":5,"losses":2,"wins":35},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":5,"losses":1,"wins":38},"claude-opus-5":{"draws":6,"losses":16,"wins":60},"claude-opus-5-5":{"draws":10,"losses":17,"wins":25},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":1,"losses":1,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":41},"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":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":55},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":71},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":0,"wins":39},"gpt-5.4":{"draws":9,"losses":1,"wins":36},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":4,"losses":1,"wins":39},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":42},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":42},"gpt-6-astra":{"draws":7,"losses":16,"wins":25},"gpt-6-luna":{"draws":8,"losses":1,"wins":39},"gpt-6-sol":{"draws":7,"losses":6,"wins":35},"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":3,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":41},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":42},"meta/muse-wonder":{"draws":5,"losses":1,"wins":40},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":38},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"o3":{"draws":2,"losses":1,"wins":61},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":44},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":46},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":39},"stealth/ox-alpha":{"draws":10,"losses":4,"wins":142},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":3,"losses":0,"wins":43},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":5,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":1,"wins":41},"x-ai/grok-4.6":{"draws":5,"losses":0,"wins":43},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":90},"z-ai/glm-5.3":{"draws":7,"losses":3,"wins":34},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":39}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":13,"wins":17},"claude-fable-5":{"draws":14,"losses":42,"wins":12},"claude-fable-5-1":{"draws":5,"losses":70,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":6},"claude-opus-4-5":{"draws":23,"losses":43,"wins":24},"claude-opus-4-8":{"draws":10,"losses":21,"wins":7},"claude-opus-5":{"draws":12,"losses":49,"wins":9},"claude-opus-5-5":{"draws":4,"losses":40,"wins":2},"claude-sonnet-5":{"draws":29,"losses":34,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":20,"losses":25,"wins":31},"deepseek/deepseek-v4-pro":{"draws":35,"losses":28,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":23,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":18,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":13,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":33,"losses":28,"wins":23},"google/gemini-3.5-flash-lite":{"draws":54,"losses":51,"wins":31},"google/gemini-3.6-flash":{"draws":43,"losses":55,"wins":18},"google/gemini-3.8-flash":{"draws":18,"losses":41,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":9},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":14,"wins":9},"gpt-5.4":{"draws":30,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":13},"gpt-5.5":{"draws":16,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":42,"losses":14,"wins":24},"gpt-5.6-sol":{"draws":12,"losses":43,"wins":11},"gpt-5.6-terra":{"draws":29,"losses":23,"wins":20},"gpt-6-astra":{"draws":4,"losses":58,"wins":2},"gpt-6-luna":{"draws":19,"losses":13,"wins":8},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":4,"wins":18},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":46,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":20,"losses":24,"wins":10},"meta/muse-spark-1.3":{"draws":18,"losses":32,"wins":8},"meta/muse-wonder":{"draws":8,"losses":23,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":29,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":21,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":12},"o3":{"draws":19,"losses":29,"wins":24},"openai/gpt-oss-120b":{"draws":36,"losses":24,"wins":8},"poolside/laguna-s-2.1":{"draws":30,"losses":14,"wins":12},"qwen/qwen3.7-max":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":26,"wins":21},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":19,"losses":20,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":33,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":15,"wins":8},"stealth/ox-alpha":{"draws":75,"losses":106,"wins":53},"stealth/space-bunny-alpha":{"draws":17,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":35,"losses":6,"wins":17},"thinkingmachines/inkling-small":{"draws":43,"losses":14,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":17,"losses":30,"wins":15},"x-ai/grok-4.6":{"draws":24,"losses":39,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":10,"wins":8},"z-ai/glm-5.2":{"draws":53,"losses":36,"wins":29},"z-ai/glm-5.3":{"draws":15,"losses":41,"wins":4},"z-ai/glm-5.3-flash":{"draws":27,"losses":31,"wins":12},"z-ai/glm-5.3-flashx":{"draws":16,"losses":19,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":38},"claude-fable-5":{"draws":21,"losses":47,"wins":18},"claude-fable-5-1":{"draws":7,"losses":91,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":16},"claude-opus-4-5":{"draws":33,"losses":33,"wins":42},"claude-opus-4-8":{"draws":11,"losses":22,"wins":17},"claude-opus-5":{"draws":13,"losses":70,"wins":9},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":28,"losses":35,"wins":21},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":38,"losses":20,"wins":48},"deepseek/deepseek-v4-pro":{"draws":20,"losses":14,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":26,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":14,"wins":18},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":12,"wins":21},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":31,"losses":33,"wins":36},"google/gemini-3.5-flash-lite":{"draws":53,"losses":34,"wins":65},"google/gemini-3.6-flash":{"draws":34,"losses":60,"wins":48},"google/gemini-3.8-flash":{"draws":32,"losses":42,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":8,"wins":20},"gpt-5.4":{"draws":37,"losses":30,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":27},"gpt-5.5":{"draws":21,"losses":22,"wins":7},"gpt-5.6-luna":{"draws":34,"losses":16,"wins":32},"gpt-5.6-sol":{"draws":13,"losses":48,"wins":23},"gpt-5.6-terra":{"draws":32,"losses":29,"wins":21},"gpt-6-astra":{"draws":8,"losses":76,"wins":4},"gpt-6-luna":{"draws":13,"losses":18,"wins":15},"gpt-6-sol":{"draws":8,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":41,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":11,"wins":33},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":32},"meta/muse-spark-1.2":{"draws":16,"losses":28,"wins":20},"meta/muse-spark-1.3":{"draws":17,"losses":39,"wins":18},"meta/muse-wonder":{"draws":13,"losses":20,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"mistralai/mistral-large-4-0":{"draws":7,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":17,"losses":0,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":29,"wins":23},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":19},"o3":{"draws":21,"losses":27,"wins":54},"openai/gpt-oss-120b":{"draws":30,"losses":15,"wins":27},"poolside/laguna-s-2.1":{"draws":25,"losses":17,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":35,"wins":25},"qwen/qwen3.8-27b":{"draws":10,"losses":22,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":19},"qwen/qwen3.8-max":{"draws":25,"losses":34,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":13},"stealth/ox-alpha":{"draws":80,"losses":125,"wins":77},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":12,"losses":5,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":24,"losses":37,"wins":23},"thinkingmachines/inkling":{"draws":24,"losses":7,"wins":41},"thinkingmachines/inkling-small":{"draws":38,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":17,"losses":28,"wins":33},"x-ai/grok-4.6":{"draws":26,"losses":42,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":36,"losses":10,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":53,"losses":45,"wins":42},"z-ai/glm-5.3":{"draws":19,"losses":35,"wins":14},"z-ai/glm-5.3-flash":{"draws":31,"losses":34,"wins":27},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"wins":19}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":11,"wins":46},"claude-fable-5":{"draws":18,"losses":45,"wins":21},"claude-fable-5-1":{"draws":4,"losses":92,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":20,"wins":14},"claude-opus-4-5":{"draws":21,"losses":27,"wins":60},"claude-opus-4-8":{"draws":14,"losses":13,"wins":19},"claude-opus-5":{"draws":7,"losses":75,"wins":10},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":27,"losses":20,"wins":43},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":36,"losses":12,"wins":56},"deepseek/deepseek-v4-pro":{"draws":20,"losses":24,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":20,"wins":13},"fireworks/ember-1":{"draws":12,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":20},"google/gemini-3.5-flash":{"draws":32,"losses":27,"wins":41},"google/gemini-3.5-flash-lite":{"draws":51,"losses":13,"wins":78},"google/gemini-3.6-flash":{"draws":33,"losses":58,"wins":63},"google/gemini-3.8-flash":{"draws":18,"losses":32,"wins":38},"google/gemma-4-31b-it":{"draws":10,"losses":0,"wins":16},"gpt-4.1":{"draws":7,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":12,"wins":24},"gpt-5.4":{"draws":24,"losses":25,"wins":27},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":27},"gpt-5.5":{"draws":9,"losses":22,"wins":13},"gpt-5.6-luna":{"draws":31,"losses":13,"wins":40},"gpt-5.6-sol":{"draws":12,"losses":49,"wins":25},"gpt-5.6-terra":{"draws":27,"losses":18,"wins":37},"gpt-6-astra":{"draws":10,"losses":74,"wins":0},"gpt-6-luna":{"draws":13,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":23,"losses":4,"wins":33},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":9,"wins":43},"meta/muse-glimmer-30b":{"draws":26,"losses":9,"wins":35},"meta/muse-spark-1.2":{"draws":17,"losses":17,"wins":34},"meta/muse-spark-1.3":{"draws":22,"losses":23,"wins":29},"meta/muse-wonder":{"draws":7,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":19,"losses":3,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":8},"moonshotai/kimi-k3":{"draws":20,"losses":10,"wins":32},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":5,"wins":22},"o3":{"draws":14,"losses":15,"wins":59},"openai/gpt-oss-120b":{"draws":29,"losses":9,"wins":30},"poolside/laguna-s-2.1":{"draws":23,"losses":8,"wins":33},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":28,"wins":36},"qwen/qwen3.8-27b":{"draws":8,"losses":16,"wins":20},"qwen/qwen3.8-flash":{"draws":18,"losses":20,"wins":22},"qwen/qwen3.8-max":{"draws":22,"losses":26,"wins":40},"qwen/qwen3.8-max-0902":{"draws":10,"losses":16,"wins":20},"stealth/ox-alpha":{"draws":60,"losses":83,"wins":131},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":35,"wins":39},"thinkingmachines/inkling":{"draws":16,"losses":13,"wins":43},"thinkingmachines/inkling-small":{"draws":25,"losses":13,"wins":40},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":23,"wins":28},"x-ai/grok-4.6":{"draws":25,"losses":39,"wins":24},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":7,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":17,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":42,"wins":57},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":25},"z-ai/glm-5.3-flash":{"draws":19,"losses":45,"wins":22},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":11,"losses":17,"wins":20},"claude-fable-5-1":{"draws":6,"losses":42,"wins":6},"claude-haiku-5-5":{"draws":12,"losses":11,"wins":21},"claude-opus-4-5":{"draws":15,"losses":12,"wins":51},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":9,"losses":55,"wins":18},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":13,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":56},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":17},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":27},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":7,"wins":38},"google/gemini-3.5-flash-lite":{"draws":16,"losses":6,"wins":62},"google/gemini-3.6-flash":{"draws":17,"losses":20,"wins":47},"google/gemini-3.8-flash":{"draws":9,"losses":10,"wins":29},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":20},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":38},"gpt-5.5":{"draws":11,"losses":8,"wins":25},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":33},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":23},"gpt-5.6-terra":{"draws":15,"losses":4,"wins":27},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":11,"losses":7,"wins":28},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":26},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":8,"losses":10,"wins":26},"meta/muse-spark-1.3":{"draws":7,"losses":12,"wins":27},"meta/muse-wonder":{"draws":11,"losses":14,"wins":19},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":27},"o3":{"draws":8,"losses":13,"wins":43},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":33},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":9,"wins":28},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":26},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":25},"stealth/ox-alpha":{"draws":31,"losses":40,"wins":85},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":24},"thinkingmachines/inkling":{"draws":15,"losses":1,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":1,"losses":23,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":23,"losses":9,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":12},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":24},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":23}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":4,"wins":31},"claude-fable-5":{"draws":5,"losses":27,"wins":16},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":22},"claude-opus-4-5":{"draws":18,"losses":13,"wins":47},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":8,"losses":50,"wins":24},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":6,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":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":26},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":52},"google/gemini-3.6-flash":{"draws":13,"losses":26,"wins":45},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":30},"gpt-5.4":{"draws":8,"losses":14,"wins":24},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":34},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":29},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":18},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":9,"losses":9,"wins":28},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":24},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":17,"wins":21},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":29},"o3":{"draws":7,"losses":6,"wins":51},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":10,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":17},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"stealth/ox-alpha":{"draws":23,"losses":43,"wins":90},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":42},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":23},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":14},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":3,"losses":26,"wins":19},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":14,"wins":23},"claude-opus-4-5":{"draws":10,"losses":19,"wins":49},"claude-opus-4-8":{"draws":8,"losses":10,"wins":26},"claude-opus-5":{"draws":5,"losses":52,"wins":25},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":7,"losses":12,"wins":29},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":14,"wins":27},"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":4,"losses":5,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":13,"losses":11,"wins":60},"google/gemini-3.6-flash":{"draws":7,"losses":22,"wins":55},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":17},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":4,"losses":5,"wins":33},"gpt-5.4":{"draws":3,"losses":16,"wins":27},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":31},"gpt-5.6-sol":{"draws":4,"losses":20,"wins":24},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":28},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":5,"losses":7,"wins":34},"gpt-6-sol":{"draws":6,"losses":25,"wins":17},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":23},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":39},"meta/muse-glimmer-30b":{"draws":7,"losses":2,"wins":33},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":4,"losses":21,"wins":21},"meta/muse-wonder":{"draws":9,"losses":20,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":17},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":25},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":30},"o3":{"draws":2,"losses":16,"wins":46},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":31},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":37},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":14,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":8,"losses":16,"wins":22},"stealth/ox-alpha":{"draws":23,"losses":43,"wins":90},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":2,"losses":15,"wins":29},"thinkingmachines/inkling":{"draws":9,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":15,"wins":23},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":23}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":14,"wins":7},"claude-fable-5":{"draws":5,"losses":26,"wins":1},"claude-fable-5-1":{"draws":2,"losses":34,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":17,"wins":4},"claude-opus-4-5":{"draws":21,"losses":61,"wins":6},"claude-opus-4-8":{"draws":13,"losses":43,"wins":4},"claude-opus-5":{"draws":10,"losses":68,"wins":2},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":16},"deepseek/deepseek-v4-flash":{"draws":19,"losses":25,"wins":22},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"fireworks/ember-1":{"draws":8,"losses":21,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":13,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":4},"google/gemini-3.5-flash-lite":{"draws":27,"losses":32,"wins":13},"google/gemini-3.6-flash":{"draws":19,"losses":51,"wins":4},"google/gemini-3.8-flash":{"draws":8,"losses":22,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":8,"wins":4},"gpt-4.1":{"draws":8,"losses":8,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":25,"wins":1},"gpt-5.4":{"draws":11,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":17,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":40,"wins":12},"gpt-5.5":{"draws":14,"losses":34,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":19,"wins":4},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":6,"losses":18,"wins":4},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":6,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":23,"wins":16},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":8,"losses":22,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":21,"wins":4},"meta/muse-wonder":{"draws":1,"losses":24,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":18,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":17,"wins":10},"o3":{"draws":12,"losses":54,"wins":8},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":10},"qwen/qwen3.7-max":{"draws":5,"losses":15,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":1},"qwen/qwen3.8-max-0902":{"draws":8,"losses":18,"wins":2},"stealth/ox-alpha":{"draws":23,"losses":59,"wins":8},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":9,"losses":22,"wins":1},"thinkingmachines/inkling":{"draws":16,"losses":26,"wins":16},"thinkingmachines/inkling-small":{"draws":11,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":7,"losses":29,"wins":2},"x-ai/grok-4.6":{"draws":5,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":41,"losses":30,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":23,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":23,"losses":45,"wins":12},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":8,"wins":43},"claude-fable-5":{"draws":14,"losses":49,"wins":25},"claude-fable-5-1":{"draws":8,"losses":88,"wins":12},"claude-haiku-5-5":{"draws":12,"losses":12,"wins":20},"claude-opus-4-5":{"draws":29,"losses":16,"wins":67},"claude-opus-4-8":{"draws":15,"losses":19,"wins":18},"claude-opus-5":{"draws":17,"losses":66,"wins":14},"claude-opus-5-5":{"draws":5,"losses":40,"wins":7},"claude-sonnet-5":{"draws":25,"losses":20,"wins":39},"claude-sonnet-5-5":{"draws":5,"losses":24,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":14,"wins":68},"deepseek/deepseek-v4-pro":{"draws":13,"losses":28,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":14,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":12,"wins":25},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":16,"losses":7,"wins":45},"google/gemini-3.5-flash-lite":{"draws":34,"losses":16,"wins":88},"google/gemini-3.6-flash":{"draws":26,"losses":34,"wins":80},"google/gemini-3.8-flash":{"draws":12,"losses":36,"wins":42},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":15},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":9,"wins":22},"gpt-5.4":{"draws":16,"losses":34,"wins":36},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":37},"gpt-5.5":{"draws":16,"losses":13,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":16,"wins":47},"gpt-5.6-sol":{"draws":11,"losses":41,"wins":40},"gpt-5.6-terra":{"draws":31,"losses":22,"wins":33},"gpt-6-astra":{"draws":14,"losses":78,"wins":4},"gpt-6-luna":{"draws":9,"losses":13,"wins":26},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":36},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":31},"meituan/longcat-2.0":{"draws":16,"losses":4,"wins":52},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":45},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":37},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":34},"meta/muse-wonder":{"draws":6,"losses":25,"wins":13},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":16,"losses":24,"wins":34},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"o3":{"draws":11,"losses":20,"wins":65},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":45},"poolside/laguna-s-2.1":{"draws":11,"losses":5,"wins":50},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":27,"wins":45},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":21},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":36},"qwen/qwen3.8-max":{"draws":29,"losses":19,"wins":36},"qwen/qwen3.8-max-0902":{"draws":12,"losses":19,"wins":17},"stealth/ox-alpha":{"draws":63,"losses":92,"wins":135},"stealth/space-bunny-alpha":{"draws":8,"losses":3,"wins":27},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":14,"losses":41,"wins":27},"thinkingmachines/inkling":{"draws":13,"losses":3,"wins":54},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":50},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":36},"x-ai/grok-4.6":{"draws":23,"losses":38,"wins":29},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":21,"losses":32,"wins":77},"z-ai/glm-5.3":{"draws":16,"losses":38,"wins":22},"z-ai/glm-5.3-flash":{"draws":12,"losses":35,"wins":45},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":18}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":44,"losses":45,"wins":47},"claude-fable-5":{"draws":22,"losses":76,"wins":20},"claude-fable-5-1":{"draws":9,"losses":125,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":46,"wins":11},"claude-opus-4-5":{"draws":67,"losses":111,"wins":72},"claude-opus-4-8":{"draws":16,"losses":58,"wins":14},"claude-opus-5":{"draws":16,"losses":137,"wins":13},"claude-opus-5-5":{"draws":8,"losses":74,"wins":0},"claude-sonnet-5":{"draws":56,"losses":97,"wins":61},"claude-sonnet-5-5":{"draws":16,"losses":48,"wins":14},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":52,"losses":55,"wins":71},"deepseek/deepseek-v4-pro":{"draws":33,"losses":67,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":58,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":34,"wins":21},"fireworks/ember-1":{"draws":29,"losses":35,"wins":14},"gemini-3.1-pro-preview":{"draws":17,"losses":37,"wins":24},"google/gemini-3.1-flash-lite":{"draws":16,"losses":16,"wins":36},"google/gemini-3.5-flash":{"draws":40,"losses":72,"wins":42},"google/gemini-3.5-flash-lite":{"draws":113,"losses":143,"wins":152},"google/gemini-3.6-flash":{"draws":105,"losses":220,"wins":97},"google/gemini-3.8-flash":{"draws":18,"losses":85,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":29,"losses":38,"wins":21},"gpt-5.4":{"draws":41,"losses":116,"wins":47},"gpt-5.4-mini":{"draws":18,"losses":20,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":27,"wins":39},"gpt-5.5":{"draws":31,"losses":45,"wins":18},"gpt-5.6-luna":{"draws":68,"losses":75,"wins":79},"gpt-5.6-sol":{"draws":35,"losses":150,"wins":15},"gpt-5.6-terra":{"draws":37,"losses":62,"wins":33},"gpt-6-astra":{"draws":9,"losses":101,"wins":2},"gpt-6-luna":{"draws":22,"losses":40,"wins":16},"gpt-6-sol":{"draws":11,"losses":63,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":74,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":17,"wins":53},"inclusionai/ling-3.0-flash":{"draws":31,"losses":24,"wins":51},"meituan/longcat-2.0":{"draws":43,"losses":58,"wins":85},"meta/muse-glimmer-30b":{"draws":42,"losses":37,"wins":55},"meta/muse-spark-1.2":{"draws":36,"losses":83,"wins":41},"meta/muse-spark-1.3":{"draws":21,"losses":69,"wins":22},"meta/muse-wonder":{"draws":10,"losses":55,"wins":9},"minimax/minimax-m3":{"draws":12,"losses":17,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":20,"wins":13},"mistralai/mistral-medium-3-5":{"draws":25,"losses":19,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":51,"losses":92,"wins":57},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":32,"wins":27},"o3":{"draws":28,"losses":166,"wins":92},"openai/gpt-oss-120b":{"draws":42,"losses":34,"wins":56},"poolside/laguna-s-2.1":{"draws":68,"losses":53,"wins":57},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":18},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":66,"wins":35},"qwen/qwen3.8-27b":{"draws":10,"losses":42,"wins":14},"qwen/qwen3.8-flash":{"draws":32,"losses":42,"wins":16},"qwen/qwen3.8-max":{"draws":48,"losses":62,"wins":26},"qwen/qwen3.8-max-0902":{"draws":19,"losses":42,"wins":15},"stealth/ox-alpha":{"draws":83,"losses":246,"wins":113},"stealth/space-bunny-alpha":{"draws":13,"losses":30,"wins":21},"stepfun/step-3.7-flash":{"draws":15,"losses":22,"wins":33},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":21,"wins":15},"tencent/hy4-preview":{"draws":29,"losses":76,"wins":33},"thinkingmachines/inkling":{"draws":50,"losses":51,"wins":83},"thinkingmachines/inkling-small":{"draws":49,"losses":59,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":48,"losses":98,"wins":50},"x-ai/grok-4.6":{"draws":30,"losses":68,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":40,"losses":38,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":20,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":33,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":9},"z-ai/glm-5.2":{"draws":60,"losses":87,"wins":83},"z-ai/glm-5.3":{"draws":19,"losses":80,"wins":11},"z-ai/glm-5.3-flash":{"draws":32,"losses":79,"wins":19},"z-ai/glm-5.3-flashx":{"draws":16,"losses":45,"wins":17}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":17,"wins":63},"claude-fable-5":{"draws":12,"losses":57,"wins":59},"claude-fable-5-1":{"draws":11,"losses":112,"wins":17},"claude-haiku-5-5":{"draws":11,"losses":16,"wins":39},"claude-opus-4-5":{"draws":49,"losses":57,"wins":134},"claude-opus-4-8":{"draws":13,"losses":36,"wins":45},"claude-opus-5":{"draws":33,"losses":123,"wins":42},"claude-opus-5-5":{"draws":10,"losses":63,"wins":7},"claude-sonnet-5":{"draws":21,"losses":43,"wins":128},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":35},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":21},"deepseek/deepseek-v4-flash":{"draws":23,"losses":6,"wins":121},"deepseek/deepseek-v4-pro":{"draws":24,"losses":29,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":18,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":37},"fireworks/ember-1":{"draws":14,"losses":18,"wins":40},"gemini-3.1-pro-preview":{"draws":8,"losses":18,"wins":46},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":53},"google/gemini-3.5-flash":{"draws":31,"losses":45,"wins":74},"google/gemini-3.5-flash-lite":{"draws":97,"losses":39,"wins":250},"google/gemini-3.6-flash":{"draws":54,"losses":103,"wins":191},"google/gemini-3.8-flash":{"draws":22,"losses":48,"wins":64},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":29},"gpt-4.1":{"draws":3,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":12,"losses":29,"wins":51},"gpt-5.4":{"draws":33,"losses":87,"wins":78},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":35},"gpt-5.4-nano":{"draws":8,"losses":11,"wins":57},"gpt-5.5":{"draws":22,"losses":31,"wins":39},"gpt-5.6-luna":{"draws":37,"losses":48,"wins":105},"gpt-5.6-sol":{"draws":19,"losses":84,"wins":95},"gpt-5.6-terra":{"draws":25,"losses":22,"wins":69},"gpt-6-astra":{"draws":8,"losses":97,"wins":21},"gpt-6-luna":{"draws":18,"losses":9,"wins":43},"gpt-6-sol":{"draws":8,"losses":38,"wins":26},"gpt-6.1-sol":{"draws":4,"losses":56,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":7,"wins":46},"inclusionai/ling-3.0-flash":{"draws":33,"losses":6,"wins":49},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":34,"losses":16,"wins":116},"meta/muse-glimmer-30b":{"draws":29,"losses":4,"wins":69},"meta/muse-spark-1.2":{"draws":17,"losses":43,"wins":80},"meta/muse-spark-1.3":{"draws":10,"losses":44,"wins":54},"meta/muse-wonder":{"draws":12,"losses":29,"wins":25},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":27},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":22},"mistralai/mistral-medium-3-5":{"draws":13,"losses":4,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":14},"moonshotai/kimi-k3":{"draws":35,"losses":34,"wins":113},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":58},"o3":{"draws":35,"losses":53,"wins":178},"openai/gpt-oss-120b":{"draws":23,"losses":5,"wins":66},"poolside/laguna-s-2.1":{"draws":39,"losses":8,"wins":91},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":26},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":33,"wins":69},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":37},"qwen/qwen3.8-flash":{"draws":29,"losses":13,"wins":42},"qwen/qwen3.8-max":{"draws":31,"losses":33,"wins":67},"qwen/qwen3.8-max-0902":{"draws":13,"losses":25,"wins":30},"stealth/ox-alpha":{"draws":63,"losses":115,"wins":214},"stealth/space-bunny-alpha":{"draws":11,"losses":5,"wins":42},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":55},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":17,"wins":35},"tencent/hy4-preview":{"draws":24,"losses":34,"wins":70},"thinkingmachines/inkling":{"draws":36,"losses":19,"wins":109},"thinkingmachines/inkling-small":{"draws":24,"losses":9,"wins":75},"unbiased/pareto-26.10-preview":{"draws":2,"losses":17,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":17},"x-ai/grok-4.5":{"draws":22,"losses":62,"wins":110},"x-ai/grok-4.6":{"draws":19,"losses":43,"wins":70},"x-ai/grok-4.7":{"draws":2,"losses":40,"wins":20},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":18},"xiaomi/mimo-v2.5":{"draws":31,"losses":6,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":19},"z-ai/glm-5.2":{"draws":40,"losses":27,"wins":121},"z-ai/glm-5.3":{"draws":14,"losses":41,"wins":47},"z-ai/glm-5.3-flash":{"draws":28,"losses":41,"wins":55},"z-ai/glm-5.3-flashx":{"draws":20,"losses":21,"wins":31}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":48},"claude-fable-5":{"draws":11,"losses":43,"wins":36},"claude-fable-5-1":{"draws":11,"losses":84,"wins":13},"claude-haiku-5-5":{"draws":9,"losses":12,"wins":21},"claude-opus-4-5":{"draws":16,"losses":25,"wins":67},"claude-opus-4-8":{"draws":6,"losses":14,"wins":26},"claude-opus-5":{"draws":4,"losses":82,"wins":24},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":11,"losses":22,"wins":51},"claude-sonnet-5-5":{"draws":4,"losses":22,"wins":22},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":81},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":52},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":24,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":17,"wins":23},"fireworks/ember-1":{"draws":5,"losses":17,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":34},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":18,"losses":13,"wins":67},"google/gemini-3.5-flash-lite":{"draws":14,"losses":9,"wins":103},"google/gemini-3.6-flash":{"draws":15,"losses":39,"wins":84},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":25},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":20},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":8,"losses":9,"wins":27},"gpt-5.4":{"draws":13,"losses":38,"wins":33},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":32},"gpt-5.5":{"draws":9,"losses":21,"wins":18},"gpt-5.6-luna":{"draws":12,"losses":16,"wins":46},"gpt-5.6-sol":{"draws":8,"losses":40,"wins":48},"gpt-5.6-terra":{"draws":20,"losses":24,"wins":36},"gpt-6-astra":{"draws":12,"losses":75,"wins":9},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":33},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":5,"wins":47},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":44},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":42},"meta/muse-spark-1.3":{"draws":13,"losses":27,"wins":28},"meta/muse-wonder":{"draws":10,"losses":21,"wins":13},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":22},"mistralai/mistral-large-4-0":{"draws":4,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":43},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":28},"o3":{"draws":8,"losses":16,"wins":68},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":50},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":47},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":28,"wins":48},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":27},"qwen/qwen3.8-flash":{"draws":7,"losses":17,"wins":30},"qwen/qwen3.8-max":{"draws":18,"losses":31,"wins":33},"qwen/qwen3.8-max-0902":{"draws":10,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":42,"losses":81,"wins":162},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":24},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":9,"losses":32,"wins":35},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":19,"losses":15,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":34,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":34,"wins":43},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":13,"losses":14,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":29,"wins":83},"z-ai/glm-5.3":{"draws":15,"losses":37,"wins":26},"z-ai/glm-5.3-flash":{"draws":18,"losses":27,"wins":43},"z-ai/glm-5.3-flashx":{"draws":9,"losses":15,"wins":24}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":9,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":14},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":20,"wins":11},"claude-opus-4-5":{"draws":58,"losses":29,"wins":39},"claude-opus-4-8":{"draws":24,"losses":42,"wins":20},"claude-opus-5":{"draws":14,"losses":130,"wins":14},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":17,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":36,"losses":5,"wins":51},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":11,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":16,"wins":10},"fireworks/ember-1":{"draws":15,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":19,"wins":13},"google/gemini-3.1-flash-lite":{"draws":20,"losses":4,"wins":36},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":27},"google/gemini-3.5-flash-lite":{"draws":47,"losses":20,"wins":43},"google/gemini-3.6-flash":{"draws":35,"losses":52,"wins":37},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":17},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":10,"losses":11,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":5,"wins":25},"gpt-5.4":{"draws":12,"losses":22,"wins":14},"gpt-5.4-mini":{"draws":15,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":50},"gpt-5.5":{"draws":34,"losses":32,"wins":18},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":15,"wins":18},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":19,"losses":12,"wins":17},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":17,"losses":10,"wins":23},"meituan/longcat-2.0":{"draws":20,"losses":19,"wins":31},"meta/muse-glimmer-30b":{"draws":21,"losses":4,"wins":21},"meta/muse-spark-1.2":{"draws":17,"losses":16,"wins":17},"meta/muse-spark-1.3":{"draws":17,"losses":20,"wins":15},"meta/muse-wonder":{"draws":9,"losses":26,"wins":7},"minimax/minimax-m3":{"draws":14,"losses":6,"wins":24},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":9},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":18},"nex-agi/nex-n2-pro":{"draws":17,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":4,"wins":39},"o3":{"draws":16,"losses":34,"wins":48},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":28,"losses":26,"wins":18},"qwen/qwen3.7-max":{"draws":21,"losses":6,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":16},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":24,"losses":11,"wins":13},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":43,"losses":72,"wins":49},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":14,"losses":6,"wins":30},"tencent/hy3-preview":{"draws":19,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":19,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":29,"losses":14,"wins":43},"thinkingmachines/inkling-small":{"draws":20,"losses":5,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":19},"x-ai/grok-4.6":{"draws":17,"losses":26,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":59,"losses":17,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":12,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":55,"losses":35,"wins":54},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":9},"z-ai/glm-5.3-flash":{"draws":18,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":19,"losses":13,"wins":16}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":37},"claude-fable-5":{"draws":21,"losses":26,"wins":37},"claude-fable-5-1":{"draws":11,"losses":68,"wins":17},"claude-haiku-5-5":{"draws":5,"losses":12,"wins":21},"claude-opus-4-5":{"draws":19,"losses":17,"wins":84},"claude-opus-4-8":{"draws":5,"losses":14,"wins":25},"claude-opus-5":{"draws":8,"losses":51,"wins":17},"claude-opus-5-5":{"draws":4,"losses":36,"wins":6},"claude-sonnet-5":{"draws":17,"losses":21,"wins":78},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":7,"wins":63},"deepseek/deepseek-v4-pro":{"draws":17,"losses":12,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":12,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":27},"fireworks/ember-1":{"draws":5,"losses":9,"wins":28},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":28},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":65},"google/gemini-3.5-flash-lite":{"draws":22,"losses":17,"wins":151},"google/gemini-3.6-flash":{"draws":34,"losses":35,"wins":133},"google/gemini-3.8-flash":{"draws":5,"losses":24,"wins":53},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":16},"gpt-4.1":{"draws":4,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":33},"gpt-5.4":{"draws":17,"losses":6,"wins":68},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":36},"gpt-5.5":{"draws":9,"losses":9,"wins":22},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":87},"gpt-5.6-sol":{"draws":27,"losses":45,"wins":62},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":58},"gpt-6-astra":{"draws":8,"losses":65,"wins":11},"gpt-6-luna":{"draws":8,"losses":7,"wins":25},"gpt-6-sol":{"draws":2,"losses":27,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":20},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":2,"wins":64},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":53},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":42},"meta/muse-wonder":{"draws":5,"losses":16,"wins":19},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":65},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":26},"o3":{"draws":2,"losses":12,"wins":112},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":36},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":55},"qwen/qwen3.7-max":{"draws":0,"losses":5,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":41},"qwen/qwen3.8-27b":{"draws":7,"losses":2,"wins":31},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":32},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":42},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":25},"stealth/ox-alpha":{"draws":75,"losses":49,"wins":137},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":52},"thinkingmachines/inkling":{"draws":18,"losses":12,"wins":50},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":37},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":16,"losses":17,"wins":62},"x-ai/grok-4.6":{"draws":17,"losses":18,"wins":47},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":25,"losses":19,"wins":70},"z-ai/glm-5.3":{"draws":4,"losses":26,"wins":34},"z-ai/glm-5.3-flash":{"draws":11,"losses":18,"wins":47},"z-ai/glm-5.3-flashx":{"draws":6,"losses":13,"wins":23}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":27},"claude-fable-5":{"draws":7,"losses":19,"wins":18},"claude-fable-5-1":{"draws":0,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":22},"claude-opus-4-5":{"draws":27,"losses":14,"wins":71},"claude-opus-4-8":{"draws":11,"losses":14,"wins":55},"claude-opus-5":{"draws":8,"losses":88,"wins":80},"claude-opus-5-5":{"draws":2,"losses":35,"wins":9},"claude-sonnet-5":{"draws":7,"losses":8,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":20,"losses":2,"wins":54},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":8,"wins":22},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":29},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":38},"google/gemini-3.5-flash":{"draws":14,"losses":9,"wins":35},"google/gemini-3.5-flash-lite":{"draws":26,"losses":10,"wins":62},"google/gemini-3.6-flash":{"draws":29,"losses":23,"wins":56},"google/gemini-3.8-flash":{"draws":12,"losses":7,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":15},"gpt-4.1":{"draws":2,"losses":2,"wins":18},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":17,"losses":9,"wins":50},"gpt-5.4":{"draws":15,"losses":12,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":55},"gpt-5.5":{"draws":24,"losses":10,"wins":24},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":25},"gpt-6-astra":{"draws":1,"losses":38,"wins":5},"gpt-6-luna":{"draws":15,"losses":3,"wins":22},"gpt-6-sol":{"draws":4,"losses":23,"wins":15},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":15,"losses":7,"wins":38},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":31},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":23},"meta/muse-wonder":{"draws":8,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":9,"losses":3,"wins":22},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":2,"wins":39},"o3":{"draws":7,"losses":9,"wins":76},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":11,"losses":5,"wins":40},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":29},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":8,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":23},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":21},"stealth/ox-alpha":{"draws":31,"losses":30,"wins":85},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":37},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":20,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":11,"wins":22},"thinkingmachines/inkling":{"draws":13,"losses":10,"wins":51},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":20,"losses":15,"wins":37},"x-ai/grok-4.6":{"draws":13,"losses":11,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":17,"wins":15},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":12},"z-ai/glm-5.2":{"draws":32,"losses":8,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":11},"z-ai/glm-5.3-flash":{"draws":5,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":10,"losses":9,"wins":23}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":15,"wins":25},"claude-fable-5":{"draws":23,"losses":36,"wins":25},"claude-fable-5-1":{"draws":5,"losses":74,"wins":9},"claude-haiku-5-5":{"draws":14,"losses":15,"wins":15},"claude-opus-4-5":{"draws":50,"losses":29,"wins":55},"claude-opus-4-8":{"draws":15,"losses":10,"wins":21},"claude-opus-5":{"draws":8,"losses":66,"wins":10},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":40,"losses":32,"wins":60},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":46,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":25,"losses":18,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":14,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":14,"wins":13},"fireworks/ember-1":{"draws":18,"losses":8,"wins":22},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":21},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":35,"losses":20,"wins":43},"google/gemini-3.5-flash-lite":{"draws":89,"losses":34,"wins":113},"google/gemini-3.6-flash":{"draws":61,"losses":67,"wins":88},"google/gemini-3.8-flash":{"draws":23,"losses":27,"wins":36},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":8,"wins":22},"gpt-5.4":{"draws":54,"losses":58,"wins":27},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":18,"losses":13,"wins":13},"gpt-5.6-luna":{"draws":41,"losses":13,"wins":35},"gpt-5.6-sol":{"draws":24,"losses":64,"wins":40},"gpt-5.6-terra":{"draws":32,"losses":13,"wins":41},"gpt-6-astra":{"draws":10,"losses":67,"wins":1},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":3,"wins":22},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":27},"meituan/longcat-2.0":{"draws":26,"losses":13,"wins":53},"meta/muse-glimmer-30b":{"draws":33,"losses":5,"wins":34},"meta/muse-spark-1.2":{"draws":19,"losses":40,"wins":35},"meta/muse-spark-1.3":{"draws":19,"losses":25,"wins":24},"meta/muse-wonder":{"draws":10,"losses":19,"wins":17},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":26,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":27,"wins":38},"nex-agi/nex-n2-pro":{"draws":10,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":22},"o3":{"draws":25,"losses":29,"wins":76},"openai/gpt-oss-120b":{"draws":38,"losses":8,"wins":28},"poolside/laguna-s-2.1":{"draws":43,"losses":11,"wins":40},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":14,"wins":35},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":15},"qwen/qwen3.8-flash":{"draws":21,"losses":22,"wins":17},"qwen/qwen3.8-max":{"draws":33,"losses":27,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":9,"wins":21},"stealth/ox-alpha":{"draws":76,"losses":92,"wins":101},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":19},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":34,"losses":18,"wins":28},"thinkingmachines/inkling":{"draws":30,"losses":4,"wins":50},"thinkingmachines/inkling-small":{"draws":38,"losses":12,"wins":32},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":25,"wins":63},"x-ai/grok-4.6":{"draws":23,"losses":35,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":3,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":55,"losses":36,"wins":41},"z-ai/glm-5.3":{"draws":16,"losses":38,"wins":18},"z-ai/glm-5.3-flash":{"draws":24,"losses":33,"wins":27},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":52},"claude-fable-5":{"draws":6,"losses":29,"wins":55},"claude-fable-5-1":{"draws":10,"losses":67,"wins":31},"claude-haiku-5-5":{"draws":7,"losses":4,"wins":31},"claude-opus-4-5":{"draws":8,"losses":29,"wins":99},"claude-opus-4-8":{"draws":7,"losses":5,"wins":34},"claude-opus-5":{"draws":9,"losses":53,"wins":34},"claude-opus-5-5":{"draws":6,"losses":31,"wins":15},"claude-sonnet-5":{"draws":0,"losses":9,"wins":131},"claude-sonnet-5-5":{"draws":2,"losses":15,"wins":31},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":87},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":2,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":39},"fireworks/ember-1":{"draws":5,"losses":7,"wins":36},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":5,"losses":15,"wins":72},"google/gemini-3.5-flash-lite":{"draws":10,"losses":3,"wins":193},"google/gemini-3.6-flash":{"draws":15,"losses":40,"wins":153},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":62},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":0,"losses":3,"wins":39},"gpt-5.4":{"draws":9,"losses":32,"wins":91},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":29},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":5,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":6,"losses":16,"wins":100},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":85},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":66},"gpt-6-astra":{"draws":12,"losses":70,"wins":14},"gpt-6-luna":{"draws":9,"losses":2,"wins":35},"gpt-6-sol":{"draws":6,"losses":18,"wins":24},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":36},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":45},"meituan/longcat-2.0":{"draws":4,"losses":7,"wins":69},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":45},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":88},"meta/muse-spark-1.3":{"draws":9,"losses":10,"wins":49},"meta/muse-wonder":{"draws":2,"losses":14,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":1,"losses":9,"wins":92},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"o3":{"draws":1,"losses":21,"wins":102},"openai/gpt-oss-120b":{"draws":5,"losses":5,"wins":42},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":79},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":11,"wins":66},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":33},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":41},"qwen/qwen3.8-max":{"draws":5,"losses":6,"wins":69},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":37},"stealth/ox-alpha":{"draws":24,"losses":31,"wins":224},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":24},"tencent/hy4-preview":{"draws":6,"losses":26,"wins":48},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":69},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":67},"unbiased/pareto-26.10-preview":{"draws":2,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":10,"losses":9,"wins":85},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":55},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":19},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":3,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":21},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":104},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":47},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":59},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":9,"wins":39},"claude-fable-5":{"draws":26,"losses":41,"wins":21},"claude-fable-5-1":{"draws":6,"losses":84,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":32,"losses":35,"wins":37},"claude-opus-4-8":{"draws":6,"losses":21,"wins":21},"claude-opus-5":{"draws":11,"losses":67,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":29,"losses":21,"wins":34},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":30,"losses":17,"wins":63},"deepseek/deepseek-v4-pro":{"draws":18,"losses":25,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":21,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":20,"wins":9},"fireworks/ember-1":{"draws":15,"losses":14,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":27},"google/gemini-3.5-flash":{"draws":32,"losses":19,"wins":47},"google/gemini-3.5-flash-lite":{"draws":40,"losses":22,"wins":84},"google/gemini-3.6-flash":{"draws":45,"losses":52,"wins":43},"google/gemini-3.8-flash":{"draws":21,"losses":37,"wins":26},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":15},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":23,"losses":38,"wins":21},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":33},"gpt-5.5":{"draws":13,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":24,"losses":23,"wins":37},"gpt-5.6-sol":{"draws":15,"losses":52,"wins":21},"gpt-5.6-terra":{"draws":18,"losses":22,"wins":18},"gpt-6-astra":{"draws":5,"losses":76,"wins":3},"gpt-6-luna":{"draws":12,"losses":16,"wins":18},"gpt-6-sol":{"draws":11,"losses":29,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":6,"wins":27},"inclusionai/ling-3.0-flash":{"draws":11,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":15,"wins":40},"meta/muse-glimmer-30b":{"draws":28,"losses":13,"wins":33},"meta/muse-spark-1.2":{"draws":17,"losses":34,"wins":15},"meta/muse-spark-1.3":{"draws":17,"losses":29,"wins":22},"meta/muse-wonder":{"draws":7,"losses":23,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":17,"losses":6,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":25,"losses":15,"wins":32},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":26},"o3":{"draws":10,"losses":31,"wins":53},"openai/gpt-oss-120b":{"draws":17,"losses":11,"wins":46},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":39},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":21},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":40,"wins":23},"qwen/qwen3.8-27b":{"draws":13,"losses":11,"wins":18},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":28},"qwen/qwen3.8-max":{"draws":32,"losses":32,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":66,"losses":100,"wins":100},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":17,"losses":30,"wins":33},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":44},"thinkingmachines/inkling-small":{"draws":26,"losses":10,"wins":50},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":34,"wins":26},"x-ai/grok-4.6":{"draws":26,"losses":50,"wins":14},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":4,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":55,"losses":29,"wins":58},"z-ai/glm-5.3":{"draws":24,"losses":29,"wins":19},"z-ai/glm-5.3-flash":{"draws":17,"losses":34,"wins":33},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":4,"wins":54},"claude-fable-5":{"draws":3,"losses":16,"wins":75},"claude-fable-5-1":{"draws":7,"losses":25,"wins":76},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":40},"claude-opus-4-5":{"draws":2,"losses":7,"wins":97},"claude-opus-4-8":{"draws":1,"losses":2,"wins":43},"claude-opus-5":{"draws":4,"losses":10,"wins":70},"claude-opus-5-5":{"draws":6,"losses":14,"wins":32},"claude-sonnet-5":{"draws":0,"losses":4,"wins":84},"claude-sonnet-5-5":{"draws":2,"losses":6,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":93},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":46},"fireworks/ember-1":{"draws":0,"losses":1,"wins":47},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":92},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":118},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":125},"google/gemini-3.8-flash":{"draws":7,"losses":3,"wins":80},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":2,"losses":8,"wins":74},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":61},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":82},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":81},"gpt-6-astra":{"draws":1,"losses":14,"wins":49},"gpt-6-luna":{"draws":3,"losses":0,"wins":43},"gpt-6-sol":{"draws":6,"losses":4,"wins":38},"gpt-6.1-sol":{"draws":5,"losses":7,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":42},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":62},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":52},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":66},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":66},"meta/muse-wonder":{"draws":3,"losses":3,"wins":38},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":70},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":41},"o3":{"draws":1,"losses":2,"wins":85},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":52},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":56},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":83},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":49},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":78},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"stealth/ox-alpha":{"draws":10,"losses":8,"wins":262},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":0,"losses":6,"wins":76},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":58},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":64},"unbiased/pareto-26.10-preview":{"draws":3,"losses":5,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":68},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":88},"x-ai/grok-4.7":{"draws":3,"losses":3,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":28},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":117},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":64},"z-ai/glm-5.3-flash":{"draws":8,"losses":2,"wins":74},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":45}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":26,"wins":13},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":20,"wins":21},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":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},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"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},"fireworks/ember-1":{"draws":6,"losses":21,"wins":21},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":23},"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":4,"losses":5,"wins":17},"gpt-4.1":{"draws":2,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"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":5,"losses":13,"wins":12},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"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":11,"losses":17,"wins":16},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"mistralai/mistral-large-4-0":{"draws":5,"losses":9,"wins":14},"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":8,"losses":16,"wins":20},"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":2,"losses":20,"wins":42},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":14,"wins":28},"qwen/qwen3.7-max":{"draws":2,"losses":8,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":21},"stealth/ox-alpha":{"draws":31,"losses":57,"wins":68},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":37},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"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":3,"losses":29,"wins":10},"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":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":21,"losses":26,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":36},"claude-fable-5":{"draws":4,"losses":10,"wins":34},"claude-fable-5-1":{"draws":4,"losses":23,"wins":27},"claude-haiku-5-5":{"draws":5,"losses":8,"wins":31},"claude-opus-4-5":{"draws":3,"losses":12,"wins":63},"claude-opus-4-8":{"draws":3,"losses":9,"wins":32},"claude-opus-5":{"draws":12,"losses":24,"wins":46},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":61},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":6,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":35},"fireworks/ember-1":{"draws":3,"losses":5,"wins":40},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":35},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":48},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":5,"losses":16,"wins":63},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":22},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":6,"wins":36},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":3,"losses":7,"wins":34},"gpt-5.6-luna":{"draws":1,"losses":6,"wins":41},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":38},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":37},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":6,"losses":4,"wins":36},"gpt-6-sol":{"draws":3,"losses":8,"wins":21},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":26},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":38},"meta/muse-wonder":{"draws":2,"losses":8,"wins":36},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":21},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":20},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":5,"wins":39},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":36},"o3":{"draws":0,"losses":9,"wins":55},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":6,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":26},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":40},"qwen/qwen3.8-max-0902":{"draws":0,"losses":9,"wins":37},"stealth/ox-alpha":{"draws":14,"losses":20,"wins":122},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":34},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":7,"wins":35},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":47},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":45},"unbiased/pareto-26.10-preview":{"draws":2,"losses":8,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":38},"x-ai/grok-4.6":{"draws":2,"losses":5,"wins":41},"x-ai/grok-4.7":{"draws":5,"losses":15,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":13,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":10,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"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":44},"claude-fable-5":{"draws":3,"losses":5,"wins":40},"claude-fable-5-1":{"draws":6,"losses":16,"wins":32},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":38},"claude-opus-4-5":{"draws":0,"losses":2,"wins":76},"claude-opus-4-8":{"draws":1,"losses":1,"wins":42},"claude-opus-5":{"draws":5,"losses":14,"wins":63},"claude-opus-5-5":{"draws":5,"losses":22,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":39},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":71},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":42},"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":32},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":55},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":74},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":5,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":38},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":44},"gpt-6-astra":{"draws":8,"losses":16,"wins":24},"gpt-6-luna":{"draws":2,"losses":1,"wins":43},"gpt-6-sol":{"draws":5,"losses":4,"wins":39},"gpt-6.1-sol":{"draws":2,"losses":7,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":51},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":40},"meta/muse-spark-1.3":{"draws":2,"losses":0,"wins":44},"meta/muse-wonder":{"draws":4,"losses":4,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":40},"o3":{"draws":0,"losses":2,"wins":64},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":30},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"stealth/ox-alpha":{"draws":3,"losses":4,"wins":149},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":52},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":5,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":46},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":93},"z-ai/glm-5.3":{"draws":6,"losses":2,"wins":36},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":42}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":18,"wins":14},"claude-fable-5":{"draws":16,"losses":34,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":25,"wins":0},"claude-opus-4-5":{"draws":37,"losses":41,"wins":2},"claude-opus-4-8":{"draws":10,"losses":26,"wins":2},"claude-opus-5":{"draws":11,"losses":45,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":23,"losses":42,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":2},"deepseek/deepseek-v4-flash":{"draws":40,"losses":39,"wins":7},"deepseek/deepseek-v4-pro":{"draws":26,"losses":28,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":28,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":2},"fireworks/ember-1":{"draws":15,"losses":20,"wins":1},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":5},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":32,"losses":35,"wins":1},"google/gemini-3.5-flash-lite":{"draws":61,"losses":53,"wins":6},"google/gemini-3.6-flash":{"draws":47,"losses":51,"wins":6},"google/gemini-3.8-flash":{"draws":17,"losses":40,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":8},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":16,"wins":1},"gpt-5.4":{"draws":24,"losses":26,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":6},"gpt-5.5":{"draws":13,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":34,"losses":18,"wins":12},"gpt-5.6-sol":{"draws":11,"losses":43,"wins":0},"gpt-5.6-terra":{"draws":24,"losses":34,"wins":4},"gpt-6-astra":{"draws":5,"losses":41,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":2},"gpt-6-sol":{"draws":4,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":21,"losses":16,"wins":9},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":23,"wins":8},"meta/muse-glimmer-30b":{"draws":32,"losses":20,"wins":8},"meta/muse-spark-1.2":{"draws":20,"losses":32,"wins":2},"meta/muse-spark-1.3":{"draws":19,"losses":27,"wins":6},"meta/muse-wonder":{"draws":8,"losses":24,"wins":0},"minimax/minimax-m3":{"draws":12,"losses":9,"wins":1},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":20,"losses":12,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":10},"o3":{"draws":16,"losses":56,"wins":2},"openai/gpt-oss-120b":{"draws":28,"losses":18,"wins":14},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":5},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":22,"losses":20,"wins":4},"qwen/qwen3.8-max":{"draws":34,"losses":26,"wins":4},"qwen/qwen3.8-max-0902":{"draws":15,"losses":16,"wins":3},"stealth/ox-alpha":{"draws":57,"losses":85,"wins":16},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":3},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"tencent/hy4-preview":{"draws":25,"losses":28,"wins":3},"thinkingmachines/inkling":{"draws":23,"losses":18,"wins":7},"thinkingmachines/inkling-small":{"draws":35,"losses":27,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":19,"losses":33,"wins":0},"x-ai/grok-4.6":{"draws":19,"losses":26,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":27,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":10,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":47,"losses":48,"wins":9},"z-ai/glm-5.3":{"draws":18,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":34,"wins":3},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":2}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":14,"wins":29},"claude-fable-5":{"draws":16,"losses":44,"wins":4},"claude-fable-5-1":{"draws":4,"losses":58,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":8},"claude-opus-4-5":{"draws":38,"losses":37,"wins":15},"claude-opus-4-8":{"draws":14,"losses":21,"wins":9},"claude-opus-5":{"draws":8,"losses":66,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":30,"losses":33,"wins":17},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":51,"losses":17,"wins":30},"deepseek/deepseek-v4-pro":{"draws":27,"losses":27,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":30,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":14,"wins":9},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":8},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":30,"losses":29,"wins":21},"google/gemini-3.5-flash-lite":{"draws":56,"losses":41,"wins":41},"google/gemini-3.6-flash":{"draws":53,"losses":49,"wins":30},"google/gemini-3.8-flash":{"draws":21,"losses":39,"wins":10},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":20,"losses":17,"wins":9},"gpt-5.4":{"draws":26,"losses":32,"wins":12},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":15},"gpt-5.5":{"draws":23,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":40,"losses":18,"wins":22},"gpt-5.6-sol":{"draws":12,"losses":41,"wins":9},"gpt-5.6-terra":{"draws":40,"losses":25,"wins":9},"gpt-6-astra":{"draws":4,"losses":56,"wins":0},"gpt-6-luna":{"draws":15,"losses":16,"wins":8},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":19},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":27,"losses":10,"wins":27},"meta/muse-glimmer-30b":{"draws":28,"losses":4,"wins":18},"meta/muse-spark-1.2":{"draws":20,"losses":24,"wins":14},"meta/muse-spark-1.3":{"draws":24,"losses":20,"wins":12},"meta/muse-wonder":{"draws":11,"losses":24,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":5,"wins":9},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":28,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":22,"losses":23,"wins":13},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":14},"o3":{"draws":17,"losses":38,"wins":21},"openai/gpt-oss-120b":{"draws":34,"losses":15,"wins":23},"poolside/laguna-s-2.1":{"draws":30,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":20,"wins":17},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":21,"losses":12,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":26,"wins":22},"qwen/qwen3.8-max-0902":{"draws":16,"losses":18,"wins":6},"stealth/ox-alpha":{"draws":65,"losses":123,"wins":48},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":20},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":4},"tencent/hy4-preview":{"draws":30,"losses":28,"wins":12},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":31},"thinkingmachines/inkling-small":{"draws":42,"losses":5,"wins":33},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":30,"wins":10},"x-ai/grok-4.6":{"draws":20,"losses":40,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":11,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":5,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":58,"losses":42,"wins":24},"z-ai/glm-5.3":{"draws":18,"losses":33,"wins":7},"z-ai/glm-5.3-flash":{"draws":22,"losses":38,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":10}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":27},"claude-fable-5":{"draws":8,"losses":22,"wins":14},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":18,"losses":16,"wins":40},"claude-opus-4-8":{"draws":8,"losses":13,"wins":21},"claude-opus-5":{"draws":12,"losses":53,"wins":7},"claude-opus-5-5":{"draws":4,"losses":42,"wins":2},"claude-sonnet-5":{"draws":11,"losses":6,"wins":25},"claude-sonnet-5-5":{"draws":6,"losses":17,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":42},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":18},"fireworks/ember-1":{"draws":12,"losses":15,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":20},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":17,"wins":27},"google/gemini-3.5-flash-lite":{"draws":16,"losses":15,"wins":49},"google/gemini-3.6-flash":{"draws":13,"losses":29,"wins":34},"google/gemini-3.8-flash":{"draws":7,"losses":18,"wins":21},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":18},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":27},"gpt-5.4":{"draws":9,"losses":20,"wins":15},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":16},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":25},"gpt-5.5":{"draws":8,"losses":20,"wins":14},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":22},"gpt-6-astra":{"draws":2,"losses":39,"wins":1},"gpt-6-luna":{"draws":11,"losses":9,"wins":24},"gpt-6-sol":{"draws":7,"losses":28,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":16},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":36},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":7,"losses":7,"wins":12},"meta/muse-spark-1.3":{"draws":6,"losses":20,"wins":18},"meta/muse-wonder":{"draws":9,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":23},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":22},"o3":{"draws":6,"losses":19,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":13,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":18},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":21},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":23},"stealth/ox-alpha":{"draws":28,"losses":52,"wins":62},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":4,"losses":16,"wins":22},"thinkingmachines/inkling":{"draws":12,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":16,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":20,"losses":22,"wins":44},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":19},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":17}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":2,"wins":31},"claude-fable-5":{"draws":6,"losses":19,"wins":21},"claude-fable-5-1":{"draws":4,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":7,"losses":13,"wins":24},"claude-opus-4-5":{"draws":9,"losses":7,"wins":52},"claude-opus-4-8":{"draws":7,"losses":8,"wins":25},"claude-opus-5":{"draws":11,"losses":43,"wins":20},"claude-opus-5-5":{"draws":1,"losses":37,"wins":4},"claude-sonnet-5":{"draws":4,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":5,"losses":15,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":58},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":25},"fireworks/ember-1":{"draws":6,"losses":6,"wins":32},"gemini-3.1-pro-preview":{"draws":6,"losses":9,"wins":29},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":35},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":60},"google/gemini-3.6-flash":{"draws":8,"losses":18,"wins":52},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":21},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":2,"wins":30},"gpt-5.4":{"draws":9,"losses":13,"wins":22},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":34},"gpt-5.5":{"draws":6,"losses":10,"wins":22},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":25},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":29},"gpt-6-astra":{"draws":5,"losses":32,"wins":5},"gpt-6-luna":{"draws":6,"losses":6,"wins":34},"gpt-6-sol":{"draws":7,"losses":22,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":27},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":26},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":32},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":27},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":27},"meta/muse-spark-1.3":{"draws":5,"losses":2,"wins":23},"meta/muse-wonder":{"draws":8,"losses":21,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":27},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":32},"o3":{"draws":3,"losses":9,"wins":50},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":27},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":30},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":27},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":16},"qwen/qwen3.8-max":{"draws":5,"losses":11,"wins":28},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":19},"stealth/ox-alpha":{"draws":21,"losses":31,"wins":98},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":26},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":45},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":36},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":9,"wins":27},"x-ai/grok-4.6":{"draws":8,"losses":14,"wins":24},"x-ai/grok-4.7":{"draws":5,"losses":19,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":61},"z-ai/glm-5.3":{"draws":10,"losses":16,"wins":18},"z-ai/glm-5.3-flash":{"draws":5,"losses":17,"wins":22},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":26}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":32},"claude-fable-5":{"draws":6,"losses":12,"wins":24},"claude-fable-5-1":{"draws":5,"losses":31,"wins":14},"claude-haiku-5-5":{"draws":5,"losses":6,"wins":33},"claude-opus-4-5":{"draws":7,"losses":4,"wins":59},"claude-opus-4-8":{"draws":9,"losses":4,"wins":25},"claude-opus-5":{"draws":10,"losses":25,"wins":37},"claude-opus-5-5":{"draws":4,"losses":30,"wins":12},"claude-sonnet-5":{"draws":5,"losses":5,"wins":36},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":60},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":5,"wins":29},"fireworks/ember-1":{"draws":10,"losses":5,"wins":29},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":28},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":45},"google/gemini-3.5-flash-lite":{"draws":8,"losses":5,"wins":65},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":62},"google/gemini-3.8-flash":{"draws":7,"losses":12,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":4,"losses":4,"wins":30},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":41},"gpt-5.5":{"draws":7,"losses":10,"wins":25},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":32},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":29},"gpt-5.6-terra":{"draws":8,"losses":5,"wins":29},"gpt-6-astra":{"draws":6,"losses":29,"wins":9},"gpt-6-luna":{"draws":7,"losses":3,"wins":36},"gpt-6-sol":{"draws":4,"losses":19,"wins":21},"gpt-6.1-sol":{"draws":9,"losses":24,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":40},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":29},"meta/muse-spark-1.2":{"draws":1,"losses":9,"wins":34},"meta/muse-spark-1.3":{"draws":6,"losses":5,"wins":35},"meta/muse-wonder":{"draws":6,"losses":7,"wins":19},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":33},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":32},"o3":{"draws":2,"losses":6,"wins":52},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":38},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":24},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":8,"wins":31},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":25},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":36},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":29},"stealth/ox-alpha":{"draws":19,"losses":15,"wins":110},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":31},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":20},"tencent/hy4-preview":{"draws":5,"losses":6,"wins":31},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":43},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":38},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":33},"x-ai/grok-4.6":{"draws":12,"losses":5,"wins":25},"x-ai/grok-4.7":{"draws":6,"losses":16,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":8,"losses":1,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":15,"losses":4,"wins":69},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":28},"z-ai/glm-5.3-flash":{"draws":9,"losses":10,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":29}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":22},"claude-fable-5":{"draws":6,"losses":23,"wins":15},"claude-fable-5-1":{"draws":1,"losses":45,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":18,"losses":18,"wins":34},"claude-opus-4-8":{"draws":7,"losses":12,"wins":23},"claude-opus-5":{"draws":13,"losses":49,"wins":12},"claude-opus-5-5":{"draws":8,"losses":34,"wins":4},"claude-sonnet-5":{"draws":14,"losses":18,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":12,"losses":8,"wins":44},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":19},"fireworks/ember-1":{"draws":7,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":5,"losses":13,"wins":24},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":15,"wins":24},"google/gemini-3.5-flash-lite":{"draws":12,"losses":14,"wins":48},"google/gemini-3.6-flash":{"draws":9,"losses":25,"wins":44},"google/gemini-3.8-flash":{"draws":10,"losses":15,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":4,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":6,"wins":24},"gpt-5.4":{"draws":12,"losses":16,"wins":12},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":31},"gpt-5.5":{"draws":7,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":27},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":17},"gpt-6-astra":{"draws":7,"losses":32,"wins":5},"gpt-6-luna":{"draws":12,"losses":15,"wins":19},"gpt-6-sol":{"draws":9,"losses":28,"wins":9},"gpt-6.1-sol":{"draws":8,"losses":31,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":27},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":20},"meta/muse-spark-1.2":{"draws":5,"losses":19,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":17,"wins":17},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":16},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":13,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":19},"o3":{"draws":10,"losses":16,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":11,"losses":11,"wins":22},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":20},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.8-max":{"draws":10,"losses":10,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":43,"losses":46,"wins":53},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":13,"losses":3,"wins":36},"thinkingmachines/inkling-small":{"draws":13,"losses":3,"wins":30},"unbiased/pareto-26.10-preview":{"draws":3,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":12,"wins":23},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":14,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":24,"losses":16,"wins":46},"z-ai/glm-5.3":{"draws":3,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":19,"wins":16},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":18}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":19,"wins":20},"claude-fable-5":{"draws":25,"losses":30,"wins":7},"claude-fable-5-1":{"draws":3,"losses":54,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":25,"wins":2},"claude-opus-4-5":{"draws":26,"losses":52,"wins":12},"claude-opus-4-8":{"draws":13,"losses":26,"wins":3},"claude-opus-5":{"draws":12,"losses":54,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":37,"losses":26,"wins":15},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":39,"losses":30,"wins":29},"deepseek/deepseek-v4-pro":{"draws":21,"losses":39,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":32,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":22,"wins":6},"fireworks/ember-1":{"draws":14,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":18,"losses":16,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":11,"wins":14},"google/gemini-3.5-flash":{"draws":28,"losses":38,"wins":16},"google/gemini-3.5-flash-lite":{"draws":59,"losses":50,"wins":33},"google/gemini-3.6-flash":{"draws":40,"losses":58,"wins":18},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":6},"google/gemma-4-31b-it":{"draws":9,"losses":10,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":17,"wins":9},"gpt-5.4":{"draws":28,"losses":30,"wins":8},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":20,"wins":13},"gpt-5.5":{"draws":16,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":36,"losses":34,"wins":8},"gpt-5.6-sol":{"draws":17,"losses":46,"wins":3},"gpt-5.6-terra":{"draws":26,"losses":38,"wins":10},"gpt-6-astra":{"draws":4,"losses":48,"wins":0},"gpt-6-luna":{"draws":15,"losses":22,"wins":5},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":14,"wins":22},"inclusionai/ling-3.0-flash":{"draws":14,"losses":13,"wins":17},"meituan/longcat-2.0":{"draws":30,"losses":23,"wins":21},"meta/muse-glimmer-30b":{"draws":36,"losses":26,"wins":10},"meta/muse-spark-1.2":{"draws":19,"losses":28,"wins":13},"meta/muse-spark-1.3":{"draws":19,"losses":36,"wins":5},"meta/muse-wonder":{"draws":8,"losses":29,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":12,"wins":13},"mistralai/mistral-large-4-0":{"draws":7,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":29,"wins":11},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":11,"wins":8},"o3":{"draws":18,"losses":53,"wins":15},"openai/gpt-oss-120b":{"draws":36,"losses":14,"wins":22},"poolside/laguna-s-2.1":{"draws":26,"losses":23,"wins":17},"qwen/qwen3.7-max":{"draws":14,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":43,"wins":4},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":21,"losses":19,"wins":6},"qwen/qwen3.8-max":{"draws":29,"losses":34,"wins":9},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":67,"losses":125,"wins":46},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":31,"losses":30,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":21,"wins":19},"thinkingmachines/inkling-small":{"draws":38,"losses":34,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":1},"x-ai/grok-4.5":{"draws":18,"losses":38,"wins":8},"x-ai/grok-4.6":{"draws":27,"losses":37,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":29,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":52,"losses":48,"wins":22},"z-ai/glm-5.3":{"draws":15,"losses":39,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":12},"z-ai/glm-5.3-flashx":{"draws":14,"losses":24,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":17},"claude-fable-5":{"draws":6,"losses":20,"wins":12},"claude-fable-5-1":{"draws":0,"losses":35,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":16,"wins":14},"claude-opus-4-5":{"draws":17,"losses":15,"wins":26},"claude-opus-4-8":{"draws":8,"losses":11,"wins":13},"claude-opus-5":{"draws":11,"losses":43,"wins":16},"claude-opus-5-5":{"draws":2,"losses":35,"wins":3},"claude-sonnet-5":{"draws":10,"losses":10,"wins":18},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":16,"wins":25},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":11,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":13},"fireworks/ember-1":{"draws":11,"losses":12,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":19},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":16},"google/gemini-3.5-flash":{"draws":13,"losses":13,"wins":22},"google/gemini-3.5-flash-lite":{"draws":19,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":12,"losses":25,"wins":27},"google/gemini-3.8-flash":{"draws":6,"losses":16,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":13,"wins":18},"gpt-5.4":{"draws":7,"losses":13,"wins":16},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":16},"gpt-5.5":{"draws":9,"losses":12,"wins":17},"gpt-5.6-luna":{"draws":11,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":13},"gpt-5.6-terra":{"draws":7,"losses":10,"wins":17},"gpt-6-astra":{"draws":5,"losses":32,"wins":1},"gpt-6-luna":{"draws":11,"losses":6,"wins":21},"gpt-6-sol":{"draws":4,"losses":29,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":7,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":22},"meta/muse-glimmer-30b":{"draws":5,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":6,"losses":15,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":15,"wins":15},"meta/muse-wonder":{"draws":6,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":13,"wins":12},"o3":{"draws":7,"losses":19,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":9,"wins":18},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":12},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":8,"losses":14,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":22,"wins":11},"stealth/ox-alpha":{"draws":29,"losses":46,"wins":61},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":15},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":26},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":17},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":15,"wins":17},"x-ai/grok-4.6":{"draws":7,"losses":21,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":17,"losses":12,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":19,"losses":24,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":15}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":14,"wins":15},"claude-fable-5":{"draws":14,"losses":39,"wins":1},"claude-fable-5-1":{"draws":4,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":7},"claude-opus-4-5":{"draws":69,"losses":72,"wins":17},"claude-opus-4-8":{"draws":29,"losses":55,"wins":12},"claude-opus-5":{"draws":22,"losses":114,"wins":2},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":28,"losses":24,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":9},"cohere/north-mini-code":{"draws":10,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":61,"losses":26,"wins":27},"deepseek/deepseek-v4-pro":{"draws":21,"losses":21,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":23,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":21,"wins":10},"fireworks/ember-1":{"draws":26,"losses":24,"wins":4},"gemini-3.1-pro-preview":{"draws":26,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":31,"losses":14,"wins":34},"google/gemini-3.5-flash":{"draws":31,"losses":30,"wins":17},"google/gemini-3.5-flash-lite":{"draws":53,"losses":36,"wins":35},"google/gemini-3.6-flash":{"draws":43,"losses":58,"wins":11},"google/gemini-3.8-flash":{"draws":23,"losses":30,"wins":3},"google/gemma-4-31b-it":{"draws":15,"losses":7,"wins":6},"gpt-4.1":{"draws":18,"losses":8,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":40,"losses":34,"wins":8},"gpt-5.4":{"draws":20,"losses":29,"wins":1},"gpt-5.4-mini":{"draws":38,"losses":16,"wins":8},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":26},"gpt-5.5":{"draws":40,"losses":41,"wins":1},"gpt-5.6-luna":{"draws":27,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":27,"losses":24,"wins":5},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":19,"losses":28,"wins":7},"gpt-6-sol":{"draws":6,"losses":46,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":31,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":14,"wins":30},"meta/muse-glimmer-30b":{"draws":28,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":15,"losses":32,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":36,"wins":3},"meta/muse-wonder":{"draws":18,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":27,"losses":13,"wins":16},"mistralai/mistral-large-4-0":{"draws":10,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":15,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":21,"wins":7},"nex-agi/nex-n2-pro":{"draws":25,"losses":7,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":24,"wins":8},"o3":{"draws":35,"losses":66,"wins":19},"openai/gpt-oss-120b":{"draws":27,"losses":9,"wins":12},"poolside/laguna-s-2.1":{"draws":37,"losses":20,"wins":13},"qwen/qwen3.7-max":{"draws":41,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":29,"losses":15,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":20,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":27,"losses":25,"wins":4},"qwen/qwen3.8-max-0902":{"draws":24,"losses":22,"wins":4},"stealth/ox-alpha":{"draws":58,"losses":84,"wins":12},"stealth/space-bunny-alpha":{"draws":20,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":20,"losses":18,"wins":14},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":40,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":20,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":41,"losses":25,"wins":46},"thinkingmachines/inkling-small":{"draws":31,"losses":13,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":24,"losses":46,"wins":2},"x-ai/grok-4.6":{"draws":26,"losses":25,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":22,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":95,"losses":30,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":20,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":21,"wins":3},"z-ai/glm-5.2":{"draws":82,"losses":54,"wins":18},"z-ai/glm-5.3":{"draws":14,"losses":38,"wins":4},"z-ai/glm-5.3-flash":{"draws":24,"losses":21,"wins":9},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":63,"wins":102},"claude-fable-5":{"draws":11,"losses":150,"wins":33},"claude-fable-5-1":{"draws":0,"losses":190,"wins":12},"claude-haiku-5-5":{"draws":7,"losses":53,"wins":44},"claude-opus-4-5":{"draws":42,"losses":258,"wins":118},"claude-opus-4-8":{"draws":7,"losses":97,"wins":44},"claude-opus-5":{"draws":6,"losses":222,"wins":14},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":23,"losses":138,"wins":163},"claude-sonnet-5-5":{"draws":4,"losses":83,"wins":27},"cohere/north-mini-code":{"draws":4,"losses":11,"wins":39},"deepseek/deepseek-v4-flash":{"draws":31,"losses":87,"wins":154},"deepseek/deepseek-v4-pro":{"draws":19,"losses":100,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":101,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":53,"wins":39},"fireworks/ember-1":{"draws":10,"losses":68,"wins":36},"gemini-3.1-pro-preview":{"draws":13,"losses":44,"wins":57},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":99},"google/gemini-3.5-flash":{"draws":23,"losses":134,"wins":77},"google/gemini-3.5-flash-lite":{"draws":88,"losses":197,"wins":427},"google/gemini-3.6-flash":{"draws":75,"losses":359,"wins":238},"google/gemini-3.8-flash":{"draws":19,"losses":129,"wins":56},"google/gemma-4-31b-it":{"draws":1,"losses":13,"wins":42},"gpt-4.1":{"draws":4,"losses":21,"wins":19},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":13,"losses":77,"wins":52},"gpt-5.4":{"draws":24,"losses":218,"wins":66},"gpt-5.4-mini":{"draws":12,"losses":17,"wins":49},"gpt-5.4-nano":{"draws":7,"losses":70,"wins":77},"gpt-5.5":{"draws":18,"losses":84,"wins":30},"gpt-5.6-luna":{"draws":42,"losses":124,"wins":156},"gpt-5.6-sol":{"draws":13,"losses":234,"wins":61},"gpt-5.6-terra":{"draws":24,"losses":88,"wins":86},"gpt-6-astra":{"draws":5,"losses":181,"wins":2},"gpt-6-luna":{"draws":11,"losses":62,"wins":35},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":107,"wins":7},"inception/mercury-2.5-preview":{"draws":21,"losses":17,"wins":100},"inclusionai/ling-3.0-flash":{"draws":10,"losses":29,"wins":107},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":78,"wins":185},"meta/muse-glimmer-30b":{"draws":32,"losses":29,"wins":113},"meta/muse-spark-1.2":{"draws":15,"losses":85,"wins":128},"meta/muse-spark-1.3":{"draws":8,"losses":98,"wins":62},"meta/muse-wonder":{"draws":3,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":5,"losses":20,"wins":49},"mistralai/mistral-large-4-0":{"draws":10,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":16,"losses":14,"wins":86},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":13,"wins":19},"moonshotai/kimi-k3":{"draws":30,"losses":113,"wins":139},"nex-agi/nex-n2-pro":{"draws":7,"losses":13,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":31,"wins":93},"o3":{"draws":27,"losses":204,"wins":209},"openai/gpt-oss-120b":{"draws":25,"losses":33,"wins":120},"poolside/laguna-s-2.1":{"draws":43,"losses":69,"wins":112},"qwen/qwen3.7-max":{"draws":12,"losses":29,"wins":35},"qwen/qwen3.7-plus":{"draws":4,"losses":17,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":112,"wins":73},"qwen/qwen3.8-27b":{"draws":7,"losses":62,"wins":47},"qwen/qwen3.8-flash":{"draws":24,"losses":55,"wins":55},"qwen/qwen3.8-max":{"draws":30,"losses":112,"wins":74},"qwen/qwen3.8-max-0902":{"draws":14,"losses":53,"wins":43},"stealth/ox-alpha":{"draws":58,"losses":284,"wins":268},"stealth/space-bunny-alpha":{"draws":7,"losses":36,"wins":49},"stepfun/step-3.7-flash":{"draws":15,"losses":42,"wins":77},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":38,"wins":42},"tencent/hy4-preview":{"draws":25,"losses":114,"wins":71},"thinkingmachines/inkling":{"draws":27,"losses":56,"wins":185},"thinkingmachines/inkling-small":{"draws":41,"losses":55,"wins":117},"unbiased/pareto-26.10-preview":{"draws":0,"losses":33,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":9,"wins":25},"x-ai/grok-4.5":{"draws":14,"losses":184,"wins":98},"x-ai/grok-4.6":{"draws":29,"losses":110,"wins":59},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":23},"xiaomi/mimo-v2.5":{"draws":23,"losses":32,"wins":135},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":39,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":44,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":45,"wins":21},"z-ai/glm-5.2":{"draws":40,"losses":126,"wins":156},"z-ai/glm-5.3":{"draws":11,"losses":112,"wins":43},"z-ai/glm-5.3-flash":{"draws":20,"losses":90,"wins":88},"z-ai/glm-5.3-flashx":{"draws":7,"losses":68,"wins":39}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":24,"wins":19},"claude-fable-5":{"draws":19,"losses":32,"wins":13},"claude-fable-5-1":{"draws":4,"losses":60,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":24,"wins":4},"claude-opus-4-5":{"draws":21,"losses":39,"wins":24},"claude-opus-4-8":{"draws":13,"losses":17,"wins":8},"claude-opus-5":{"draws":13,"losses":59,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":22,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":41,"losses":23,"wins":28},"deepseek/deepseek-v4-pro":{"draws":30,"losses":21,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":25,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":11},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":12},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":31,"losses":29,"wins":22},"google/gemini-3.5-flash-lite":{"draws":51,"losses":38,"wins":39},"google/gemini-3.6-flash":{"draws":43,"losses":61,"wins":18},"google/gemini-3.8-flash":{"draws":13,"losses":39,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":15,"wins":9},"gpt-5.4":{"draws":27,"losses":25,"wins":14},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":15},"gpt-5.5":{"draws":15,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":40,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":15,"losses":43,"wins":10},"gpt-5.6-terra":{"draws":31,"losses":28,"wins":15},"gpt-6-astra":{"draws":6,"losses":50,"wins":0},"gpt-6-luna":{"draws":13,"losses":18,"wins":9},"gpt-6-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":20},"meituan/longcat-2.0":{"draws":23,"losses":25,"wins":20},"meta/muse-glimmer-30b":{"draws":28,"losses":15,"wins":17},"meta/muse-spark-1.2":{"draws":19,"losses":25,"wins":14},"meta/muse-spark-1.3":{"draws":13,"losses":38,"wins":9},"meta/muse-wonder":{"draws":9,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":7},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":13},"o3":{"draws":19,"losses":44,"wins":21},"openai/gpt-oss-120b":{"draws":21,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":34,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":31,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-max":{"draws":21,"losses":44,"wins":7},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":60,"losses":106,"wins":55},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":6},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":27,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":18,"wins":20},"thinkingmachines/inkling-small":{"draws":38,"losses":19,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":18,"losses":37,"wins":7},"x-ai/grok-4.6":{"draws":18,"losses":33,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":12,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":1},"z-ai/glm-5.2":{"draws":48,"losses":46,"wins":26},"z-ai/glm-5.3":{"draws":20,"losses":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":23,"losses":34,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":26,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":2,"wins":43},"claude-fable-5":{"draws":22,"losses":24,"wins":41},"claude-fable-5-1":{"draws":11,"losses":86,"wins":11},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":23},"claude-opus-4-5":{"draws":29,"losses":11,"wins":64},"claude-opus-4-8":{"draws":8,"losses":5,"wins":31},"claude-opus-5":{"draws":18,"losses":66,"wins":20},"claude-opus-5-5":{"draws":4,"losses":37,"wins":11},"claude-sonnet-5":{"draws":25,"losses":10,"wins":45},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":20,"losses":9,"wins":67},"deepseek/deepseek-v4-pro":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":9,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":24},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":20,"losses":17,"wins":55},"google/gemini-3.5-flash-lite":{"draws":30,"losses":8,"wins":90},"google/gemini-3.6-flash":{"draws":37,"losses":32,"wins":67},"google/gemini-3.8-flash":{"draws":21,"losses":28,"wins":41},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":19},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":9,"wins":28},"gpt-5.4":{"draws":12,"losses":22,"wins":50},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":2,"wins":43},"gpt-5.5":{"draws":13,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":42},"gpt-5.6-sol":{"draws":17,"losses":34,"wins":43},"gpt-5.6-terra":{"draws":26,"losses":12,"wins":46},"gpt-6-astra":{"draws":2,"losses":84,"wins":10},"gpt-6-luna":{"draws":12,"losses":8,"wins":26},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":33,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":26},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":33},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":14,"losses":4,"wins":42},"meta/muse-spark-1.2":{"draws":20,"losses":15,"wins":31},"meta/muse-spark-1.3":{"draws":14,"losses":16,"wins":46},"meta/muse-wonder":{"draws":8,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":17},"mistralai/mistral-medium-3-5":{"draws":12,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":24,"losses":15,"wins":31},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":30},"o3":{"draws":4,"losses":20,"wins":68},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":41},"poolside/laguna-s-2.1":{"draws":16,"losses":2,"wins":40},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":10,"wins":34},"qwen/qwen3.8-27b":{"draws":15,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":30},"qwen/qwen3.8-max":{"draws":24,"losses":16,"wins":42},"qwen/qwen3.8-max-0902":{"draws":14,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":67,"losses":72,"wins":141},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":20,"losses":24,"wins":34},"thinkingmachines/inkling":{"draws":20,"losses":3,"wins":39},"thinkingmachines/inkling-small":{"draws":23,"losses":8,"wins":41},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":16,"wins":36},"x-ai/grok-4.6":{"draws":20,"losses":25,"wins":47},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":15},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":37,"losses":20,"wins":65},"z-ai/glm-5.3":{"draws":20,"losses":28,"wins":26},"z-ai/glm-5.3-flash":{"draws":16,"losses":22,"wins":48},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":12,"wins":36},"claude-fable-5":{"draws":6,"losses":39,"wins":21},"claude-fable-5-1":{"draws":3,"losses":69,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":12,"wins":17},"claude-opus-4-5":{"draws":11,"losses":22,"wins":51},"claude-opus-4-8":{"draws":5,"losses":13,"wins":18},"claude-opus-5":{"draws":6,"losses":52,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":20,"wins":34},"claude-sonnet-5-5":{"draws":3,"losses":18,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":5,"losses":23,"wins":52},"deepseek/deepseek-v4-pro":{"draws":3,"losses":21,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":19,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":20,"wins":13},"fireworks/ember-1":{"draws":3,"losses":11,"wins":22},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":15,"wins":43},"google/gemini-3.5-flash-lite":{"draws":10,"losses":15,"wins":81},"google/gemini-3.6-flash":{"draws":13,"losses":42,"wins":53},"google/gemini-3.8-flash":{"draws":8,"losses":26,"wins":30},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":14},"gpt-4.1":{"draws":2,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":12,"wins":24},"gpt-5.4":{"draws":10,"losses":34,"wins":20},"gpt-5.4-mini":{"draws":1,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":4,"losses":13,"wins":25},"gpt-5.5":{"draws":3,"losses":22,"wins":15},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":31},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":24},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":28},"gpt-6-astra":{"draws":0,"losses":68,"wins":0},"gpt-6-luna":{"draws":4,"losses":13,"wins":19},"gpt-6-sol":{"draws":5,"losses":23,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":3,"wins":34},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":30},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":44},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":4,"losses":15,"wins":33},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":31},"meta/muse-wonder":{"draws":2,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":7,"losses":28,"wins":17},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":24},"o3":{"draws":6,"losses":29,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":8,"wins":40},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":1,"losses":10,"wins":17},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":25,"wins":22},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":22},"qwen/qwen3.8-max":{"draws":14,"losses":24,"wins":24},"qwen/qwen3.8-max-0902":{"draws":6,"losses":13,"wins":17},"stealth/ox-alpha":{"draws":31,"losses":68,"wins":93},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":20},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":28},"thinkingmachines/inkling":{"draws":1,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":56},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":0,"losses":36,"wins":20},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":29},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":18,"losses":28,"wins":52},"z-ai/glm-5.3":{"draws":12,"losses":33,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":20,"wins":36},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":17}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":24,"wins":33},"claude-fable-5":{"draws":16,"losses":50,"wins":18},"claude-fable-5-1":{"draws":5,"losses":95,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":10},"claude-opus-4-5":{"draws":35,"losses":25,"wins":54},"claude-opus-4-8":{"draws":5,"losses":23,"wins":18},"claude-opus-5":{"draws":7,"losses":67,"wins":12},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":18,"losses":27,"wins":41},"claude-sonnet-5-5":{"draws":7,"losses":23,"wins":18},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":27,"losses":24,"wins":57},"deepseek/deepseek-v4-pro":{"draws":21,"losses":21,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":23,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":27,"losses":37,"wins":30},"google/gemini-3.5-flash-lite":{"draws":40,"losses":23,"wins":85},"google/gemini-3.6-flash":{"draws":27,"losses":59,"wins":62},"google/gemini-3.8-flash":{"draws":27,"losses":41,"wins":20},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":16},"gpt-4.1":{"draws":8,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":14,"wins":15},"gpt-5.4":{"draws":23,"losses":28,"wins":31},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":12,"wins":30},"gpt-5.5":{"draws":13,"losses":17,"wins":18},"gpt-5.6-luna":{"draws":17,"losses":16,"wins":44},"gpt-5.6-sol":{"draws":19,"losses":55,"wins":16},"gpt-5.6-terra":{"draws":36,"losses":19,"wins":27},"gpt-6-astra":{"draws":10,"losses":80,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":20},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":21,"losses":0,"wins":35},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":50},"meta/muse-glimmer-30b":{"draws":21,"losses":16,"wins":29},"meta/muse-spark-1.2":{"draws":18,"losses":24,"wins":21},"meta/muse-spark-1.3":{"draws":17,"losses":34,"wins":23},"meta/muse-wonder":{"draws":8,"losses":25,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":15,"losses":3,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":28},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":21},"o3":{"draws":13,"losses":36,"wins":50},"openai/gpt-oss-120b":{"draws":19,"losses":4,"wins":45},"poolside/laguna-s-2.1":{"draws":23,"losses":12,"wins":31},"qwen/qwen3.7-max":{"draws":14,"losses":8,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":34,"wins":25},"qwen/qwen3.8-27b":{"draws":12,"losses":8,"wins":24},"qwen/qwen3.8-flash":{"draws":18,"losses":12,"wins":26},"qwen/qwen3.8-max":{"draws":20,"losses":27,"wins":36},"qwen/qwen3.8-max-0902":{"draws":8,"losses":23,"wins":15},"stealth/ox-alpha":{"draws":75,"losses":117,"wins":104},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":2,"wins":12},"tencent/hy4-preview":{"draws":18,"losses":34,"wins":30},"thinkingmachines/inkling":{"draws":22,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":44,"losses":25,"wins":59},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":29},"x-ai/grok-4.6":{"draws":27,"losses":33,"wins":34},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":8,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":45,"losses":41,"wins":48},"z-ai/glm-5.3":{"draws":9,"losses":45,"wins":20},"z-ai/glm-5.3-flash":{"draws":28,"losses":22,"wins":42},"z-ai/glm-5.3-flashx":{"draws":17,"losses":15,"wins":16}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":32},"claude-fable-5":{"draws":9,"losses":15,"wins":22},"claude-fable-5-1":{"draws":3,"losses":35,"wins":14},"claude-haiku-5-5":{"draws":10,"losses":9,"wins":27},"claude-opus-4-5":{"draws":13,"losses":12,"wins":51},"claude-opus-4-8":{"draws":3,"losses":10,"wins":25},"claude-opus-5":{"draws":8,"losses":40,"wins":30},"claude-opus-5-5":{"draws":8,"losses":30,"wins":8},"claude-sonnet-5":{"draws":8,"losses":5,"wins":29},"claude-sonnet-5-5":{"draws":5,"losses":14,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":26},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":9,"losses":5,"wins":28},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":5,"wins":62},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":54},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":22},"gpt-4.1":{"draws":5,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":4,"wins":28},"gpt-5.4":{"draws":10,"losses":11,"wins":21},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":32},"gpt-5.5":{"draws":11,"losses":8,"wins":21},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":8,"losses":17,"wins":19},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":39,"wins":4},"gpt-6-luna":{"draws":8,"losses":5,"wins":31},"gpt-6-sol":{"draws":5,"losses":22,"wins":17},"gpt-6.1-sol":{"draws":4,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":36},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":7,"wins":28},"meta/muse-spark-1.3":{"draws":8,"losses":7,"wins":31},"meta/muse-wonder":{"draws":13,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":30},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":29},"o3":{"draws":5,"losses":12,"wins":43},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":35},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":5,"wins":28},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":27},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":14},"qwen/qwen3.8-max":{"draws":4,"losses":9,"wins":29},"qwen/qwen3.8-max-0902":{"draws":6,"losses":1,"wins":21},"stealth/ox-alpha":{"draws":27,"losses":36,"wins":83},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":8,"losses":6,"wins":28},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":42},"thinkingmachines/inkling-small":{"draws":10,"losses":4,"wins":32},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":12,"wins":26},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":19},"x-ai/grok-4.7":{"draws":6,"losses":18,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":17,"losses":2,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":16,"losses":10,"wins":64},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":18},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":24},"z-ai/glm-5.3-flashx":{"draws":9,"losses":10,"wins":25}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":30,"wins":152},"claude-fable-5":{"draws":36,"losses":149,"wins":85},"claude-fable-5-1":{"draws":40,"losses":258,"wins":36},"claude-haiku-5-5":{"draws":17,"losses":39,"wins":72},"claude-opus-4-5":{"draws":44,"losses":68,"wins":217},"claude-opus-4-8":{"draws":22,"losses":33,"wins":79},"claude-opus-5":{"draws":41,"losses":193,"wins":59},"claude-opus-5-5":{"draws":11,"losses":123,"wins":22},"claude-sonnet-5":{"draws":28,"losses":60,"wins":181},"claude-sonnet-5-5":{"draws":11,"losses":62,"wins":71},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":45},"deepseek/deepseek-v4-flash":{"draws":21,"losses":27,"wins":245},"deepseek/deepseek-v4-pro":{"draws":28,"losses":56,"wins":140},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":55,"wins":137},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":39,"wins":88},"fireworks/ember-1":{"draws":23,"losses":31,"wins":90},"gemini-3.1-pro-preview":{"draws":15,"losses":38,"wins":91},"google/gemini-3.1-flash-lite":{"draws":8,"losses":8,"wins":79},"google/gemini-3.5-flash":{"draws":30,"losses":74,"wins":185},"google/gemini-3.5-flash-lite":{"draws":36,"losses":42,"wins":301},"google/gemini-3.6-flash":{"draws":48,"losses":133,"wins":241},"google/gemini-3.8-flash":{"draws":30,"losses":103,"wins":145},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":61},"gpt-4.1":{"draws":8,"losses":9,"wins":31},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":12},"gpt-5":{"draws":12,"losses":27,"wins":91},"gpt-5.4":{"draws":47,"losses":84,"wins":124},"gpt-5.4-mini":{"draws":15,"losses":10,"wins":73},"gpt-5.4-nano":{"draws":6,"losses":38,"wins":102},"gpt-5.5":{"draws":18,"losses":41,"wins":81},"gpt-5.6-luna":{"draws":35,"losses":38,"wins":148},"gpt-5.6-sol":{"draws":31,"losses":133,"wins":123},"gpt-5.6-terra":{"draws":40,"losses":68,"wins":134},"gpt-6-astra":{"draws":43,"losses":219,"wins":32},"gpt-6-luna":{"draws":21,"losses":26,"wins":95},"gpt-6-sol":{"draws":18,"losses":86,"wins":40},"gpt-6.1-sol":{"draws":16,"losses":111,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":21,"losses":15,"wins":95},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":98},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":21,"losses":25,"wins":150},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":146},"meta/muse-spark-1.2":{"draws":29,"losses":39,"wins":141},"meta/muse-spark-1.3":{"draws":28,"losses":67,"wins":125},"meta/muse-wonder":{"draws":12,"losses":67,"wins":55},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":62},"mistralai/mistral-large-4-0":{"draws":12,"losses":22,"wins":46},"mistralai/mistral-medium-3-5":{"draws":16,"losses":9,"wins":83},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":22},"moonshotai/kimi-k3":{"draws":34,"losses":56,"wins":133},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":62},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":19,"wins":84},"o3":{"draws":11,"losses":70,"wins":198},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":148},"poolside/laguna-s-2.1":{"draws":25,"losses":19,"wins":141},"qwen/qwen3.7-max":{"draws":6,"losses":13,"wins":67},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":61},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":74,"wins":151},"qwen/qwen3.8-27b":{"draws":13,"losses":32,"wins":89},"qwen/qwen3.8-flash":{"draws":22,"losses":44,"wins":105},"qwen/qwen3.8-max":{"draws":36,"losses":66,"wins":158},"qwen/qwen3.8-max-0902":{"draws":20,"losses":38,"wins":82},"stealth/ox-alpha":{"draws":130,"losses":214,"wins":555},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":87},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":87},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":14,"losses":14,"wins":52},"tencent/hy4-preview":{"draws":36,"losses":82,"wins":131},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":160},"thinkingmachines/inkling-small":{"draws":29,"losses":9,"wins":188},"unbiased/pareto-26.10-preview":{"draws":9,"losses":31,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":21,"losses":102,"wins":97},"x-ai/grok-4.6":{"draws":49,"losses":108,"wins":119},"x-ai/grok-4.7":{"draws":12,"losses":75,"wins":37},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":44},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":184},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":15,"wins":67},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":20,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":35,"wins":44},"z-ai/glm-5.2":{"draws":45,"losses":69,"wins":258},"z-ai/glm-5.3":{"draws":28,"losses":87,"wins":105},"z-ai/glm-5.3-flash":{"draws":33,"losses":81,"wins":153},"z-ai/glm-5.3-flashx":{"draws":18,"losses":44,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":15},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":1,"losses":37,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":11},"claude-opus-4-5":{"draws":18,"losses":27,"wins":15},"claude-opus-4-8":{"draws":8,"losses":15,"wins":13},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":6,"losses":13,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":14,"wins":8},"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":6,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":15},"google/gemini-3.5-flash-lite":{"draws":16,"losses":16,"wins":34},"google/gemini-3.6-flash":{"draws":14,"losses":33,"wins":21},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":8},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":11},"gpt-4.1":{"draws":6,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":13,"wins":13},"gpt-5.4":{"draws":6,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":11,"losses":15,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":13},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":12},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":15},"meta/muse-wonder":{"draws":5,"losses":20,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":13},"mistralai/mistral-large-4-0":{"draws":5,"losses":9,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":14,"wins":12},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":7,"losses":18,"wins":9},"stealth/ox-alpha":{"draws":22,"losses":45,"wins":35},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":10,"wins":21},"thinkingmachines/inkling-small":{"draws":8,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":21,"wins":9},"claude-fable-5":{"draws":2,"losses":29,"wins":3},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":22,"wins":5},"claude-opus-4-5":{"draws":8,"losses":59,"wins":15},"claude-opus-4-8":{"draws":4,"losses":37,"wins":9},"claude-opus-5":{"draws":1,"losses":60,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":5,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":0,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":15,"losses":30,"wins":25},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":18,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":2},"fireworks/ember-1":{"draws":4,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":15,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":38},"google/gemini-3.5-flash":{"draws":9,"losses":26,"wins":11},"google/gemini-3.5-flash-lite":{"draws":16,"losses":37,"wins":19},"google/gemini-3.6-flash":{"draws":11,"losses":57,"wins":5},"google/gemini-3.8-flash":{"draws":6,"losses":27,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":38,"wins":2},"gpt-5.4":{"draws":6,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":6,"losses":32,"wins":22},"gpt-5.5":{"draws":7,"losses":38,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":14,"wins":11},"gpt-5.6-sol":{"draws":0,"losses":28,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":17,"wins":5},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":1,"losses":20,"wins":7},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":6,"losses":9,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":22,"wins":17},"meta/muse-glimmer-30b":{"draws":6,"losses":19,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":22,"wins":7},"meta/muse-spark-1.3":{"draws":2,"losses":34,"wins":0},"meta/muse-wonder":{"draws":1,"losses":26,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":17,"wins":4},"mistralai/mistral-large-4-0":{"draws":2,"losses":13,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":22,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":22,"wins":22},"o3":{"draws":14,"losses":61,"wins":21},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":12},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.7-max":{"draws":8,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":20,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":1,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":6,"losses":27,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":17,"wins":6},"stealth/ox-alpha":{"draws":9,"losses":72,"wins":15},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":1,"losses":10,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":4,"losses":24,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":14,"wins":36},"thinkingmachines/inkling-small":{"draws":7,"losses":13,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":37,"wins":3},"x-ai/grok-4.6":{"draws":4,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":41,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":45,"wins":20},"z-ai/glm-5.3":{"draws":2,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":21,"wins":5}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":14},"claude-fable-5":{"draws":13,"losses":24,"wins":5},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":18,"wins":12},"claude-opus-4-5":{"draws":42,"losses":48,"wins":26},"claude-opus-4-8":{"draws":15,"losses":36,"wins":17},"claude-opus-5":{"draws":17,"losses":108,"wins":5},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":32,"wins":33},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":11},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":14},"google/gemini-3.1-flash-lite":{"draws":18,"losses":17,"wins":29},"google/gemini-3.5-flash":{"draws":16,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":24,"losses":23,"wins":37},"google/gemini-3.6-flash":{"draws":25,"losses":50,"wins":25},"google/gemini-3.8-flash":{"draws":16,"losses":24,"wins":6},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":10},"gpt-4.1":{"draws":16,"losses":14,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":20,"losses":27,"wins":31},"gpt-5.4":{"draws":13,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":15,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":32},"gpt-5.5":{"draws":37,"losses":30,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":12},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":9,"wins":23},"meituan/longcat-2.0":{"draws":16,"losses":22,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":24,"wins":12},"meta/muse-spark-1.3":{"draws":5,"losses":29,"wins":10},"meta/muse-wonder":{"draws":5,"losses":27,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":16,"wins":33},"o3":{"draws":17,"losses":36,"wins":41},"openai/gpt-oss-120b":{"draws":12,"losses":12,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":24},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":8},"qwen/qwen3.7-plus":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":12},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":38,"losses":58,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":15,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":31},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":45,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.5":{"draws":35,"losses":35,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":20,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":34,"losses":40,"wins":42},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":7},"z-ai/glm-5.3-flashx":{"draws":6,"losses":27,"wins":9}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":4,"wins":38},"claude-fable-5":{"draws":21,"losses":37,"wins":32},"claude-fable-5-1":{"draws":6,"losses":85,"wins":17},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":29,"losses":21,"wins":60},"claude-opus-4-8":{"draws":15,"losses":13,"wins":26},"claude-opus-5":{"draws":14,"losses":77,"wins":15},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":28,"losses":8,"wins":50},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":32,"losses":8,"wins":60},"deepseek/deepseek-v4-pro":{"draws":21,"losses":16,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":10,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"fireworks/ember-1":{"draws":14,"losses":7,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":25,"losses":10,"wins":65},"google/gemini-3.5-flash-lite":{"draws":49,"losses":11,"wins":74},"google/gemini-3.6-flash":{"draws":37,"losses":41,"wins":68},"google/gemini-3.8-flash":{"draws":21,"losses":26,"wins":41},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":17},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":19,"losses":7,"wins":18},"gpt-5.4":{"draws":24,"losses":30,"wins":30},"gpt-5.4-mini":{"draws":13,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":33},"gpt-5.5":{"draws":14,"losses":11,"wins":21},"gpt-5.6-luna":{"draws":28,"losses":10,"wins":38},"gpt-5.6-sol":{"draws":12,"losses":42,"wins":40},"gpt-5.6-terra":{"draws":27,"losses":12,"wins":41},"gpt-6-astra":{"draws":11,"losses":75,"wins":10},"gpt-6-luna":{"draws":12,"losses":7,"wins":27},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":36},"meta/muse-glimmer-30b":{"draws":29,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":7,"losses":22,"wins":41},"meta/muse-spark-1.3":{"draws":19,"losses":25,"wins":28},"meta/muse-wonder":{"draws":9,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":21},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":14,"losses":1,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":18,"losses":14,"wins":40},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"o3":{"draws":20,"losses":23,"wins":51},"openai/gpt-oss-120b":{"draws":30,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":30,"losses":7,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":22},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":46},"qwen/qwen3.8-27b":{"draws":13,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":18,"losses":15,"wins":21},"qwen/qwen3.8-max":{"draws":21,"losses":20,"wins":43},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"stealth/ox-alpha":{"draws":75,"losses":51,"wins":160},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":24},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":11,"wins":27},"thinkingmachines/inkling":{"draws":23,"losses":6,"wins":35},"thinkingmachines/inkling-small":{"draws":27,"losses":4,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":22,"wins":43},"x-ai/grok-4.6":{"draws":34,"losses":30,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":30,"losses":0,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":12},"z-ai/glm-5.2":{"draws":37,"losses":11,"wins":78},"z-ai/glm-5.3":{"draws":14,"losses":37,"wins":23},"z-ai/glm-5.3-flash":{"draws":28,"losses":35,"wins":27},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":40,"wins":24},"claude-fable-5":{"draws":19,"losses":65,"wins":0},"claude-fable-5-1":{"draws":6,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":16,"losses":28,"wins":4},"claude-opus-4-5":{"draws":52,"losses":102,"wins":26},"claude-opus-4-8":{"draws":16,"losses":45,"wins":5},"claude-opus-5":{"draws":13,"losses":93,"wins":10},"claude-opus-5-5":{"draws":2,"losses":56,"wins":0},"claude-sonnet-5":{"draws":45,"losses":91,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":7},"deepseek/deepseek-v4-flash":{"draws":50,"losses":44,"wins":32},"deepseek/deepseek-v4-pro":{"draws":39,"losses":46,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":38,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":30,"wins":6},"fireworks/ember-1":{"draws":18,"losses":27,"wins":9},"gemini-3.1-pro-preview":{"draws":18,"losses":23,"wins":13},"google/gemini-3.1-flash-lite":{"draws":13,"losses":10,"wins":29},"google/gemini-3.5-flash":{"draws":34,"losses":50,"wins":28},"google/gemini-3.5-flash-lite":{"draws":120,"losses":129,"wins":107},"google/gemini-3.6-flash":{"draws":89,"losses":179,"wins":40},"google/gemini-3.8-flash":{"draws":35,"losses":45,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":10,"wins":11},"gpt-4.1":{"draws":4,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":34,"wins":19},"gpt-5.4":{"draws":33,"losses":75,"wins":26},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":12},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":19},"gpt-5.5":{"draws":24,"losses":36,"wins":10},"gpt-5.6-luna":{"draws":65,"losses":61,"wins":30},"gpt-5.6-sol":{"draws":27,"losses":98,"wins":13},"gpt-5.6-terra":{"draws":30,"losses":49,"wins":13},"gpt-6-astra":{"draws":4,"losses":67,"wins":1},"gpt-6-luna":{"draws":17,"losses":28,"wins":7},"gpt-6-sol":{"draws":4,"losses":45,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":45,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":16,"wins":20},"inclusionai/ling-3.0-flash":{"draws":40,"losses":17,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":40,"wins":66},"meta/muse-glimmer-30b":{"draws":37,"losses":34,"wins":23},"meta/muse-spark-1.2":{"draws":41,"losses":63,"wins":8},"meta/muse-spark-1.3":{"draws":17,"losses":56,"wins":5},"meta/muse-wonder":{"draws":16,"losses":30,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":20,"wins":2},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":53,"losses":71,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":12,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":28,"wins":13},"o3":{"draws":34,"losses":125,"wins":49},"openai/gpt-oss-120b":{"draws":32,"losses":24,"wins":34},"poolside/laguna-s-2.1":{"draws":52,"losses":54,"wins":30},"qwen/qwen3.7-max":{"draws":8,"losses":23,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":13,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":46,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":29,"wins":9},"qwen/qwen3.8-flash":{"draws":24,"losses":27,"wins":13},"qwen/qwen3.8-max":{"draws":28,"losses":42,"wins":18},"qwen/qwen3.8-max-0902":{"draws":15,"losses":34,"wins":3},"stealth/ox-alpha":{"draws":82,"losses":181,"wins":45},"stealth/space-bunny-alpha":{"draws":15,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":9},"tencent/hy4-preview":{"draws":31,"losses":49,"wins":12},"thinkingmachines/inkling":{"draws":17,"losses":25,"wins":26},"thinkingmachines/inkling-small":{"draws":42,"losses":20,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":17,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":43,"losses":76,"wins":17},"x-ai/grok-4.6":{"draws":31,"losses":44,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":32,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":14,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":24,"wins":3},"z-ai/glm-5.2":{"draws":49,"losses":70,"wins":39},"z-ai/glm-5.3":{"draws":20,"losses":49,"wins":7},"z-ai/glm-5.3-flash":{"draws":28,"losses":53,"wins":13},"z-ai/glm-5.3-flashx":{"draws":15,"losses":37,"wins":2}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":32,"wins":21},"claude-fable-5":{"draws":14,"losses":51,"wins":9},"claude-fable-5-1":{"draws":5,"losses":85,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":28,"wins":5},"claude-opus-4-5":{"draws":41,"losses":41,"wins":28},"claude-opus-4-8":{"draws":15,"losses":25,"wins":6},"claude-opus-5":{"draws":11,"losses":72,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":22,"losses":38,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":39,"losses":45,"wins":32},"deepseek/deepseek-v4-pro":{"draws":35,"losses":34,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":40,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":21,"wins":8},"fireworks/ember-1":{"draws":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":16,"wins":17},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":23},"google/gemini-3.5-flash":{"draws":26,"losses":49,"wins":21},"google/gemini-3.5-flash-lite":{"draws":51,"losses":39,"wins":71},"google/gemini-3.6-flash":{"draws":50,"losses":68,"wins":25},"google/gemini-3.8-flash":{"draws":24,"losses":49,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":19,"wins":7},"gpt-5.4":{"draws":23,"losses":43,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":21,"losses":13,"wins":22},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":40,"losses":19,"wins":33},"gpt-5.6-sol":{"draws":12,"losses":61,"wins":10},"gpt-5.6-terra":{"draws":24,"losses":39,"wins":21},"gpt-6-astra":{"draws":8,"losses":66,"wins":0},"gpt-6-luna":{"draws":13,"losses":19,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":10,"wins":25},"inclusionai/ling-3.0-flash":{"draws":19,"losses":8,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":16,"wins":30},"meta/muse-glimmer-30b":{"draws":38,"losses":24,"wins":20},"meta/muse-spark-1.2":{"draws":24,"losses":32,"wins":16},"meta/muse-spark-1.3":{"draws":24,"losses":41,"wins":9},"meta/muse-wonder":{"draws":9,"losses":28,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":23,"losses":4,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":32,"wins":13},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":20},"o3":{"draws":26,"losses":44,"wins":32},"openai/gpt-oss-120b":{"draws":36,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":29,"losses":26,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":34,"wins":16},"qwen/qwen3.8-27b":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-flash":{"draws":31,"losses":14,"wins":15},"qwen/qwen3.8-max":{"draws":44,"losses":38,"wins":45},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":79,"losses":159,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":33,"losses":45,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":34,"losses":15,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":43,"wins":18},"x-ai/grok-4.6":{"draws":32,"losses":41,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":17,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":18,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":4},"z-ai/glm-5.2":{"draws":56,"losses":48,"wins":36},"z-ai/glm-5.3":{"draws":14,"losses":48,"wins":8},"z-ai/glm-5.3-flash":{"draws":36,"losses":38,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":10},"claude-fable-5":{"draws":0,"losses":14,"wins":4},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":0,"losses":20,"wins":10},"claude-opus-4-8":{"draws":0,"losses":15,"wins":3},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":0,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":0,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":0,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":14,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":15,"wins":3},"fireworks/ember-1":{"draws":0,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":0,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":0,"losses":15,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":22},"google/gemini-3.6-flash":{"draws":1,"losses":26,"wins":7},"google/gemini-3.8-flash":{"draws":0,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":13,"wins":3},"gpt-5.4":{"draws":0,"losses":16,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":11,"wins":11},"gpt-5.5":{"draws":0,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":1,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":0,"losses":9,"wins":9},"gpt-6-sol":{"draws":0,"losses":17,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":9,"wins":14},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":14,"wins":4},"meta/muse-wonder":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"mistralai/mistral-large-4-0":{"draws":0,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":10},"o3":{"draws":2,"losses":22,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":14,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":0,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":11,"wins":7},"qwen/qwen3.8-max-0902":{"draws":0,"losses":15,"wins":3},"stealth/ox-alpha":{"draws":0,"losses":40,"wins":12},"stealth/space-bunny-alpha":{"draws":0,"losses":9,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":15,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":17},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":13,"wins":5},"x-ai/grok-4.6":{"draws":0,"losses":14,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":0,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":12,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":15,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":2,"wins":52},"claude-fable-5":{"draws":9,"losses":34,"wins":45},"claude-fable-5-1":{"draws":3,"losses":81,"wins":10},"claude-haiku-5-5":{"draws":10,"losses":12,"wins":20},"claude-opus-4-5":{"draws":46,"losses":37,"wins":87},"claude-opus-4-8":{"draws":17,"losses":23,"wins":22},"claude-opus-5":{"draws":17,"losses":88,"wins":25},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":27,"losses":32,"wins":81},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":15,"losses":17,"wins":70},"deepseek/deepseek-v4-pro":{"draws":23,"losses":17,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":32},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":52},"google/gemini-3.5-flash-lite":{"draws":42,"losses":66,"wins":154},"google/gemini-3.6-flash":{"draws":34,"losses":104,"wins":138},"google/gemini-3.8-flash":{"draws":10,"losses":27,"wins":47},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":19},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":13,"wins":34},"gpt-5.4":{"draws":28,"losses":49,"wins":58},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":14,"losses":20,"wins":24},"gpt-5.6-luna":{"draws":22,"losses":39,"wins":65},"gpt-5.6-sol":{"draws":17,"losses":62,"wins":57},"gpt-5.6-terra":{"draws":20,"losses":12,"wins":58},"gpt-6-astra":{"draws":1,"losses":71,"wins":12},"gpt-6-luna":{"draws":6,"losses":15,"wins":25},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":39},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":52},"meituan/longcat-2.0":{"draws":30,"losses":9,"wins":89},"meta/muse-glimmer-30b":{"draws":12,"losses":12,"wins":42},"meta/muse-spark-1.2":{"draws":17,"losses":20,"wins":63},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":38},"meta/muse-wonder":{"draws":11,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":22,"losses":29,"wins":75},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":39},"o3":{"draws":16,"losses":32,"wins":112},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":50},"poolside/laguna-s-2.1":{"draws":31,"losses":13,"wins":76},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":26,"wins":44},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":29},"qwen/qwen3.8-flash":{"draws":8,"losses":16,"wins":28},"qwen/qwen3.8-max":{"draws":15,"losses":24,"wins":47},"qwen/qwen3.8-max-0902":{"draws":8,"losses":16,"wins":22},"stealth/ox-alpha":{"draws":58,"losses":74,"wins":138},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":35},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":32},"tencent/hy4-preview":{"draws":15,"losses":28,"wins":41},"thinkingmachines/inkling":{"draws":30,"losses":16,"wins":58},"thinkingmachines/inkling-small":{"draws":9,"losses":14,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":33,"losses":18,"wins":39},"x-ai/grok-4.6":{"draws":15,"losses":31,"wins":44},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":26,"losses":22,"wins":80},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":25},"z-ai/glm-5.3-flash":{"draws":11,"losses":31,"wins":36},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":38},"claude-fable-5":{"draws":23,"losses":33,"wins":38},"claude-fable-5-1":{"draws":7,"losses":75,"wins":26},"claude-haiku-5-5":{"draws":13,"losses":13,"wins":18},"claude-opus-4-5":{"draws":23,"losses":24,"wins":57},"claude-opus-4-8":{"draws":10,"losses":18,"wins":22},"claude-opus-5":{"draws":10,"losses":52,"wins":27},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":17,"losses":13,"wins":54},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":25},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":31,"losses":7,"wins":66},"deepseek/deepseek-v4-pro":{"draws":17,"losses":21,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":19,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":13,"wins":27},"fireworks/ember-1":{"draws":12,"losses":12,"wins":24},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":30,"losses":14,"wins":54},"google/gemini-3.5-flash-lite":{"draws":37,"losses":17,"wins":82},"google/gemini-3.6-flash":{"draws":30,"losses":54,"wins":60},"google/gemini-3.8-flash":{"draws":25,"losses":24,"wins":41},"google/gemma-4-31b-it":{"draws":8,"losses":0,"wins":18},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":5,"wins":26},"gpt-5.4":{"draws":27,"losses":26,"wins":37},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":17,"losses":8,"wins":27},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":52},"gpt-5.6-sol":{"draws":15,"losses":30,"wins":49},"gpt-5.6-terra":{"draws":18,"losses":8,"wins":66},"gpt-6-astra":{"draws":9,"losses":71,"wins":16},"gpt-6-luna":{"draws":9,"losses":10,"wins":27},"gpt-6-sol":{"draws":2,"losses":36,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":32},"inclusionai/ling-3.0-flash":{"draws":16,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":19,"losses":3,"wins":50},"meta/muse-glimmer-30b":{"draws":18,"losses":14,"wins":36},"meta/muse-spark-1.2":{"draws":12,"losses":18,"wins":40},"meta/muse-spark-1.3":{"draws":15,"losses":26,"wins":29},"meta/muse-wonder":{"draws":10,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":20,"wins":37},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":20},"o3":{"draws":22,"losses":24,"wins":46},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":40},"poolside/laguna-s-2.1":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":34,"wins":39},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":26},"qwen/qwen3.8-flash":{"draws":22,"losses":8,"wins":26},"qwen/qwen3.8-max":{"draws":12,"losses":32,"wins":44},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":22},"stealth/ox-alpha":{"draws":86,"losses":79,"wins":123},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":16},"tencent/hy4-preview":{"draws":30,"losses":18,"wins":36},"thinkingmachines/inkling":{"draws":23,"losses":5,"wins":34},"thinkingmachines/inkling-small":{"draws":30,"losses":9,"wins":41},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":20,"losses":25,"wins":35},"x-ai/grok-4.6":{"draws":23,"losses":11,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":4,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":82},"z-ai/glm-5.3":{"draws":18,"losses":24,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":32,"wins":34},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":1,"losses":12,"wins":29},"claude-fable-5-1":{"draws":1,"losses":28,"wins":17},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":32},"claude-opus-4-5":{"draws":1,"losses":5,"wins":62},"claude-opus-4-8":{"draws":3,"losses":7,"wins":28},"claude-opus-5":{"draws":4,"losses":30,"wins":36},"claude-opus-5-5":{"draws":0,"losses":32,"wins":14},"claude-sonnet-5":{"draws":0,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"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":2,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":48},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":58},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":20},"gpt-4.1":{"draws":0,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":32},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":43},"gpt-5.5":{"draws":3,"losses":9,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":34},"gpt-6-sol":{"draws":1,"losses":12,"wins":29},"gpt-6.1-sol":{"draws":1,"losses":24,"wins":17},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":34},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":33},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":33},"meta/muse-wonder":{"draws":5,"losses":9,"wins":24},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":17},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":33},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":36},"o3":{"draws":1,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":41},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":28},"stealth/ox-alpha":{"draws":6,"losses":13,"wins":119},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":32},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":40},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":35},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":28},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":72},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":30},"z-ai/glm-5.3-flash":{"draws":2,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":33}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":7,"wins":6},"claude-fable-5":{"draws":10,"losses":20,"wins":0},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":15,"wins":1},"claude-opus-4-5":{"draws":52,"losses":26,"wins":6},"claude-opus-4-8":{"draws":22,"losses":22,"wins":4},"claude-opus-5":{"draws":13,"losses":58,"wins":5},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":16,"losses":11,"wins":3},"claude-sonnet-5-5":{"draws":11,"losses":17,"wins":2},"cohere/north-mini-code":{"draws":8,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":35,"losses":12,"wins":11},"deepseek/deepseek-v4-pro":{"draws":19,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":9,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":1},"fireworks/ember-1":{"draws":17,"losses":8,"wins":5},"gemini-3.1-pro-preview":{"draws":15,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":29,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":22,"losses":14,"wins":6},"google/gemini-3.5-flash-lite":{"draws":36,"losses":14,"wins":10},"google/gemini-3.6-flash":{"draws":30,"losses":22,"wins":8},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":3},"gpt-4.1":{"draws":14,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":34,"losses":11,"wins":7},"gpt-5.4":{"draws":12,"losses":15,"wins":1},"gpt-5.4-mini":{"draws":27,"losses":4,"wins":11},"gpt-5.4-nano":{"draws":27,"losses":24,"wins":11},"gpt-5.5":{"draws":22,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":10,"losses":20,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":30,"wins":0},"gpt-6-luna":{"draws":18,"losses":11,"wins":1},"gpt-6-sol":{"draws":6,"losses":22,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":29,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":26,"losses":11,"wins":7},"meta/muse-glimmer-30b":{"draws":21,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":13,"wins":4},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":0},"meta/muse-wonder":{"draws":9,"losses":13,"wins":4},"minimax/minimax-m3":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":15,"losses":0,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":6,"wins":8},"o3":{"draws":20,"losses":19,"wins":7},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":3},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":2},"qwen/qwen3.7-max":{"draws":22,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":16,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":4,"wins":0},"qwen/qwen3.8-max":{"draws":18,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":17,"losses":7,"wins":4},"stealth/ox-alpha":{"draws":39,"losses":40,"wins":11},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":15,"losses":6,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":35,"losses":5,"wins":10},"thinkingmachines/inkling-small":{"draws":23,"losses":4,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":20,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":51,"losses":28,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":58,"losses":25,"wins":13},"z-ai/glm-5.3":{"draws":11,"losses":19,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":2},"z-ai/glm-5.3-flashx":{"draws":16,"losses":13,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":22,"wins":22},"claude-fable-5":{"draws":20,"losses":42,"wins":14},"claude-fable-5-1":{"draws":6,"losses":73,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":25,"losses":48,"wins":31},"claude-opus-4-8":{"draws":16,"losses":22,"wins":12},"claude-opus-5":{"draws":23,"losses":63,"wins":4},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":18,"losses":37,"wins":35},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":36,"losses":32,"wins":40},"deepseek/deepseek-v4-pro":{"draws":19,"losses":26,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":30,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":11},"fireworks/ember-1":{"draws":13,"losses":19,"wins":16},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":26,"losses":42,"wins":26},"google/gemini-3.5-flash-lite":{"draws":52,"losses":31,"wins":55},"google/gemini-3.6-flash":{"draws":33,"losses":63,"wins":36},"google/gemini-3.8-flash":{"draws":22,"losses":41,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":18,"losses":16,"wins":12},"gpt-5.4":{"draws":25,"losses":44,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":21,"wins":23},"gpt-5.5":{"draws":13,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":25,"losses":19,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":61,"wins":9},"gpt-5.6-terra":{"draws":44,"losses":37,"wins":7},"gpt-6-astra":{"draws":8,"losses":64,"wins":2},"gpt-6-luna":{"draws":18,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":14,"wins":26},"inclusionai/ling-3.0-flash":{"draws":21,"losses":8,"wins":17},"meituan/longcat-2.0":{"draws":19,"losses":24,"wins":22},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":30},"meta/muse-spark-1.2":{"draws":15,"losses":31,"wins":20},"meta/muse-spark-1.3":{"draws":11,"losses":41,"wins":14},"meta/muse-wonder":{"draws":9,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":13},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":18,"losses":10,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":7,"wins":15},"o3":{"draws":18,"losses":49,"wins":31},"openai/gpt-oss-120b":{"draws":26,"losses":12,"wins":38},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":31},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":27,"wins":25},"qwen/qwen3.8-27b":{"draws":12,"losses":13,"wins":19},"qwen/qwen3.8-flash":{"draws":19,"losses":20,"wins":11},"qwen/qwen3.8-max":{"draws":32,"losses":29,"wins":19},"qwen/qwen3.8-max-0902":{"draws":13,"losses":27,"wins":6},"stealth/ox-alpha":{"draws":84,"losses":123,"wins":59},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":9},"tencent/hy4-preview":{"draws":25,"losses":32,"wins":17},"thinkingmachines/inkling":{"draws":22,"losses":19,"wins":31},"thinkingmachines/inkling-small":{"draws":32,"losses":20,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":39,"wins":16},"x-ai/grok-4.6":{"draws":27,"losses":37,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":37,"losses":15,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":35,"wins":34},"z-ai/glm-5.3":{"draws":19,"losses":28,"wins":17},"z-ai/glm-5.3-flash":{"draws":27,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":30},"claude-fable-5":{"draws":4,"losses":4,"wins":28},"claude-fable-5-1":{"draws":2,"losses":31,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":30},"claude-opus-4-5":{"draws":5,"losses":3,"wins":50},"claude-opus-4-8":{"draws":5,"losses":5,"wins":24},"claude-opus-5":{"draws":6,"losses":25,"wins":33},"claude-opus-5-5":{"draws":2,"losses":28,"wins":8},"claude-sonnet-5":{"draws":5,"losses":2,"wins":31},"claude-sonnet-5-5":{"draws":6,"losses":11,"wins":19},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":53},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":33},"fireworks/ember-1":{"draws":3,"losses":2,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":25},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":39},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":67},"google/gemini-3.6-flash":{"draws":8,"losses":6,"wins":50},"google/gemini-3.8-flash":{"draws":7,"losses":5,"wins":26},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":21},"gpt-4.1":{"draws":1,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":31},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":22},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":29},"gpt-5.5":{"draws":3,"losses":3,"wins":26},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":32},"gpt-5.6-sol":{"draws":5,"losses":5,"wins":28},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":27},"gpt-6-astra":{"draws":8,"losses":26,"wins":6},"gpt-6-luna":{"draws":5,"losses":1,"wins":32},"gpt-6-sol":{"draws":7,"losses":17,"wins":14},"gpt-6.1-sol":{"draws":8,"losses":22,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":38},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":25},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":28},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":25},"meta/muse-wonder":{"draws":5,"losses":8,"wins":29},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":15},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":27},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":32},"o3":{"draws":1,"losses":1,"wins":50},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":32},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":17},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":36},"qwen/qwen3.8-27b":{"draws":3,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":21},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":32},"qwen/qwen3.8-max-0902":{"draws":8,"losses":5,"wins":27},"stealth/ox-alpha":{"draws":15,"losses":12,"wins":107},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":25},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":16},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":29},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":32},"x-ai/grok-4.6":{"draws":5,"losses":5,"wins":26},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":4,"wins":16},"z-ai/glm-5.2":{"draws":11,"losses":2,"wins":59},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":17},"z-ai/glm-5.3-flash":{"draws":6,"losses":5,"wins":27},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":29}},"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-haiku-5-5":{"draws":5,"losses":17,"wins":22},"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},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":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},"fireworks/ember-1":{"draws":7,"losses":17,"wins":24},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":22},"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":7,"losses":4,"wins":15},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"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":11,"losses":11,"wins":26},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":11,"wins":26},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"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":7,"losses":24,"wins":39},"meta/muse-spark-1.3":{"draws":12,"losses":22,"wins":40},"meta/muse-wonder":{"draws":5,"losses":22,"wins":17},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"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":14,"losses":20,"wins":34},"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":39},"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":7,"losses":15,"wins":24},"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":11,"losses":12,"wins":23},"stealth/ox-alpha":{"draws":55,"losses":86,"wins":137},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":17,"losses":17,"wins":46},"thinkingmachines/inkling":{"draws":12,"losses":8,"wins":44},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":45},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":34},"x-ai/grok-4.6":{"draws":13,"losses":37,"wins":36},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":15},"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":4,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":32,"wins":69},"z-ai/glm-5.3":{"draws":16,"losses":32,"wins":22},"z-ai/glm-5.3-flash":{"draws":17,"losses":24,"wins":15},"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":6,"losses":7,"wins":31},"claude-fable-5":{"draws":8,"losses":16,"wins":24},"claude-fable-5-1":{"draws":8,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":5,"losses":10,"wins":27},"claude-opus-4-5":{"draws":9,"losses":13,"wins":56},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":19,"wins":22},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"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":9,"losses":9,"wins":30},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":39},"google/gemini-3.5-flash-lite":{"draws":20,"losses":8,"wins":55},"google/gemini-3.6-flash":{"draws":18,"losses":19,"wins":47},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":30},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":5,"wins":26},"gpt-5.4":{"draws":7,"losses":10,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":34},"gpt-5.5":{"draws":10,"losses":12,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":24},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":28},"gpt-6-astra":{"draws":3,"losses":39,"wins":6},"gpt-6-luna":{"draws":7,"losses":8,"wins":31},"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":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":27},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"meituan/longcat-2.0":{"draws":9,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":12,"wins":25},"meta/muse-wonder":{"draws":10,"losses":16,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"mistralai/mistral-large-4-0":{"draws":8,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":8,"wins":30},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"o3":{"draws":3,"losses":13,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":27},"stealth/ox-alpha":{"draws":18,"losses":34,"wins":104},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":42},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":32},"unbiased/pareto-26.10-preview":{"draws":2,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":26},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":20,"losses":15,"wins":61},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":17},"z-ai/glm-5.3-flash":{"draws":12,"losses":14,"wins":22},"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":15,"losses":13,"wins":22},"claude-fable-5":{"draws":11,"losses":35,"wins":16},"claude-fable-5-1":{"draws":2,"losses":62,"wins":4},"claude-haiku-5-5":{"draws":6,"losses":16,"wins":14},"claude-opus-4-5":{"draws":27,"losses":36,"wins":33},"claude-opus-4-8":{"draws":11,"losses":15,"wins":16},"claude-opus-5":{"draws":14,"losses":54,"wins":12},"claude-opus-5-5":{"draws":2,"losses":39,"wins":5},"claude-sonnet-5":{"draws":27,"losses":30,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":29,"losses":29,"wins":34},"deepseek/deepseek-v4-pro":{"draws":24,"losses":27,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":28,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"fireworks/ember-1":{"draws":10,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":9,"losses":7,"wins":16},"google/gemini-3.5-flash":{"draws":20,"losses":28,"wins":26},"google/gemini-3.5-flash-lite":{"draws":41,"losses":35,"wins":58},"google/gemini-3.6-flash":{"draws":30,"losses":56,"wins":38},"google/gemini-3.8-flash":{"draws":15,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":8,"losses":10,"wins":18},"gpt-5.4":{"draws":14,"losses":22,"wins":20},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":13,"wins":26},"gpt-5.5":{"draws":14,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":15,"wins":36},"gpt-5.6-sol":{"draws":13,"losses":43,"wins":12},"gpt-5.6-terra":{"draws":21,"losses":28,"wins":17},"gpt-6-astra":{"draws":5,"losses":41,"wins":10},"gpt-6-luna":{"draws":11,"losses":15,"wins":14},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":20,"wins":14},"inclusionai/ling-3.0-flash":{"draws":12,"losses":7,"wins":19},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":31},"meta/muse-glimmer-30b":{"draws":19,"losses":17,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":20,"wins":24},"meta/muse-spark-1.3":{"draws":14,"losses":28,"wins":14},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":14,"losses":13,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":14,"losses":29,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":17},"o3":{"draws":10,"losses":34,"wins":28},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":27},"poolside/laguna-s-2.1":{"draws":21,"losses":17,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":28,"wins":20},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":14},"qwen/qwen3.8-flash":{"draws":11,"losses":19,"wins":22},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":28},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":53,"losses":108,"wins":63},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":38,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":23,"losses":16,"wins":37},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":17,"losses":32,"wins":9},"x-ai/grok-4.6":{"draws":22,"losses":30,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":39,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":19},"z-ai/glm-5.3-flash":{"draws":14,"losses":33,"wins":19},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":14,"wins":37},"claude-fable-5":{"draws":12,"losses":19,"wins":29},"claude-fable-5-1":{"draws":2,"losses":82,"wins":16},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":24,"losses":13,"wins":71},"claude-opus-4-8":{"draws":13,"losses":8,"wins":25},"claude-opus-5":{"draws":13,"losses":67,"wins":28},"claude-opus-5-5":{"draws":5,"losses":38,"wins":9},"claude-sonnet-5":{"draws":13,"losses":16,"wins":55},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"losses":6,"wins":68},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":20,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":13,"wins":23},"fireworks/ember-1":{"draws":11,"losses":7,"wins":30},"gemini-3.1-pro-preview":{"draws":10,"losses":8,"wins":30},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":53},"google/gemini-3.5-flash-lite":{"draws":24,"losses":26,"wins":76},"google/gemini-3.6-flash":{"draws":19,"losses":52,"wins":63},"google/gemini-3.8-flash":{"draws":9,"losses":25,"wins":52},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":14},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":10,"wins":29},"gpt-5.4":{"draws":21,"losses":23,"wins":44},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":37},"gpt-5.5":{"draws":11,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":20,"losses":13,"wins":39},"gpt-5.6-sol":{"draws":6,"losses":42,"wins":42},"gpt-5.6-terra":{"draws":25,"losses":10,"wins":53},"gpt-6-astra":{"draws":6,"losses":69,"wins":19},"gpt-6-luna":{"draws":12,"losses":7,"wins":27},"gpt-6-sol":{"draws":8,"losses":24,"wins":16},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":27},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":27},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":44},"meta/muse-glimmer-30b":{"draws":10,"losses":10,"wins":36},"meta/muse-spark-1.2":{"draws":15,"losses":15,"wins":34},"meta/muse-spark-1.3":{"draws":16,"losses":21,"wins":31},"meta/muse-wonder":{"draws":9,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":49},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":30},"o3":{"draws":7,"losses":12,"wins":73},"openai/gpt-oss-120b":{"draws":19,"losses":11,"wins":32},"poolside/laguna-s-2.1":{"draws":10,"losses":16,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":18,"wins":37},"qwen/qwen3.8-27b":{"draws":10,"losses":7,"wins":27},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":28,"wins":43},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"stealth/ox-alpha":{"draws":61,"losses":67,"wins":144},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":18},"tencent/hy4-preview":{"draws":16,"losses":12,"wins":50},"thinkingmachines/inkling":{"draws":16,"losses":1,"wins":43},"thinkingmachines/inkling-small":{"draws":14,"losses":15,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":33},"x-ai/grok-4.6":{"draws":24,"losses":36,"wins":30},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":2,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":28,"losses":21,"wins":77},"z-ai/glm-5.3":{"draws":8,"losses":36,"wins":26},"z-ai/glm-5.3-flash":{"draws":16,"losses":22,"wins":46},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":23}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":56},"claude-fable-5":{"draws":7,"losses":17,"wins":66},"claude-fable-5-1":{"draws":5,"losses":47,"wins":24},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":40},"claude-opus-4-5":{"draws":6,"losses":5,"wins":97},"claude-opus-4-8":{"draws":4,"losses":5,"wins":35},"claude-opus-5":{"draws":10,"losses":40,"wins":38},"claude-opus-5-5":{"draws":6,"losses":35,"wins":11},"claude-sonnet-5":{"draws":6,"losses":4,"wins":76},"claude-sonnet-5-5":{"draws":3,"losses":10,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":9,"losses":1,"wins":88},"deepseek/deepseek-v4-pro":{"draws":6,"losses":2,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"fireworks/ember-1":{"draws":0,"losses":5,"wins":43},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":42},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":7,"losses":7,"wins":80},"google/gemini-3.5-flash-lite":{"draws":14,"losses":0,"wins":104},"google/gemini-3.6-flash":{"draws":11,"losses":19,"wins":102},"google/gemini-3.8-flash":{"draws":8,"losses":9,"wins":73},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":23},"gpt-4.1":{"draws":0,"losses":2,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":0,"wins":38},"gpt-5.4":{"draws":11,"losses":11,"wins":62},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":3,"losses":9,"wins":36},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":56},"gpt-5.6-sol":{"draws":9,"losses":16,"wins":69},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":66},"gpt-6-astra":{"draws":9,"losses":70,"wins":17},"gpt-6-luna":{"draws":5,"losses":4,"wins":37},"gpt-6-sol":{"draws":6,"losses":12,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":29,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":38},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":33},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":55},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":45},"meta/muse-spark-1.2":{"draws":7,"losses":4,"wins":55},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":53},"meta/muse-wonder":{"draws":3,"losses":14,"wins":31},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":58},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"o3":{"draws":3,"losses":7,"wins":80},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":50},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":51},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":10,"wins":70},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":41},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":45},"qwen/qwen3.8-max":{"draws":5,"losses":3,"wins":72},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":37},"stealth/ox-alpha":{"draws":19,"losses":25,"wins":238},"stealth/space-bunny-alpha":{"draws":1,"losses":2,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":12,"wins":65},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":54},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":60},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":60},"x-ai/grok-4.6":{"draws":6,"losses":19,"wins":67},"x-ai/grok-4.7":{"draws":1,"losses":17,"wins":24},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":24},"z-ai/glm-5.2":{"draws":13,"losses":4,"wins":101},"z-ai/glm-5.3":{"draws":6,"losses":15,"wins":53},"z-ai/glm-5.3-flash":{"draws":4,"losses":14,"wins":66},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":36}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":26},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":12,"wins":9},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":15,"losses":56,"wins":11},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":6,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":11,"wins":20},"fireworks/ember-1":{"draws":14,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":21,"losses":30,"wins":33},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":24},"gpt-5.5":{"draws":19,"losses":10,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":17,"losses":11,"wins":20},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":37},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":18},"meta/muse-wonder":{"draws":8,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":23},"o3":{"draws":13,"losses":14,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":8,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"qwen/qwen3.8-max-0902":{"draws":15,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":36,"losses":59,"wins":61},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":17},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":39},"thinkingmachines/inkling-small":{"draws":9,"losses":5,"wins":34},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":11},"z-ai/glm-5.2":{"draws":24,"losses":21,"wins":51},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":16,"wins":20}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":16,"wins":42},"claude-fable-5":{"draws":12,"losses":60,"wins":10},"claude-fable-5-1":{"draws":5,"losses":94,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":13},"claude-opus-4-5":{"draws":32,"losses":28,"wins":52},"claude-opus-4-8":{"draws":20,"losses":26,"wins":22},"claude-opus-5":{"draws":24,"losses":90,"wins":20},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":31,"losses":29,"wins":72},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":22},"deepseek/deepseek-v4-flash":{"draws":25,"losses":23,"wins":60},"deepseek/deepseek-v4-pro":{"draws":13,"losses":28,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":29,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"fireworks/ember-1":{"draws":16,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":34},"google/gemini-3.5-flash":{"draws":25,"losses":42,"wins":33},"google/gemini-3.5-flash-lite":{"draws":69,"losses":48,"wins":141},"google/gemini-3.6-flash":{"draws":57,"losses":106,"wins":87},"google/gemini-3.8-flash":{"draws":20,"losses":46,"wins":26},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":15},"gpt-4.1":{"draws":7,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":19,"wins":24},"gpt-5.4":{"draws":28,"losses":64,"wins":26},"gpt-5.4-mini":{"draws":18,"losses":11,"wins":21},"gpt-5.4-nano":{"draws":19,"losses":18,"wins":45},"gpt-5.5":{"draws":31,"losses":27,"wins":14},"gpt-5.6-luna":{"draws":42,"losses":33,"wins":49},"gpt-5.6-sol":{"draws":21,"losses":86,"wins":25},"gpt-5.6-terra":{"draws":24,"losses":22,"wins":32},"gpt-6-astra":{"draws":12,"losses":72,"wins":6},"gpt-6-luna":{"draws":16,"losses":11,"wins":21},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":34},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":41},"meituan/longcat-2.0":{"draws":26,"losses":17,"wins":67},"meta/muse-glimmer-30b":{"draws":17,"losses":14,"wins":37},"meta/muse-spark-1.2":{"draws":24,"losses":46,"wins":28},"meta/muse-spark-1.3":{"draws":12,"losses":36,"wins":24},"meta/muse-wonder":{"draws":11,"losses":24,"wins":11},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":26},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k3":{"draws":45,"losses":37,"wins":36},"nex-agi/nex-n2-pro":{"draws":10,"losses":2,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":26},"o3":{"draws":18,"losses":57,"wins":107},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":44},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":59},"qwen/qwen3.7-max":{"draws":13,"losses":8,"wins":25},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":32,"wins":26},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":15},"qwen/qwen3.8-flash":{"draws":18,"losses":13,"wins":23},"qwen/qwen3.8-max":{"draws":20,"losses":42,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":15},"stealth/ox-alpha":{"draws":83,"losses":103,"wins":87},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":40,"wins":25},"thinkingmachines/inkling":{"draws":21,"losses":20,"wins":53},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":59},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":42,"losses":57,"wins":43},"x-ai/grok-4.6":{"draws":22,"losses":44,"wins":18},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":10},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":18},"xiaomi/mimo-v2.5":{"draws":39,"losses":17,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":16,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":13,"wins":6},"z-ai/glm-5.2":{"draws":43,"losses":35,"wins":56},"z-ai/glm-5.3":{"draws":20,"losses":32,"wins":14},"z-ai/glm-5.3-flash":{"draws":20,"losses":42,"wins":26},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":7,"wins":20},"claude-fable-5":{"draws":16,"losses":28,"wins":10},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":16},"claude-opus-4-5":{"draws":41,"losses":42,"wins":47},"claude-opus-4-8":{"draws":13,"losses":33,"wins":14},"claude-opus-5":{"draws":19,"losses":102,"wins":7},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":18,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":13,"losses":6,"wins":19},"deepseek/deepseek-v4-flash":{"draws":37,"losses":13,"wins":36},"deepseek/deepseek-v4-pro":{"draws":19,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":18,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":19,"wins":11},"fireworks/ember-1":{"draws":19,"losses":16,"wins":13},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":22,"losses":3,"wins":39},"google/gemini-3.5-flash":{"draws":25,"losses":18,"wins":23},"google/gemini-3.5-flash-lite":{"draws":44,"losses":10,"wins":50},"google/gemini-3.6-flash":{"draws":36,"losses":47,"wins":31},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":13},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":13},"gpt-4.1":{"draws":16,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":27,"losses":20,"wins":29},"gpt-5.4":{"draws":16,"losses":18,"wins":14},"gpt-5.4-mini":{"draws":25,"losses":21,"wins":16},"gpt-5.4-nano":{"draws":26,"losses":27,"wins":41},"gpt-5.5":{"draws":34,"losses":26,"wins":20},"gpt-5.6-luna":{"draws":21,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":14,"losses":31,"wins":13},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":16},"gpt-6-astra":{"draws":1,"losses":48,"wins":3},"gpt-6-luna":{"draws":15,"losses":16,"wins":15},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":45,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":17},"inclusionai/ling-3.0-flash":{"draws":31,"losses":0,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":19,"wins":30},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":19},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":18},"meta/muse-wonder":{"draws":11,"losses":24,"wins":11},"minimax/minimax-m3":{"draws":20,"losses":11,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":8},"moonshotai/kimi-k3":{"draws":18,"losses":19,"wins":15},"nex-agi/nex-n2-pro":{"draws":27,"losses":0,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":13,"wins":26},"o3":{"draws":22,"losses":20,"wins":42},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":36,"losses":10,"wins":34},"qwen/qwen3.7-max":{"draws":30,"losses":9,"wins":21},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":23,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":20,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":17,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":17,"wins":15},"stealth/ox-alpha":{"draws":48,"losses":73,"wins":47},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":9},"tencent/hy4-preview":{"draws":19,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":23,"losses":3,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":29,"wins":21},"x-ai/grok-4.6":{"draws":19,"losses":22,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":21},"xiaomi/mimo-v2.5":{"draws":60,"losses":13,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":9,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":63,"losses":29,"wins":58},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":17},"z-ai/glm-5.3-flashx":{"draws":11,"losses":22,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":59},"claude-fable-5":{"draws":9,"losses":27,"wins":62},"claude-fable-5-1":{"draws":6,"losses":69,"wins":21},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":49},"claude-opus-4-5":{"draws":45,"losses":18,"wins":195},"claude-opus-4-8":{"draws":29,"losses":27,"wins":88},"claude-opus-5":{"draws":43,"losses":161,"wins":130},"claude-opus-5-5":{"draws":6,"losses":61,"wins":25},"claude-sonnet-5":{"draws":13,"losses":11,"wins":66},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":45},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":32},"deepseek/deepseek-v4-flash":{"draws":17,"losses":2,"wins":129},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":16,"wins":56},"fireworks/ember-1":{"draws":9,"losses":15,"wins":60},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":61},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":58},"google/gemini-3.5-flash":{"draws":18,"losses":7,"wins":97},"google/gemini-3.5-flash-lite":{"draws":34,"losses":14,"wins":138},"google/gemini-3.6-flash":{"draws":19,"losses":36,"wins":149},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":74},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":31},"gpt-4.1":{"draws":4,"losses":5,"wins":47},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":9,"wins":105},"gpt-5.4":{"draws":10,"losses":15,"wins":57},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":71},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":102},"gpt-5.5":{"draws":19,"losses":49,"wins":96},"gpt-5.6-luna":{"draws":9,"losses":13,"wins":66},"gpt-5.6-sol":{"draws":17,"losses":21,"wins":60},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":62},"gpt-6-astra":{"draws":6,"losses":61,"wins":19},"gpt-6-luna":{"draws":16,"losses":7,"wins":59},"gpt-6-sol":{"draws":12,"losses":32,"wins":40},"gpt-6.1-sol":{"draws":6,"losses":49,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":40},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":58},"meituan/longcat-2.0":{"draws":16,"losses":16,"wins":104},"meta/muse-glimmer-30b":{"draws":4,"losses":10,"wins":66},"meta/muse-spark-1.2":{"draws":12,"losses":15,"wins":59},"meta/muse-spark-1.3":{"draws":10,"losses":20,"wins":58},"meta/muse-wonder":{"draws":9,"losses":32,"wins":37},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":59},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":32},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":44},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":80},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":1,"wins":97},"o3":{"draws":9,"losses":10,"wins":117},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":70},"poolside/laguna-s-2.1":{"draws":9,"losses":8,"wins":119},"qwen/qwen3.7-max":{"draws":16,"losses":9,"wins":77},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":13,"wins":65},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":40},"qwen/qwen3.8-flash":{"draws":12,"losses":5,"wins":49},"qwen/qwen3.8-max":{"draws":13,"losses":5,"wins":70},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":54},"stealth/ox-alpha":{"draws":40,"losses":34,"wins":229},"stealth/space-bunny-alpha":{"draws":14,"losses":4,"wins":50},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":55},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":11,"wins":59},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":69},"thinkingmachines/inkling":{"draws":25,"losses":6,"wins":93},"thinkingmachines/inkling-small":{"draws":15,"losses":4,"wins":65},"unbiased/pareto-26.10-preview":{"draws":2,"losses":16,"wins":8},"upstage/solar-mini4":{"draws":4,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":17,"losses":28,"wins":85},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":56},"x-ai/grok-4.7":{"draws":7,"losses":41,"wins":28},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":28},"xiaomi/mimo-v2.5":{"draws":45,"losses":13,"wins":142},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":1,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":31},"z-ai/glm-5.2":{"draws":35,"losses":18,"wins":179},"z-ai/glm-5.3":{"draws":12,"losses":21,"wins":47},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":69},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":59}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":3,"wins":48},"claude-fable-5-1":{"draws":5,"losses":18,"wins":37},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":46},"claude-opus-4-5":{"draws":4,"losses":0,"wins":84},"claude-opus-4-8":{"draws":2,"losses":1,"wins":47},"claude-opus-5":{"draws":4,"losses":19,"wins":71},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":1,"wins":53},"claude-sonnet-5-5":{"draws":5,"losses":8,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":79},"deepseek/deepseek-v4-pro":{"draws":3,"losses":0,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"fireworks/ember-1":{"draws":0,"losses":0,"wins":54},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":49},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":36},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":67},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":93},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":84},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":48},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":26},"gpt-4.1":{"draws":0,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":47},"gpt-5.4":{"draws":1,"losses":3,"wins":48},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":55},"gpt-5.5":{"draws":4,"losses":0,"wins":46},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":50},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":47},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":50},"gpt-6-astra":{"draws":5,"losses":25,"wins":24},"gpt-6-luna":{"draws":2,"losses":0,"wins":48},"gpt-6-sol":{"draws":3,"losses":12,"wins":39},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":38},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":36},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":57},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":48},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":51},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":50},"meta/muse-wonder":{"draws":2,"losses":7,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":30},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":25},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":47},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":50},"o3":{"draws":2,"losses":1,"wins":71},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":48},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":0,"wins":53},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":34},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":46},"stealth/ox-alpha":{"draws":8,"losses":5,"wins":159},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":41},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":28},"tencent/hy4-preview":{"draws":1,"losses":4,"wins":47},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":58},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":10},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":49},"x-ai/grok-4.6":{"draws":2,"losses":1,"wins":51},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":32},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":108},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":41},"z-ai/glm-5.3-flash":{"draws":4,"losses":4,"wins":46},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":50}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":10,"wins":44},"claude-fable-5":{"draws":17,"losses":61,"wins":10},"claude-fable-5-1":{"draws":5,"losses":95,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":42,"losses":62,"wins":34},"claude-opus-4-8":{"draws":13,"losses":21,"wins":10},"claude-opus-5":{"draws":13,"losses":60,"wins":13},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":26,"losses":41,"wins":21},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":38,"losses":20,"wins":58},"deepseek/deepseek-v4-pro":{"draws":32,"losses":28,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":35,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":16,"wins":13},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":34,"losses":39,"wins":27},"google/gemini-3.5-flash-lite":{"draws":80,"losses":62,"wins":102},"google/gemini-3.6-flash":{"draws":73,"losses":98,"wins":47},"google/gemini-3.8-flash":{"draws":26,"losses":45,"wins":13},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":10,"wins":19},"gpt-5.4":{"draws":41,"losses":72,"wins":21},"gpt-5.4-mini":{"draws":18,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":18,"wins":22},"gpt-5.5":{"draws":21,"losses":21,"wins":4},"gpt-5.6-luna":{"draws":47,"losses":34,"wins":59},"gpt-5.6-sol":{"draws":20,"losses":110,"wins":21},"gpt-5.6-terra":{"draws":39,"losses":24,"wins":15},"gpt-6-astra":{"draws":5,"losses":83,"wins":4},"gpt-6-luna":{"draws":12,"losses":17,"wins":17},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":8,"wins":30},"inclusionai/ling-3.0-flash":{"draws":23,"losses":6,"wins":31},"meituan/longcat-2.0":{"draws":40,"losses":14,"wins":46},"meta/muse-glimmer-30b":{"draws":36,"losses":10,"wins":36},"meta/muse-spark-1.2":{"draws":29,"losses":43,"wins":26},"meta/muse-spark-1.3":{"draws":22,"losses":34,"wins":16},"meta/muse-wonder":{"draws":9,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":40,"losses":47,"wins":17},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":7,"wins":19},"o3":{"draws":24,"losses":70,"wins":46},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":42},"poolside/laguna-s-2.1":{"draws":44,"losses":13,"wins":37},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":35,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":22,"wins":9},"qwen/qwen3.8-flash":{"draws":26,"losses":18,"wins":18},"qwen/qwen3.8-max":{"draws":34,"losses":36,"wins":23},"qwen/qwen3.8-max-0902":{"draws":15,"losses":22,"wins":9},"stealth/ox-alpha":{"draws":71,"losses":166,"wins":63},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"tencent/hy3-preview":{"draws":13,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":37,"losses":41,"wins":12},"thinkingmachines/inkling":{"draws":30,"losses":11,"wins":51},"thinkingmachines/inkling-small":{"draws":33,"losses":14,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":28,"losses":56,"wins":26},"x-ai/grok-4.6":{"draws":25,"losses":47,"wins":18},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":51,"losses":42,"wins":53},"z-ai/glm-5.3":{"draws":13,"losses":50,"wins":5},"z-ai/glm-5.3-flash":{"draws":27,"losses":47,"wins":16},"z-ai/glm-5.3-flashx":{"draws":15,"losses":26,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":11,"losses":28,"wins":9},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":14},"claude-opus-4-5":{"draws":22,"losses":21,"wins":35},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":8,"losses":61,"wins":13},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":21,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"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":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":12,"losses":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":24,"losses":17,"wins":43},"google/gemini-3.6-flash":{"draws":20,"losses":36,"wins":28},"google/gemini-3.8-flash":{"draws":6,"losses":24,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":13},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":3,"wins":34},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":16,"losses":13,"wins":17},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":16,"wins":17},"gpt-6-sol":{"draws":4,"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":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":12,"wins":30},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":13,"wins":17},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":14},"meta/muse-wonder":{"draws":11,"losses":21,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":14},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":24},"o3":{"draws":7,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":23},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":15},"stealth/ox-alpha":{"draws":33,"losses":68,"wins":55},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":16,"losses":14,"wins":24},"thinkingmachines/inkling-small":{"draws":17,"losses":5,"wins":26},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":8,"losses":26,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":22,"wins":45},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":15,"wins":12},"claude-fable-5":{"draws":6,"losses":32,"wins":2},"claude-fable-5-1":{"draws":0,"losses":42,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":7},"claude-opus-4-5":{"draws":13,"losses":58,"wins":13},"claude-opus-4-8":{"draws":15,"losses":35,"wins":6},"claude-opus-5":{"draws":9,"losses":59,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":6,"losses":24,"wins":10},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":24,"losses":23,"wins":27},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":6},"fireworks/ember-1":{"draws":8,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":19,"losses":21,"wins":20},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":10},"google/gemini-3.5-flash-lite":{"draws":36,"losses":29,"wins":27},"google/gemini-3.6-flash":{"draws":28,"losses":52,"wins":10},"google/gemini-3.8-flash":{"draws":7,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":5},"gpt-4.1":{"draws":9,"losses":13,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":39,"wins":10},"gpt-5.4":{"draws":8,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":15,"losses":22,"wins":9},"gpt-5.4-nano":{"draws":19,"losses":36,"wins":15},"gpt-5.5":{"draws":21,"losses":31,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":20,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":24,"wins":8},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":20,"wins":6},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":20,"losses":20,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":36,"wins":15},"meta/muse-glimmer-30b":{"draws":16,"losses":11,"wins":9},"meta/muse-spark-1.2":{"draws":3,"losses":25,"wins":12},"meta/muse-spark-1.3":{"draws":2,"losses":34,"wins":2},"meta/muse-wonder":{"draws":3,"losses":27,"wins":4},"minimax/minimax-m3":{"draws":9,"losses":18,"wins":17},"mistralai/mistral-large-4-0":{"draws":4,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":11},"nex-agi/nex-n2-pro":{"draws":19,"losses":19,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":16,"wins":23},"o3":{"draws":16,"losses":43,"wins":17},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":10},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":26},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":29,"wins":3},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":5,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":28,"losses":81,"wins":21},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":15,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":15,"wins":8},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":19},"thinkingmachines/inkling-small":{"draws":15,"losses":15,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":36,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":10,"losses":15,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":28,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":17,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":42,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":27,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":48,"losses":62,"wins":54},"claude-fable-5":{"draws":31,"losses":128,"wins":9},"claude-fable-5-1":{"draws":5,"losses":174,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":69,"wins":20},"claude-opus-4-5":{"draws":90,"losses":143,"wins":53},"claude-opus-4-8":{"draws":46,"losses":98,"wins":16},"claude-opus-5":{"draws":29,"losses":243,"wins":14},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":55,"losses":96,"wins":35},"claude-sonnet-5-5":{"draws":28,"losses":86,"wins":18},"cohere/north-mini-code":{"draws":17,"losses":28,"wins":21},"deepseek/deepseek-v4-flash":{"draws":73,"losses":77,"wins":76},"deepseek/deepseek-v4-pro":{"draws":44,"losses":82,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":59,"losses":77,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":74,"wins":15},"fireworks/ember-1":{"draws":41,"losses":73,"wins":18},"gemini-3.1-pro-preview":{"draws":39,"losses":64,"wins":29},"google/gemini-3.1-flash-lite":{"draws":42,"losses":50,"wins":78},"google/gemini-3.5-flash":{"draws":53,"losses":120,"wins":41},"google/gemini-3.5-flash-lite":{"draws":100,"losses":93,"wins":113},"google/gemini-3.6-flash":{"draws":86,"losses":178,"wins":56},"google/gemini-3.8-flash":{"draws":36,"losses":113,"wins":19},"google/gemma-4-31b-it":{"draws":24,"losses":17,"wins":25},"gpt-4.1":{"draws":32,"losses":32,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":63,"losses":66,"wins":29},"gpt-5.4":{"draws":53,"losses":99,"wins":16},"gpt-5.4-mini":{"draws":58,"losses":50,"wins":36},"gpt-5.4-nano":{"draws":51,"losses":71,"wins":78},"gpt-5.5":{"draws":74,"losses":79,"wins":13},"gpt-5.6-luna":{"draws":68,"losses":67,"wins":37},"gpt-5.6-sol":{"draws":22,"losses":140,"wins":10},"gpt-5.6-terra":{"draws":60,"losses":92,"wins":24},"gpt-6-astra":{"draws":4,"losses":156,"wins":4},"gpt-6-luna":{"draws":35,"losses":69,"wins":24},"gpt-6-sol":{"draws":18,"losses":105,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":122,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":53,"losses":23,"wins":50},"inclusionai/ling-3.0-flash":{"draws":66,"losses":34,"wins":54},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":62,"losses":68,"wins":78},"meta/muse-glimmer-30b":{"draws":62,"losses":30,"wins":56},"meta/muse-spark-1.2":{"draws":39,"losses":83,"wins":26},"meta/muse-spark-1.3":{"draws":30,"losses":100,"wins":26},"meta/muse-wonder":{"draws":22,"losses":90,"wins":16},"minimax/minimax-m3":{"draws":39,"losses":41,"wins":44},"mistralai/mistral-large-4-0":{"draws":19,"losses":40,"wins":11},"mistralai/mistral-medium-3-5":{"draws":40,"losses":22,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":23,"wins":14},"moonshotai/kimi-k3":{"draws":44,"losses":83,"wins":27},"nex-agi/nex-n2-pro":{"draws":30,"losses":41,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":79,"losses":47,"wins":60},"o3":{"draws":34,"losses":147,"wins":61},"openai/gpt-oss-120b":{"draws":59,"losses":39,"wins":54},"poolside/laguna-s-2.1":{"draws":80,"losses":56,"wins":58},"qwen/qwen3.7-max":{"draws":49,"losses":40,"wins":29},"qwen/qwen3.7-plus":{"draws":34,"losses":41,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":97,"wins":26},"qwen/qwen3.8-27b":{"draws":25,"losses":56,"wins":27},"qwen/qwen3.8-flash":{"draws":40,"losses":45,"wins":27},"qwen/qwen3.8-max":{"draws":60,"losses":83,"wins":31},"qwen/qwen3.8-max-0902":{"draws":34,"losses":77,"wins":15},"stealth/ox-alpha":{"draws":143,"losses":309,"wins":85},"stealth/space-bunny-alpha":{"draws":36,"losses":51,"wins":17},"stepfun/step-3.7-flash":{"draws":29,"losses":46,"wins":39},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":39,"losses":44,"wins":33},"tencent/hy4-preview":{"draws":46,"losses":88,"wins":26},"thinkingmachines/inkling":{"draws":59,"losses":72,"wins":69},"thinkingmachines/inkling-small":{"draws":74,"losses":36,"wins":70},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":31,"losses":125,"wins":26},"x-ai/grok-4.6":{"draws":52,"losses":108,"wins":14},"x-ai/grok-4.7":{"draws":12,"losses":98,"wins":8},"x-ai/grok-build-0.1":{"draws":29,"losses":19,"wins":28},"xiaomi/mimo-v2.5":{"draws":124,"losses":125,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":37,"losses":48,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":52,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":60,"wins":12},"z-ai/glm-5.2":{"draws":128,"losses":156,"wins":80},"z-ai/glm-5.3":{"draws":37,"losses":101,"wins":8},"z-ai/glm-5.3-flash":{"draws":43,"losses":92,"wins":27},"z-ai/glm-5.3-flashx":{"draws":34,"losses":78,"wins":20}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":16,"wins":51},"claude-fable-5":{"draws":16,"losses":47,"wins":29},"claude-fable-5-1":{"draws":6,"losses":86,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":17,"wins":16},"claude-opus-4-5":{"draws":23,"losses":27,"wins":54},"claude-opus-4-8":{"draws":12,"losses":18,"wins":18},"claude-opus-5":{"draws":9,"losses":62,"wins":15},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":27,"losses":23,"wins":40},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":29,"wins":54},"deepseek/deepseek-v4-pro":{"draws":14,"losses":18,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":29,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"wins":17},"fireworks/ember-1":{"draws":12,"losses":19,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":23,"losses":42,"wins":35},"google/gemini-3.5-flash-lite":{"draws":27,"losses":42,"wins":85},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":73},"google/gemini-3.8-flash":{"draws":11,"losses":49,"wins":26},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":23},"gpt-5.4":{"draws":11,"losses":45,"wins":32},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":28},"gpt-5.5":{"draws":8,"losses":21,"wins":17},"gpt-5.6-luna":{"draws":26,"losses":21,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":53,"wins":26},"gpt-5.6-terra":{"draws":18,"losses":26,"wins":44},"gpt-6-astra":{"draws":4,"losses":64,"wins":16},"gpt-6-luna":{"draws":10,"losses":20,"wins":18},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":3,"wins":37},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":5,"wins":50},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":38},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":33},"meta/muse-spark-1.3":{"draws":7,"losses":35,"wins":28},"meta/muse-wonder":{"draws":7,"losses":28,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":29,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":25},"o3":{"draws":8,"losses":38,"wins":54},"openai/gpt-oss-120b":{"draws":19,"losses":12,"wins":41},"poolside/laguna-s-2.1":{"draws":15,"losses":13,"wins":42},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":19},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":25},"qwen/qwen3.8-27b":{"draws":10,"losses":10,"wins":26},"qwen/qwen3.8-flash":{"draws":13,"losses":25,"wins":20},"qwen/qwen3.8-max":{"draws":22,"losses":37,"wins":31},"qwen/qwen3.8-max-0902":{"draws":11,"losses":23,"wins":12},"stealth/ox-alpha":{"draws":70,"losses":106,"wins":104},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":21},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":18,"losses":35,"wins":31},"thinkingmachines/inkling":{"draws":22,"losses":10,"wins":40},"thinkingmachines/inkling-small":{"draws":26,"losses":12,"wins":50},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":35,"wins":25},"x-ai/grok-4.6":{"draws":12,"losses":48,"wins":30},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":22,"losses":9,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":37,"losses":31,"wins":64},"z-ai/glm-5.3":{"draws":12,"losses":41,"wins":21},"z-ai/glm-5.3-flash":{"draws":10,"losses":39,"wins":31},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":35},"claude-fable-5":{"draws":9,"losses":56,"wins":17},"claude-fable-5-1":{"draws":2,"losses":90,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":24,"wins":11},"claude-opus-4-5":{"draws":32,"losses":34,"wins":38},"claude-opus-4-8":{"draws":11,"losses":19,"wins":18},"claude-opus-5":{"draws":11,"losses":66,"wins":11},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":27,"losses":21,"wins":38},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":35,"losses":36,"wins":45},"deepseek/deepseek-v4-pro":{"draws":21,"losses":33,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":36,"losses":42,"wins":26},"google/gemini-3.5-flash-lite":{"draws":50,"losses":29,"wins":71},"google/gemini-3.6-flash":{"draws":40,"losses":74,"wins":32},"google/gemini-3.8-flash":{"draws":26,"losses":35,"wins":19},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":17,"wins":14},"gpt-5.4":{"draws":18,"losses":40,"wins":20},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":17},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":25},"gpt-5.5":{"draws":14,"losses":15,"wins":17},"gpt-5.6-luna":{"draws":28,"losses":37,"wins":23},"gpt-5.6-sol":{"draws":15,"losses":56,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":40,"wins":26},"gpt-6-astra":{"draws":3,"losses":79,"wins":0},"gpt-6-luna":{"draws":14,"losses":19,"wins":13},"gpt-6-sol":{"draws":5,"losses":35,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":12,"wins":32},"inclusionai/ling-3.0-flash":{"draws":21,"losses":6,"wins":15},"meituan/longcat-2.0":{"draws":28,"losses":17,"wins":31},"meta/muse-glimmer-30b":{"draws":28,"losses":12,"wins":40},"meta/muse-spark-1.2":{"draws":22,"losses":31,"wins":19},"meta/muse-spark-1.3":{"draws":17,"losses":34,"wins":21},"meta/muse-wonder":{"draws":13,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":24},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":20,"losses":32,"wins":20},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":23},"o3":{"draws":15,"losses":38,"wins":45},"openai/gpt-oss-120b":{"draws":17,"losses":18,"wins":33},"poolside/laguna-s-2.1":{"draws":20,"losses":23,"wins":29},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":28,"wins":25},"qwen/qwen3.8-27b":{"draws":14,"losses":17,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":20,"wins":13},"qwen/qwen3.8-max":{"draws":40,"losses":31,"wins":17},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":74,"losses":118,"wins":88},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":12,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":22,"losses":35,"wins":23},"thinkingmachines/inkling":{"draws":22,"losses":19,"wins":31},"thinkingmachines/inkling-small":{"draws":24,"losses":16,"wins":50},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":21,"losses":35,"wins":28},"x-ai/grok-4.6":{"draws":24,"losses":44,"wins":22},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":13,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":55,"losses":36,"wins":47},"z-ai/glm-5.3":{"draws":22,"losses":30,"wins":16},"z-ai/glm-5.3-flash":{"draws":15,"losses":44,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":6,"wins":22},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":8,"losses":41,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":16,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":11,"losses":11,"wins":22},"claude-opus-5":{"draws":17,"losses":52,"wins":13},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":11,"losses":15,"wins":22},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":29,"losses":6,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":13,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":10,"wins":17},"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":12,"wins":20},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":22,"losses":15,"wins":23},"google/gemini-3.5-flash-lite":{"draws":38,"losses":7,"wins":39},"google/gemini-3.6-flash":{"draws":25,"losses":32,"wins":27},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":14,"losses":3,"wins":11},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":16,"losses":9,"wins":17},"gpt-5.4":{"draws":17,"losses":15,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":10,"wins":20},"gpt-5.5":{"draws":14,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":22,"losses":6,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":6,"losses":37,"wins":3},"gpt-6-luna":{"draws":16,"losses":8,"wins":22},"gpt-6-sol":{"draws":9,"losses":27,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":13},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":28},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":11,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":16,"wins":18},"meta/muse-wonder":{"draws":16,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"o3":{"draws":15,"losses":16,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":22,"losses":5,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":17},"stealth/ox-alpha":{"draws":37,"losses":57,"wins":62},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":21},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":10,"wins":24},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":6,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":10},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":19},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":5,"wins":25},"claude-fable-5":{"draws":14,"losses":29,"wins":5},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":25,"wins":6},"claude-opus-4-5":{"draws":30,"losses":21,"wins":27},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":10,"wins":37},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"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":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":19,"losses":17,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":9,"wins":41},"google/gemini-3.6-flash":{"draws":28,"losses":25,"wins":31},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":14},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":9,"wins":21},"gpt-5.4":{"draws":14,"losses":20,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":15,"losses":9,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":14,"losses":11,"wins":21},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":19},"meituan/longcat-2.0":{"draws":14,"losses":5,"wins":32},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":19},"meta/muse-spark-1.3":{"draws":19,"losses":16,"wins":11},"meta/muse-wonder":{"draws":9,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":17},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":19},"o3":{"draws":12,"losses":18,"wins":34},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":7,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":17,"losses":11,"wins":20},"qwen/qwen3.8-max-0902":{"draws":19,"losses":18,"wins":11},"stealth/ox-alpha":{"draws":50,"losses":49,"wins":57},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":3,"wins":31},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":16},"x-ai/grok-4.6":{"draws":16,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":43},"z-ai/glm-5.3":{"draws":10,"losses":25,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":22,"wins":14},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":13,"losses":25,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":13},"claude-opus-4-5":{"draws":27,"losses":34,"wins":17},"claude-opus-4-8":{"draws":16,"losses":22,"wins":6},"claude-opus-5":{"draws":10,"losses":65,"wins":7},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":19,"losses":15,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":30,"losses":16,"wins":26},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"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":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":17,"losses":29,"wins":14},"google/gemini-3.5-flash-lite":{"draws":35,"losses":23,"wins":26},"google/gemini-3.6-flash":{"draws":20,"losses":43,"wins":21},"google/gemini-3.8-flash":{"draws":12,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":9},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":12,"wins":13},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":18},"gpt-5.5":{"draws":15,"losses":20,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":16,"wins":14},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":22},"meta/muse-glimmer-30b":{"draws":20,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":12},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":24,"wins":10},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":8},"o3":{"draws":15,"losses":28,"wins":21},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":45,"losses":70,"wins":41},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":25,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":37,"losses":14,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":35,"losses":35,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":16,"wins":8},"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-fable-5-1":{"draws":1,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":3},"claude-opus-4-5":{"draws":23,"losses":74,"wins":3},"claude-opus-4-8":{"draws":21,"losses":44,"wins":5},"claude-opus-5":{"draws":11,"losses":61,"wins":6},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":16,"losses":24,"wins":2},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":10,"losses":12,"wins":8},"deepseek/deepseek-v4-flash":{"draws":20,"losses":42,"wins":18},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":8,"losses":25,"wins":3},"gemini-3.1-pro-preview":{"draws":7,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":17,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":26,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":34,"wins":28},"google/gemini-3.6-flash":{"draws":18,"losses":51,"wins":9},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":7},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":30,"wins":4},"gpt-5.4":{"draws":7,"losses":28,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":32,"wins":8},"gpt-5.4-nano":{"draws":21,"losses":52,"wins":21},"gpt-5.5":{"draws":18,"losses":29,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":33,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":25,"wins":5},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":9,"losses":22,"wins":3},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":35,"wins":25},"meta/muse-glimmer-30b":{"draws":15,"losses":14,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":34,"wins":1},"meta/muse-wonder":{"draws":5,"losses":26,"wins":1},"minimax/minimax-m3":{"draws":15,"losses":21,"wins":18},"mistralai/mistral-large-4-0":{"draws":6,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":21,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":21,"wins":28},"o3":{"draws":16,"losses":50,"wins":4},"openai/gpt-oss-120b":{"draws":9,"losses":19,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":24,"wins":16},"qwen/qwen3.7-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.7-plus":{"draws":10,"losses":22,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":27,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":0},"stealth/ox-alpha":{"draws":21,"losses":69,"wins":15},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":23,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":2},"thinkingmachines/inkling":{"draws":13,"losses":27,"wins":20},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":13},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":38,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":21,"wins":3},"xiaomi/mimo-v2.5":{"draws":45,"losses":46,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":29,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":1},"z-ai/glm-5.2":{"draws":25,"losses":65,"wins":16},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":38},"claude-fable-5":{"draws":20,"losses":46,"wins":20},"claude-fable-5-1":{"draws":11,"losses":91,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":19},"claude-opus-4-5":{"draws":28,"losses":25,"wins":53},"claude-opus-4-8":{"draws":9,"losses":18,"wins":25},"claude-opus-5":{"draws":8,"losses":75,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":19,"losses":17,"wins":50},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":19},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":34,"losses":12,"wins":54},"deepseek/deepseek-v4-pro":{"draws":21,"losses":13,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":17,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":11,"losses":16,"wins":21},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":22,"wins":31},"google/gemini-3.5-flash-lite":{"draws":31,"losses":21,"wins":78},"google/gemini-3.6-flash":{"draws":33,"losses":43,"wins":62},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":32},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":16},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":10,"wins":24},"gpt-5.4":{"draws":15,"losses":38,"wins":29},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":28},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":33,"losses":13,"wins":36},"gpt-5.6-sol":{"draws":12,"losses":54,"wins":22},"gpt-5.6-terra":{"draws":23,"losses":27,"wins":30},"gpt-6-astra":{"draws":9,"losses":76,"wins":5},"gpt-6-luna":{"draws":13,"losses":11,"wins":22},"gpt-6-sol":{"draws":6,"losses":34,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":2,"wins":28},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":36},"meta/muse-glimmer-30b":{"draws":21,"losses":9,"wins":34},"meta/muse-spark-1.2":{"draws":16,"losses":17,"wins":31},"meta/muse-spark-1.3":{"draws":15,"losses":32,"wins":21},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":12,"losses":8,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":26,"losses":16,"wins":32},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":26},"o3":{"draws":12,"losses":19,"wins":57},"openai/gpt-oss-120b":{"draws":22,"losses":8,"wins":36},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":23,"wins":39},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":22},"qwen/qwen3.8-flash":{"draws":19,"losses":14,"wins":23},"qwen/qwen3.8-max":{"draws":20,"losses":28,"wins":32},"qwen/qwen3.8-max-0902":{"draws":12,"losses":19,"wins":15},"stealth/ox-alpha":{"draws":65,"losses":82,"wins":132},"stealth/space-bunny-alpha":{"draws":12,"losses":3,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":23},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":39,"wins":31},"thinkingmachines/inkling":{"draws":21,"losses":7,"wins":38},"thinkingmachines/inkling-small":{"draws":20,"losses":13,"wins":39},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":26,"wins":33},"x-ai/grok-4.6":{"draws":26,"losses":42,"wins":18},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":35,"losses":31,"wins":64},"z-ai/glm-5.3":{"draws":16,"losses":28,"wins":28},"z-ai/glm-5.3-flash":{"draws":27,"losses":29,"wins":36},"z-ai/glm-5.3-flashx":{"draws":20,"losses":15,"wins":13}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":56,"losses":57,"wins":35},"claude-fable-5":{"draws":30,"losses":86,"wins":10},"claude-fable-5-1":{"draws":8,"losses":101,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":46,"wins":12},"claude-opus-4-5":{"draws":102,"losses":155,"wins":19},"claude-opus-4-8":{"draws":39,"losses":62,"wins":1},"claude-opus-5":{"draws":30,"losses":142,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":63,"losses":129,"wins":32},"claude-sonnet-5-5":{"draws":15,"losses":57,"wins":12},"cohere/north-mini-code":{"draws":21,"losses":23,"wins":6},"deepseek/deepseek-v4-flash":{"draws":71,"losses":79,"wins":42},"deepseek/deepseek-v4-pro":{"draws":45,"losses":59,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":55,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":41,"wins":8},"fireworks/ember-1":{"draws":34,"losses":42,"wins":8},"gemini-3.1-pro-preview":{"draws":32,"losses":37,"wins":15},"google/gemini-3.1-flash-lite":{"draws":29,"losses":21,"wins":32},"google/gemini-3.5-flash":{"draws":45,"losses":79,"wins":34},"google/gemini-3.5-flash-lite":{"draws":155,"losses":150,"wins":123},"google/gemini-3.6-flash":{"draws":162,"losses":221,"wins":56},"google/gemini-3.8-flash":{"draws":32,"losses":84,"wins":4},"google/gemma-4-31b-it":{"draws":16,"losses":14,"wins":14},"gpt-4.1":{"draws":13,"losses":16,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":40,"losses":34,"wins":20},"gpt-5.4":{"draws":70,"losses":120,"wins":16},"gpt-5.4-mini":{"draws":37,"losses":37,"wins":12},"gpt-5.4-nano":{"draws":32,"losses":37,"wins":39},"gpt-5.5":{"draws":51,"losses":45,"wins":6},"gpt-5.6-luna":{"draws":77,"losses":115,"wins":40},"gpt-5.6-sol":{"draws":32,"losses":163,"wins":9},"gpt-5.6-terra":{"draws":47,"losses":76,"wins":11},"gpt-6-astra":{"draws":7,"losses":103,"wins":0},"gpt-6-luna":{"draws":26,"losses":39,"wins":17},"gpt-6-sol":{"draws":14,"losses":61,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":78,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":45,"losses":34,"wins":31},"inclusionai/ling-3.0-flash":{"draws":45,"losses":37,"wins":42},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":63,"losses":95,"wins":48},"meta/muse-glimmer-30b":{"draws":66,"losses":33,"wins":43},"meta/muse-spark-1.2":{"draws":40,"losses":102,"wins":18},"meta/muse-spark-1.3":{"draws":27,"losses":77,"wins":14},"meta/muse-wonder":{"draws":15,"losses":59,"wins":6},"minimax/minimax-m3":{"draws":21,"losses":19,"wins":28},"mistralai/mistral-large-4-0":{"draws":14,"losses":25,"wins":7},"mistralai/mistral-medium-3-5":{"draws":40,"losses":25,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":9},"moonshotai/kimi-k3":{"draws":78,"losses":103,"wins":19},"nex-agi/nex-n2-pro":{"draws":22,"losses":16,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":32,"wins":20},"o3":{"draws":54,"losses":226,"wins":26},"openai/gpt-oss-120b":{"draws":55,"losses":48,"wins":31},"poolside/laguna-s-2.1":{"draws":89,"losses":87,"wins":34},"qwen/qwen3.7-max":{"draws":23,"losses":28,"wins":13},"qwen/qwen3.7-plus":{"draws":26,"losses":20,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":74,"wins":9},"qwen/qwen3.8-27b":{"draws":15,"losses":45,"wins":12},"qwen/qwen3.8-flash":{"draws":41,"losses":43,"wins":4},"qwen/qwen3.8-max":{"draws":52,"losses":67,"wins":22},"qwen/qwen3.8-max-0902":{"draws":25,"losses":50,"wins":5},"stealth/ox-alpha":{"draws":131,"losses":272,"wins":56},"stealth/space-bunny-alpha":{"draws":20,"losses":35,"wins":11},"stepfun/step-3.7-flash":{"draws":17,"losses":30,"wins":11},"tencent/hy3-preview":{"draws":23,"losses":20,"wins":7},"tencent/hy4-preview":{"draws":45,"losses":72,"wins":19},"thinkingmachines/inkling":{"draws":55,"losses":67,"wins":62},"thinkingmachines/inkling-small":{"draws":61,"losses":46,"wins":62},"unbiased/pareto-26.10-preview":{"draws":0,"losses":26,"wins":0},"upstage/solar-mini4":{"draws":8,"losses":12,"wins":2},"x-ai/grok-4.5":{"draws":63,"losses":138,"wins":15},"x-ai/grok-4.6":{"draws":51,"losses":78,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":25,"losses":22,"wins":5},"xiaomi/mimo-v2.5":{"draws":68,"losses":62,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":30,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":35,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":40,"wins":6},"z-ai/glm-5.2":{"draws":103,"losses":100,"wins":43},"z-ai/glm-5.3":{"draws":31,"losses":72,"wins":5},"z-ai/glm-5.3-flash":{"draws":44,"losses":66,"wins":20},"z-ai/glm-5.3-flashx":{"draws":23,"losses":51,"wins":9}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":21,"wins":68},"claude-fable-5":{"draws":22,"losses":71,"wins":45},"claude-fable-5-1":{"draws":10,"losses":126,"wins":14},"claude-haiku-5-5":{"draws":15,"losses":27,"wins":36},"claude-opus-4-5":{"draws":66,"losses":57,"wins":133},"claude-opus-4-8":{"draws":33,"losses":32,"wins":55},"claude-opus-5":{"draws":20,"losses":134,"wins":52},"claude-opus-5-5":{"draws":7,"losses":70,"wins":11},"claude-sonnet-5":{"draws":48,"losses":55,"wins":87},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":38},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":34},"deepseek/deepseek-v4-flash":{"draws":43,"losses":27,"wins":116},"deepseek/deepseek-v4-pro":{"draws":27,"losses":43,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":31,"wins":72},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":25,"wins":39},"fireworks/ember-1":{"draws":21,"losses":29,"wins":34},"gemini-3.1-pro-preview":{"draws":14,"losses":27,"wins":43},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":61},"google/gemini-3.5-flash":{"draws":33,"losses":52,"wins":71},"google/gemini-3.5-flash-lite":{"draws":105,"losses":64,"wins":230},"google/gemini-3.6-flash":{"draws":69,"losses":106,"wins":163},"google/gemini-3.8-flash":{"draws":25,"losses":59,"wins":50},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":26},"gpt-4.1":{"draws":11,"losses":5,"wins":22},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":21,"losses":21,"wins":56},"gpt-5.4":{"draws":45,"losses":85,"wins":68},"gpt-5.4-mini":{"draws":23,"losses":18,"wins":50},"gpt-5.4-nano":{"draws":23,"losses":16,"wins":77},"gpt-5.5":{"draws":31,"losses":39,"wins":44},"gpt-5.6-luna":{"draws":42,"losses":33,"wins":109},"gpt-5.6-sol":{"draws":31,"losses":97,"wins":68},"gpt-5.6-terra":{"draws":37,"losses":30,"wins":61},"gpt-6-astra":{"draws":14,"losses":112,"wins":8},"gpt-6-luna":{"draws":21,"losses":21,"wins":40},"gpt-6-sol":{"draws":9,"losses":51,"wins":24},"gpt-6.1-sol":{"draws":4,"losses":66,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":47},"inclusionai/ling-3.0-flash":{"draws":38,"losses":6,"wins":66},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":50,"losses":20,"wins":118},"meta/muse-glimmer-30b":{"draws":32,"losses":15,"wins":67},"meta/muse-spark-1.2":{"draws":30,"losses":50,"wins":72},"meta/muse-spark-1.3":{"draws":16,"losses":51,"wins":47},"meta/muse-wonder":{"draws":13,"losses":42,"wins":27},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":41},"mistralai/mistral-large-4-0":{"draws":8,"losses":19,"wins":21},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":4,"wins":21},"moonshotai/kimi-k3":{"draws":48,"losses":55,"wins":97},"nex-agi/nex-n2-pro":{"draws":8,"losses":8,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":52},"o3":{"draws":30,"losses":58,"wins":176},"openai/gpt-oss-120b":{"draws":31,"losses":11,"wins":62},"poolside/laguna-s-2.1":{"draws":45,"losses":27,"wins":96},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":46},"qwen/qwen3.7-plus":{"draws":20,"losses":6,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":45,"wins":59},"qwen/qwen3.8-27b":{"draws":10,"losses":23,"wins":41},"qwen/qwen3.8-flash":{"draws":26,"losses":23,"wins":41},"qwen/qwen3.8-max":{"draws":36,"losses":41,"wins":59},"qwen/qwen3.8-max-0902":{"draws":17,"losses":30,"wins":35},"stealth/ox-alpha":{"draws":92,"losses":157,"wins":200},"stealth/space-bunny-alpha":{"draws":19,"losses":10,"wins":39},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":43},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":19,"losses":14,"wins":23},"tencent/hy4-preview":{"draws":30,"losses":45,"wins":63},"thinkingmachines/inkling":{"draws":40,"losses":23,"wins":97},"thinkingmachines/inkling-small":{"draws":32,"losses":16,"wins":79},"unbiased/pareto-26.10-preview":{"draws":3,"losses":20,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":51,"losses":75,"wins":98},"x-ai/grok-4.6":{"draws":35,"losses":51,"wins":48},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":22},"x-ai/grok-build-0.1":{"draws":13,"losses":0,"wins":29},"xiaomi/mimo-v2.5":{"draws":70,"losses":17,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":8,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":18,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":17,"wins":23},"z-ai/glm-5.2":{"draws":60,"losses":66,"wins":104},"z-ai/glm-5.3":{"draws":21,"losses":59,"wins":32},"z-ai/glm-5.3-flash":{"draws":12,"losses":63,"wins":49},"z-ai/glm-5.3-flashx":{"draws":15,"losses":30,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":10,"wins":33},"claude-fable-5":{"draws":15,"losses":28,"wins":43},"claude-fable-5-1":{"draws":4,"losses":86,"wins":12},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":23},"claude-opus-4-5":{"draws":44,"losses":15,"wins":55},"claude-opus-4-8":{"draws":14,"losses":14,"wins":22},"claude-opus-5":{"draws":12,"losses":57,"wins":23},"claude-opus-5-5":{"draws":7,"losses":41,"wins":4},"claude-sonnet-5":{"draws":28,"losses":23,"wins":37},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":30,"losses":13,"wins":61},"deepseek/deepseek-v4-pro":{"draws":29,"losses":20,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":14,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"fireworks/ember-1":{"draws":17,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":9,"wins":25},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":26,"losses":27,"wins":47},"google/gemini-3.5-flash-lite":{"draws":46,"losses":5,"wins":83},"google/gemini-3.6-flash":{"draws":39,"losses":44,"wins":58},"google/gemini-3.8-flash":{"draws":17,"losses":19,"wins":26},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":7,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":15,"wins":20},"gpt-5.4":{"draws":27,"losses":33,"wins":28},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":27},"gpt-5.5":{"draws":25,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":23,"losses":13,"wins":48},"gpt-5.6-sol":{"draws":16,"losses":48,"wins":24},"gpt-5.6-terra":{"draws":27,"losses":18,"wins":35},"gpt-6-astra":{"draws":7,"losses":79,"wins":4},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":27},"meituan/longcat-2.0":{"draws":18,"losses":8,"wins":36},"meta/muse-glimmer-30b":{"draws":31,"losses":5,"wins":30},"meta/muse-spark-1.2":{"draws":17,"losses":36,"wins":15},"meta/muse-spark-1.3":{"draws":20,"losses":21,"wins":27},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":10,"losses":0,"wins":18},"mistralai/mistral-large-4-0":{"draws":7,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":18,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":22,"losses":14,"wins":34},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":26},"o3":{"draws":17,"losses":26,"wins":53},"openai/gpt-oss-120b":{"draws":27,"losses":7,"wins":32},"poolside/laguna-s-2.1":{"draws":25,"losses":9,"wins":28},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":25,"wins":37},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":26},"qwen/qwen3.8-flash":{"draws":21,"losses":12,"wins":27},"qwen/qwen3.8-max":{"draws":24,"losses":26,"wins":34},"qwen/qwen3.8-max-0902":{"draws":16,"losses":11,"wins":19},"stealth/ox-alpha":{"draws":70,"losses":80,"wins":136},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":24,"losses":26,"wins":32},"thinkingmachines/inkling":{"draws":25,"losses":2,"wins":37},"thinkingmachines/inkling-small":{"draws":31,"losses":4,"wins":39},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":23},"x-ai/grok-4.6":{"draws":33,"losses":31,"wins":22},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":4,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":11},"z-ai/glm-5.2":{"draws":42,"losses":20,"wins":66},"z-ai/glm-5.3":{"draws":15,"losses":32,"wins":27},"z-ai/glm-5.3-flash":{"draws":21,"losses":28,"wins":41},"z-ai/glm-5.3-flashx":{"draws":12,"losses":14,"wins":22}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":17},"claude-fable-5":{"draws":9,"losses":26,"wins":7},"claude-fable-5-1":{"draws":1,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":28,"wins":6},"claude-opus-4-5":{"draws":27,"losses":30,"wins":13},"claude-opus-4-8":{"draws":10,"losses":24,"wins":8},"claude-opus-5":{"draws":13,"losses":54,"wins":7},"claude-opus-5-5":{"draws":4,"losses":40,"wins":0},"claude-sonnet-5":{"draws":12,"losses":22,"wins":10},"claude-sonnet-5-5":{"draws":8,"losses":28,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":25,"losses":23,"wins":14},"deepseek/deepseek-v4-pro":{"draws":18,"losses":13,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":17,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":11},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":9,"losses":28,"wins":15},"google/gemini-3.5-flash-lite":{"draws":23,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":23,"losses":43,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":6},"gpt-4.1":{"draws":3,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":17,"wins":7},"gpt-5.4":{"draws":14,"losses":21,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":18,"wins":10},"gpt-5.5":{"draws":18,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":34,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":17,"wins":9},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":16,"wins":15},"gpt-6-sol":{"draws":5,"losses":39,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.0-flash":{"draws":14,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":13,"wins":15},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":17,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"o3":{"draws":9,"losses":32,"wins":17},"openai/gpt-oss-120b":{"draws":15,"losses":17,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":18,"losses":21,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":29,"losses":78,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":19,"wins":9},"thinkingmachines/inkling":{"draws":22,"losses":10,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":16},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":25,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":30,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":31,"wins":21},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":8},"z-ai/glm-5.3-flashx":{"draws":14,"losses":24,"wins":6}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":16,"wins":16},"claude-fable-5":{"draws":9,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":6},"claude-opus-4-5":{"draws":28,"losses":49,"wins":37},"claude-opus-4-8":{"draws":17,"losses":38,"wins":23},"claude-opus-5":{"draws":17,"losses":82,"wins":9},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":13,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":26,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":2,"wins":25},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":16,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"fireworks/ember-1":{"draws":11,"losses":21,"wins":10},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":12},"google/gemini-3.1-flash-lite":{"draws":19,"losses":0,"wins":33},"google/gemini-3.5-flash":{"draws":18,"losses":27,"wins":17},"google/gemini-3.5-flash-lite":{"draws":32,"losses":31,"wins":31},"google/gemini-3.6-flash":{"draws":13,"losses":49,"wins":30},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":7,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":25,"wins":6},"gpt-5.4":{"draws":11,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":21,"losses":19,"wins":18},"gpt-5.4-nano":{"draws":14,"losses":35,"wins":25},"gpt-5.5":{"draws":18,"losses":32,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":10,"losses":19,"wins":13},"gpt-6-sol":{"draws":2,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":21,"losses":20,"wins":13},"meituan/longcat-2.0":{"draws":26,"losses":13,"wins":47},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":5,"losses":28,"wins":9},"meta/muse-wonder":{"draws":6,"losses":22,"wins":10},"minimax/minimax-m3":{"draws":10,"losses":16,"wins":18},"mistralai/mistral-large-4-0":{"draws":4,"losses":15,"wins":3},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":24,"wins":21},"o3":{"draws":15,"losses":27,"wins":40},"openai/gpt-oss-120b":{"draws":9,"losses":9,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":24,"wins":21},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":12,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":25,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":11},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":9,"losses":27,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":36,"losses":62,"wins":48},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":15,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":14,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":33,"wins":18},"x-ai/grok-4.6":{"draws":12,"losses":29,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":21},"xiaomi/mimo-v2.5":{"draws":45,"losses":36,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":12,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":41,"losses":39,"wins":42},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":16,"wins":31},"claude-fable-5":{"draws":27,"losses":35,"wins":26},"claude-fable-5-1":{"draws":2,"losses":78,"wins":12},"claude-haiku-5-5":{"draws":11,"losses":16,"wins":15},"claude-opus-4-5":{"draws":46,"losses":19,"wins":67},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":6,"losses":71,"wins":13},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":55,"losses":27,"wins":54},"claude-sonnet-5-5":{"draws":17,"losses":20,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":40,"losses":14,"wins":56},"deepseek/deepseek-v4-pro":{"draws":23,"losses":22,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":19,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":13,"wins":14},"fireworks/ember-1":{"draws":16,"losses":14,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":24,"losses":34,"wins":40},"google/gemini-3.5-flash-lite":{"draws":79,"losses":32,"wins":117},"google/gemini-3.6-flash":{"draws":68,"losses":73,"wins":83},"google/gemini-3.8-flash":{"draws":29,"losses":28,"wins":31},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":11},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":10,"wins":19},"gpt-5.4":{"draws":30,"losses":28,"wins":41},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":12,"wins":28},"gpt-5.5":{"draws":16,"losses":18,"wins":12},"gpt-5.6-luna":{"draws":55,"losses":20,"wins":65},"gpt-5.6-sol":{"draws":23,"losses":78,"wins":41},"gpt-5.6-terra":{"draws":35,"losses":16,"wins":35},"gpt-6-astra":{"draws":9,"losses":62,"wins":13},"gpt-6-luna":{"draws":14,"losses":11,"wins":21},"gpt-6-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":14,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":13,"wins":50},"meta/muse-glimmer-30b":{"draws":32,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":33,"losses":22,"wins":45},"meta/muse-spark-1.3":{"draws":23,"losses":20,"wins":27},"meta/muse-wonder":{"draws":14,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":5,"wins":13},"mistralai/mistral-medium-3-5":{"draws":20,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":24,"losses":27,"wins":57},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"o3":{"draws":20,"losses":22,"wins":92},"openai/gpt-oss-120b":{"draws":38,"losses":10,"wins":26},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":45},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":38,"wins":28},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":24},"qwen/qwen3.8-flash":{"draws":16,"losses":15,"wins":25},"qwen/qwen3.8-max":{"draws":36,"losses":29,"wins":29},"qwen/qwen3.8-max-0902":{"draws":14,"losses":15,"wins":17},"stealth/ox-alpha":{"draws":89,"losses":78,"wins":105},"stealth/space-bunny-alpha":{"draws":15,"losses":6,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"tencent/hy3-preview":{"draws":14,"losses":3,"wins":11},"tencent/hy4-preview":{"draws":27,"losses":26,"wins":31},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":44},"thinkingmachines/inkling-small":{"draws":44,"losses":7,"wins":40},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":27,"losses":37,"wins":44},"x-ai/grok-4.6":{"draws":35,"losses":25,"wins":28},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":29,"losses":5,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":13},"z-ai/glm-5.2":{"draws":48,"losses":23,"wins":55},"z-ai/glm-5.3":{"draws":21,"losses":33,"wins":22},"z-ai/glm-5.3-flash":{"draws":20,"losses":34,"wins":30},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":20},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":9},"claude-opus-4-5":{"draws":39,"losses":54,"wins":49},"claude-opus-4-8":{"draws":20,"losses":30,"wins":36},"claude-opus-5":{"draws":20,"losses":106,"wins":16},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":18,"losses":13,"wins":23},"claude-sonnet-5-5":{"draws":8,"losses":27,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":23},"deepseek/deepseek-v4-flash":{"draws":33,"losses":13,"wins":48},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":18,"wins":15},"fireworks/ember-1":{"draws":14,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":18},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":36},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":27},"google/gemini-3.5-flash-lite":{"draws":38,"losses":13,"wins":61},"google/gemini-3.6-flash":{"draws":20,"losses":55,"wins":32},"google/gemini-3.8-flash":{"draws":10,"losses":33,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":15},"gpt-4.1":{"draws":14,"losses":7,"wins":15},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":19,"losses":15,"wins":44},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":22,"losses":39,"wins":39},"gpt-5.5":{"draws":41,"losses":26,"wins":13},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":13},"gpt-5.6-terra":{"draws":20,"losses":13,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":17,"wins":10},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":14,"wins":47},"meta/muse-glimmer-30b":{"draws":19,"losses":0,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":12},"meta/muse-wonder":{"draws":9,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":25,"losses":8,"wins":33},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":13,"wins":11},"moonshotai/kimi-k3":{"draws":20,"losses":15,"wins":25},"nex-agi/nex-n2-pro":{"draws":18,"losses":4,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":17,"wins":31},"o3":{"draws":13,"losses":34,"wins":37},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":30,"losses":12,"wins":42},"qwen/qwen3.7-max":{"draws":17,"losses":21,"wins":20},"qwen/qwen3.7-plus":{"draws":18,"losses":16,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":25,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":19,"losses":22,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":13},"stealth/ox-alpha":{"draws":36,"losses":75,"wins":53},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":13},"thinkingmachines/inkling":{"draws":26,"losses":17,"wins":31},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":19,"losses":36,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":14},"x-ai/grok-4.7":{"draws":7,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":22},"xiaomi/mimo-v2.5":{"draws":53,"losses":25,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":13,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":59,"losses":43,"wins":38},"z-ai/glm-5.3":{"draws":6,"losses":30,"wins":8},"z-ai/glm-5.3-flash":{"draws":16,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":28,"wins":28},"claude-fable-5":{"draws":8,"losses":54,"wins":12},"claude-fable-5-1":{"draws":0,"losses":80,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":36,"wins":24},"claude-opus-4-5":{"draws":54,"losses":77,"wins":75},"claude-opus-4-8":{"draws":23,"losses":72,"wins":33},"claude-opus-5":{"draws":17,"losses":141,"wins":32},"claude-opus-5-5":{"draws":2,"losses":76,"wins":2},"claude-sonnet-5":{"draws":11,"losses":38,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":52,"wins":11},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":29},"deepseek/deepseek-v4-flash":{"draws":35,"losses":46,"wins":53},"deepseek/deepseek-v4-pro":{"draws":10,"losses":37,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":32,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":37,"wins":21},"fireworks/ember-1":{"draws":16,"losses":35,"wins":21},"gemini-3.1-pro-preview":{"draws":14,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":22,"losses":19,"wins":73},"google/gemini-3.5-flash":{"draws":20,"losses":52,"wins":38},"google/gemini-3.5-flash-lite":{"draws":22,"losses":76,"wins":54},"google/gemini-3.6-flash":{"draws":29,"losses":91,"wins":38},"google/gemini-3.8-flash":{"draws":14,"losses":46,"wins":18},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":24},"gpt-4.1":{"draws":5,"losses":17,"wins":20},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":18,"losses":47,"wins":45},"gpt-5.4":{"draws":12,"losses":39,"wins":21},"gpt-5.4-mini":{"draws":16,"losses":29,"wins":55},"gpt-5.4-nano":{"draws":15,"losses":51,"wins":60},"gpt-5.5":{"draws":29,"losses":59,"wins":38},"gpt-5.6-luna":{"draws":14,"losses":33,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":56,"wins":10},"gpt-5.6-terra":{"draws":10,"losses":37,"wins":25},"gpt-6-astra":{"draws":1,"losses":70,"wins":1},"gpt-6-luna":{"draws":14,"losses":28,"wins":26},"gpt-6-sol":{"draws":12,"losses":56,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":67,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":33},"inclusionai/ling-3.0-flash":{"draws":23,"losses":25,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":42,"wins":79},"meta/muse-glimmer-30b":{"draws":13,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":30,"wins":26},"meta/muse-spark-1.3":{"draws":15,"losses":38,"wins":19},"meta/muse-wonder":{"draws":7,"losses":52,"wins":9},"minimax/minimax-m3":{"draws":20,"losses":24,"wins":42},"mistralai/mistral-large-4-0":{"draws":6,"losses":23,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":9,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":21,"wins":18},"moonshotai/kimi-k3":{"draws":21,"losses":39,"wins":22},"nex-agi/nex-n2-pro":{"draws":10,"losses":16,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":48,"wins":46},"o3":{"draws":11,"losses":65,"wins":74},"openai/gpt-oss-120b":{"draws":13,"losses":28,"wins":27},"poolside/laguna-s-2.1":{"draws":22,"losses":44,"wins":42},"qwen/qwen3.7-max":{"draws":17,"losses":35,"wins":32},"qwen/qwen3.7-plus":{"draws":20,"losses":37,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":44,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":25,"wins":21},"qwen/qwen3.8-flash":{"draws":13,"losses":22,"wins":17},"qwen/qwen3.8-max":{"draws":19,"losses":40,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":36,"wins":18},"stealth/ox-alpha":{"draws":34,"losses":111,"wins":69},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":9,"losses":18,"wins":41},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":23,"wins":20},"tencent/hy4-preview":{"draws":9,"losses":43,"wins":22},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":59},"thinkingmachines/inkling-small":{"draws":25,"losses":22,"wins":31},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":17,"losses":51,"wins":36},"x-ai/grok-4.6":{"draws":9,"losses":51,"wins":12},"x-ai/grok-4.7":{"draws":7,"losses":50,"wins":9},"x-ai/grok-build-0.1":{"draws":12,"losses":15,"wins":29},"xiaomi/mimo-v2.5":{"draws":60,"losses":74,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":32,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":25,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":29,"wins":11},"z-ai/glm-5.2":{"draws":45,"losses":79,"wins":92},"z-ai/glm-5.3":{"draws":7,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":14,"losses":36,"wins":22},"z-ai/glm-5.3-flashx":{"draws":12,"losses":41,"wins":19}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":10,"wins":16},"claude-fable-5":{"draws":11,"losses":24,"wins":15},"claude-fable-5-1":{"draws":3,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":19,"losses":19,"wins":6},"claude-opus-4-5":{"draws":62,"losses":33,"wins":41},"claude-opus-4-8":{"draws":29,"losses":25,"wins":36},"claude-opus-5":{"draws":23,"losses":108,"wins":23},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":23,"losses":7,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":9,"losses":2,"wins":19},"deepseek/deepseek-v4-flash":{"draws":36,"losses":13,"wins":43},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"google/gemini-3.1-flash-lite":{"draws":18,"losses":8,"wins":32},"google/gemini-3.5-flash":{"draws":20,"losses":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":46,"losses":12,"wins":44},"google/gemini-3.6-flash":{"draws":33,"losses":37,"wins":36},"google/gemini-3.8-flash":{"draws":18,"losses":20,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":14},"gpt-4.1":{"draws":11,"losses":7,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":25,"losses":21,"wins":34},"gpt-5.4":{"draws":15,"losses":16,"wins":15},"gpt-5.4-mini":{"draws":35,"losses":11,"wins":22},"gpt-5.4-nano":{"draws":31,"losses":43,"wins":32},"gpt-5.5":{"draws":22,"losses":20,"wins":20},"gpt-5.6-luna":{"draws":19,"losses":9,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":21,"losses":9,"wins":16},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inclusionai/ling-3.0-flash":{"draws":25,"losses":8,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":27,"losses":20,"wins":37},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":12,"losses":17,"wins":17},"meta/muse-wonder":{"draws":11,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":17,"losses":4,"wins":31},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":11},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":19,"losses":22,"wins":19},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":42},"o3":{"draws":21,"losses":24,"wins":35},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":27},"qwen/qwen3.7-max":{"draws":21,"losses":10,"wins":25},"qwen/qwen3.7-plus":{"draws":24,"losses":6,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":9,"wins":17},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"stealth/ox-alpha":{"draws":47,"losses":70,"wins":47},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":4,"wins":21},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":23,"losses":20,"wins":33},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":34,"wins":27},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":24,"losses":9,"wins":7},"xiaomi/mimo-v2.5":{"draws":56,"losses":17,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":59,"losses":29,"wins":48},"z-ai/glm-5.3":{"draws":17,"losses":22,"wins":9},"z-ai/glm-5.3-flash":{"draws":13,"losses":18,"wins":19},"z-ai/glm-5.3-flashx":{"draws":14,"losses":19,"wins":15}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":26,"wins":30},"claude-fable-5":{"draws":22,"losses":58,"wins":4},"claude-fable-5-1":{"draws":8,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":25,"wins":7},"claude-opus-4-5":{"draws":50,"losses":51,"wins":37},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":66,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":53,"losses":50,"wins":33},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":39,"losses":30,"wins":45},"deepseek/deepseek-v4-pro":{"draws":30,"losses":28,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":36,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":22,"wins":7},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":16,"losses":16,"wins":16},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":36,"losses":44,"wins":22},"google/gemini-3.5-flash-lite":{"draws":80,"losses":53,"wins":103},"google/gemini-3.6-flash":{"draws":66,"losses":105,"wins":51},"google/gemini-3.8-flash":{"draws":24,"losses":51,"wins":7},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":17,"wins":10},"gpt-5.4":{"draws":47,"losses":68,"wins":19},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":16,"losses":13,"wins":23},"gpt-5.5":{"draws":18,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":42,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":25,"losses":91,"wins":16},"gpt-5.6-terra":{"draws":24,"losses":34,"wins":28},"gpt-6-astra":{"draws":10,"losses":63,"wins":1},"gpt-6-luna":{"draws":18,"losses":18,"wins":12},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":4,"wins":29},"inclusionai/ling-3.0-flash":{"draws":22,"losses":12,"wins":24},"meituan/longcat-2.0":{"draws":30,"losses":18,"wins":48},"meta/muse-glimmer-30b":{"draws":36,"losses":12,"wins":34},"meta/muse-spark-1.2":{"draws":30,"losses":45,"wins":27},"meta/muse-spark-1.3":{"draws":20,"losses":35,"wins":17},"meta/muse-wonder":{"draws":9,"losses":32,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":3,"wins":14},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":2},"mistralai/mistral-medium-3-5":{"draws":20,"losses":2,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":51,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":14},"o3":{"draws":27,"losses":52,"wins":57},"openai/gpt-oss-120b":{"draws":36,"losses":16,"wins":30},"poolside/laguna-s-2.1":{"draws":36,"losses":14,"wins":42},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":37,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":13},"qwen/qwen3.8-flash":{"draws":17,"losses":20,"wins":23},"qwen/qwen3.8-max":{"draws":33,"losses":33,"wins":19},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":100,"losses":112,"wins":70},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":47,"wins":10},"thinkingmachines/inkling":{"draws":35,"losses":17,"wins":40},"thinkingmachines/inkling-small":{"draws":42,"losses":19,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":29,"losses":46,"wins":27},"x-ai/grok-4.6":{"draws":28,"losses":45,"wins":9},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":50,"losses":45,"wins":43},"z-ai/glm-5.3":{"draws":17,"losses":42,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":43,"wins":15},"z-ai/glm-5.3-flashx":{"draws":16,"losses":22,"wins":10}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":16,"wins":46},"claude-fable-5":{"draws":14,"losses":37,"wins":33},"claude-fable-5-1":{"draws":10,"losses":87,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":12,"wins":20},"claude-opus-4-5":{"draws":29,"losses":27,"wins":84},"claude-opus-4-8":{"draws":3,"losses":24,"wins":25},"claude-opus-5":{"draws":19,"losses":70,"wins":21},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":19,"losses":25,"wins":101},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":70},"deepseek/deepseek-v4-pro":{"draws":5,"losses":17,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"fireworks/ember-1":{"draws":7,"losses":12,"wins":29},"gemini-3.1-pro-preview":{"draws":3,"losses":17,"wins":28},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":9,"losses":24,"wins":55},"google/gemini-3.5-flash-lite":{"draws":20,"losses":26,"wins":158},"google/gemini-3.6-flash":{"draws":29,"losses":66,"wins":107},"google/gemini-3.8-flash":{"draws":10,"losses":39,"wins":39},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":23},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":25,"losses":37,"wins":64},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":39},"gpt-5.5":{"draws":11,"losses":15,"wins":22},"gpt-5.6-luna":{"draws":12,"losses":23,"wins":83},"gpt-5.6-sol":{"draws":20,"losses":64,"wins":18},"gpt-5.6-terra":{"draws":23,"losses":13,"wins":48},"gpt-6-astra":{"draws":12,"losses":73,"wins":5},"gpt-6-luna":{"draws":9,"losses":9,"wins":28},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":43},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":42},"meituan/longcat-2.0":{"draws":17,"losses":12,"wins":61},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":44},"meta/muse-spark-1.2":{"draws":10,"losses":30,"wins":62},"meta/muse-spark-1.3":{"draws":14,"losses":21,"wins":33},"meta/muse-wonder":{"draws":10,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":5,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":27,"losses":27,"wins":50},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":33},"o3":{"draws":16,"losses":20,"wins":92},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":48},"poolside/laguna-s-2.1":{"draws":14,"losses":3,"wins":71},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":50},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":27},"qwen/qwen3.8-flash":{"draws":9,"losses":11,"wins":32},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":38},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":29},"stealth/ox-alpha":{"draws":42,"losses":70,"wins":167},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":23,"wins":48},"thinkingmachines/inkling":{"draws":14,"losses":10,"wins":58},"thinkingmachines/inkling-small":{"draws":10,"losses":15,"wins":49},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":13,"losses":41,"wins":56},"x-ai/grok-4.6":{"draws":16,"losses":38,"wins":34},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":12,"losses":8,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":10,"wins":10},"z-ai/glm-5.2":{"draws":13,"losses":18,"wins":93},"z-ai/glm-5.3":{"draws":17,"losses":17,"wins":36},"z-ai/glm-5.3-flash":{"draws":19,"losses":32,"wins":35},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":26}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":19,"wins":34},"claude-fable-5":{"draws":19,"losses":58,"wins":17},"claude-fable-5-1":{"draws":9,"losses":87,"wins":4},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":15},"claude-opus-4-5":{"draws":35,"losses":33,"wins":38},"claude-opus-4-8":{"draws":14,"losses":21,"wins":13},"claude-opus-5":{"draws":5,"losses":80,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":26,"losses":26,"wins":34},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":40,"losses":19,"wins":45},"deepseek/deepseek-v4-pro":{"draws":33,"losses":26,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":27,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":14,"wins":16},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":16,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":21,"losses":28,"wins":43},"google/gemini-3.5-flash-lite":{"draws":44,"losses":29,"wins":73},"google/gemini-3.6-flash":{"draws":33,"losses":67,"wins":46},"google/gemini-3.8-flash":{"draws":26,"losses":29,"wins":33},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":13},"gpt-4.1":{"draws":13,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":26},"gpt-5.4":{"draws":29,"losses":39,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":27},"gpt-5.5":{"draws":14,"losses":18,"wins":12},"gpt-5.6-luna":{"draws":30,"losses":32,"wins":28},"gpt-5.6-sol":{"draws":22,"losses":51,"wins":17},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":19},"gpt-6-astra":{"draws":7,"losses":79,"wins":4},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":6,"losses":37,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":43,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":23,"losses":2,"wins":31},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":27},"meituan/longcat-2.0":{"draws":18,"losses":18,"wins":44},"meta/muse-glimmer-30b":{"draws":28,"losses":10,"wins":36},"meta/muse-spark-1.2":{"draws":21,"losses":25,"wins":28},"meta/muse-spark-1.3":{"draws":14,"losses":36,"wins":22},"meta/muse-wonder":{"draws":12,"losses":21,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":18},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":36,"wins":25},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":21},"o3":{"draws":17,"losses":39,"wins":44},"openai/gpt-oss-120b":{"draws":26,"losses":12,"wins":40},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":36},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":42,"wins":18},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":20},"qwen/qwen3.8-flash":{"draws":18,"losses":24,"wins":12},"qwen/qwen3.8-max":{"draws":36,"losses":28,"wins":24},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":13},"stealth/ox-alpha":{"draws":81,"losses":113,"wins":80},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":17,"losses":40,"wins":21},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":38},"thinkingmachines/inkling-small":{"draws":27,"losses":16,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":17,"losses":42,"wins":21},"x-ai/grok-4.6":{"draws":27,"losses":44,"wins":23},"x-ai/grok-4.7":{"draws":6,"losses":28,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":7},"xiaomi/mimo-v2.5":{"draws":27,"losses":4,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":55,"losses":33,"wins":56},"z-ai/glm-5.3":{"draws":17,"losses":46,"wins":11},"z-ai/glm-5.3-flash":{"draws":18,"losses":36,"wins":28},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":53},"claude-fable-5":{"draws":7,"losses":16,"wins":67},"claude-fable-5-1":{"draws":10,"losses":37,"wins":61},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":39},"claude-opus-4-5":{"draws":9,"losses":2,"wins":95},"claude-opus-4-8":{"draws":2,"losses":2,"wins":42},"claude-opus-5":{"draws":11,"losses":27,"wins":52},"claude-opus-5-5":{"draws":4,"losses":24,"wins":24},"claude-sonnet-5":{"draws":2,"losses":0,"wins":84},"claude-sonnet-5-5":{"draws":6,"losses":9,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":7,"losses":2,"wins":87},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":3,"wins":39},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":5,"losses":2,"wins":41},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":77},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":115},"google/gemini-3.6-flash":{"draws":9,"losses":13,"wins":110},"google/gemini-3.8-flash":{"draws":9,"losses":4,"wins":81},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":26},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":1,"wins":37},"gpt-5.4":{"draws":5,"losses":10,"wins":69},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":2,"losses":3,"wins":41},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":64},"gpt-5.6-sol":{"draws":10,"losses":15,"wins":69},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":74},"gpt-6-astra":{"draws":8,"losses":42,"wins":14},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":6,"losses":7,"wins":35},"gpt-6.1-sol":{"draws":7,"losses":19,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":56},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":45},"meta/muse-spark-1.2":{"draws":6,"losses":1,"wins":59},"meta/muse-spark-1.3":{"draws":11,"losses":4,"wins":53},"meta/muse-wonder":{"draws":3,"losses":6,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":55},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"o3":{"draws":3,"losses":0,"wins":91},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":46},"poolside/laguna-s-2.1":{"draws":5,"losses":0,"wins":55},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":4,"wins":75},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":43},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":46},"qwen/qwen3.8-max":{"draws":10,"losses":0,"wins":70},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"stealth/ox-alpha":{"draws":40,"losses":16,"wins":224},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":70},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":59},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":61},"unbiased/pareto-26.10-preview":{"draws":3,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":8,"wins":65},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":71},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":29},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":105},"z-ai/glm-5.3":{"draws":11,"losses":5,"wins":56},"z-ai/glm-5.3-flash":{"draws":11,"losses":4,"wins":71},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":41}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":20,"wins":9},"claude-opus-4-5":{"draws":31,"losses":33,"wins":14},"claude-opus-4-8":{"draws":11,"losses":22,"wins":11},"claude-opus-5":{"draws":19,"losses":57,"wins":6},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":14,"losses":22,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":32,"losses":13,"wins":27},"deepseek/deepseek-v4-pro":{"draws":16,"losses":10,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":17,"losses":21,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":26,"wins":15},"google/gemini-3.5-flash-lite":{"draws":31,"losses":21,"wins":32},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":11},"google/gemini-3.8-flash":{"draws":19,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":15,"wins":10},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":7,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":16,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":29,"wins":11},"meta/muse-wonder":{"draws":11,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":19,"losses":16,"wins":9},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"o3":{"draws":14,"losses":19,"wins":31},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":11,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":12},"stealth/ox-alpha":{"draws":38,"losses":74,"wins":44},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":6,"wins":24},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":32,"losses":9,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":16,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":7,"losses":13,"wins":28},"claude-fable-5-1":{"draws":7,"losses":37,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":4,"wins":25},"claude-opus-4-5":{"draws":18,"losses":5,"wins":55},"claude-opus-4-8":{"draws":10,"losses":7,"wins":27},"claude-opus-5":{"draws":11,"losses":36,"wins":35},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":26},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":29},"fireworks/ember-1":{"draws":7,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":39},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":3,"wins":44},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":57},"google/gemini-3.6-flash":{"draws":11,"losses":16,"wins":57},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":32},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":22},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":33},"gpt-5.5":{"draws":7,"losses":9,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":27},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":32},"gpt-6-astra":{"draws":8,"losses":30,"wins":10},"gpt-6-luna":{"draws":9,"losses":9,"wins":28},"gpt-6-sol":{"draws":6,"losses":12,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":24},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":44},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":6,"losses":8,"wins":30},"meta/muse-spark-1.3":{"draws":11,"losses":6,"wins":29},"meta/muse-wonder":{"draws":4,"losses":16,"wins":26},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":32},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"o3":{"draws":6,"losses":3,"wins":55},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":11,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":34},"qwen/qwen3.8-27b":{"draws":9,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":35},"stealth/ox-alpha":{"draws":23,"losses":19,"wins":114},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":6,"wins":33},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":33},"x-ai/grok-4.6":{"draws":7,"losses":9,"wins":32},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":3,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":17,"losses":6,"wins":73},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":7,"losses":10,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":4,"losses":9,"wins":35},"claude-fable-5-1":{"draws":3,"losses":21,"wins":30},"claude-haiku-5-5":{"draws":5,"losses":4,"wins":33},"claude-opus-4-5":{"draws":2,"losses":5,"wins":71},"claude-opus-4-8":{"draws":2,"losses":5,"wins":37},"claude-opus-5":{"draws":11,"losses":26,"wins":45},"claude-opus-5-5":{"draws":3,"losses":28,"wins":21},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":65},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"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":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":51},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":74},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":38},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":23},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":2,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":45},"gpt-5.5":{"draws":1,"losses":6,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":5,"losses":26,"wins":17},"gpt-6-luna":{"draws":1,"losses":1,"wins":46},"gpt-6-sol":{"draws":5,"losses":10,"wins":33},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":33},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":38},"meta/muse-wonder":{"draws":7,"losses":9,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":36},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"o3":{"draws":1,"losses":0,"wins":65},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":41},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":39},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":45},"stealth/ox-alpha":{"draws":14,"losses":8,"wins":134},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":51},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":42},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":40},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":11,"losses":5,"wins":80},"z-ai/glm-5.3":{"draws":8,"losses":7,"wins":31},"z-ai/glm-5.3-flash":{"draws":5,"losses":5,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":22,"wins":14},"claude-fable-5":{"draws":14,"losses":32,"wins":0},"claude-fable-5-1":{"draws":4,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":1},"claude-opus-4-5":{"draws":26,"losses":51,"wins":1},"claude-opus-4-8":{"draws":11,"losses":24,"wins":1},"claude-opus-5":{"draws":7,"losses":49,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":27,"losses":33,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":6},"deepseek/deepseek-v4-flash":{"draws":38,"losses":35,"wins":9},"deepseek/deepseek-v4-pro":{"draws":26,"losses":30,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":26,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":16,"losses":20,"wins":0},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":21,"losses":40,"wins":7},"google/gemini-3.5-flash-lite":{"draws":53,"losses":56,"wins":15},"google/gemini-3.6-flash":{"draws":35,"losses":59,"wins":4},"google/gemini-3.8-flash":{"draws":22,"losses":27,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":2},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":24,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":26,"wins":3},"gpt-5.5":{"draws":14,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":10},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":0},"gpt-5.6-terra":{"draws":30,"losses":30,"wins":0},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":11,"losses":20,"wins":3},"gpt-6-sol":{"draws":5,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":16,"losses":11,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":23,"wins":13},"meta/muse-glimmer-30b":{"draws":32,"losses":20,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":27,"wins":5},"meta/muse-spark-1.3":{"draws":16,"losses":33,"wins":1},"meta/muse-wonder":{"draws":7,"losses":24,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":1},"mistralai/mistral-medium-3-5":{"draws":23,"losses":14,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":30,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":12,"wins":7},"o3":{"draws":19,"losses":50,"wins":7},"openai/gpt-oss-120b":{"draws":26,"losses":26,"wins":6},"poolside/laguna-s-2.1":{"draws":24,"losses":11,"wins":11},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":20,"wins":2},"qwen/qwen3.8-flash":{"draws":22,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":24,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":5},"stealth/ox-alpha":{"draws":50,"losses":98,"wins":10},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":0},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":21,"losses":27,"wins":6},"thinkingmachines/inkling":{"draws":21,"losses":20,"wins":11},"thinkingmachines/inkling-small":{"draws":31,"losses":25,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":18,"losses":33,"wins":1},"x-ai/grok-4.6":{"draws":14,"losses":39,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":25,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":38,"losses":55,"wins":7},"z-ai/glm-5.3":{"draws":19,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":20,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":2}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":24,"wins":12},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":2,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":1},"claude-opus-4-5":{"draws":38,"losses":54,"wins":28},"claude-opus-4-8":{"draws":18,"losses":26,"wins":0},"claude-opus-5":{"draws":15,"losses":46,"wins":3},"claude-opus-5-5":{"draws":3,"losses":32,"wins":0},"claude-sonnet-5":{"draws":32,"losses":61,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":15},"deepseek/deepseek-v4-flash":{"draws":29,"losses":33,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":34,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":24,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":3},"fireworks/ember-1":{"draws":13,"losses":19,"wins":4},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":43,"wins":11},"google/gemini-3.5-flash-lite":{"draws":63,"losses":116,"wins":51},"google/gemini-3.6-flash":{"draws":76,"losses":100,"wins":36},"google/gemini-3.8-flash":{"draws":10,"losses":41,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":8},"gpt-4.1":{"draws":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":22,"wins":4},"gpt-5.4":{"draws":18,"losses":52,"wins":18},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":16},"gpt-5.5":{"draws":11,"losses":21,"wins":6},"gpt-5.6-luna":{"draws":31,"losses":33,"wins":36},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":37,"wins":8},"gpt-6-astra":{"draws":3,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":6},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":10,"wins":22},"inclusionai/ling-3.0-flash":{"draws":8,"losses":16,"wins":16},"meituan/longcat-2.0":{"draws":32,"losses":45,"wins":39},"meta/muse-glimmer-30b":{"draws":28,"losses":20,"wins":12},"meta/muse-spark-1.2":{"draws":28,"losses":30,"wins":16},"meta/muse-spark-1.3":{"draws":5,"losses":39,"wins":8},"meta/muse-wonder":{"draws":9,"losses":27,"wins":0},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":17,"losses":9,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":24,"losses":52,"wins":20},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":15},"o3":{"draws":4,"losses":101,"wins":29},"openai/gpt-oss-120b":{"draws":16,"losses":32,"wins":12},"poolside/laguna-s-2.1":{"draws":25,"losses":33,"wins":10},"qwen/qwen3.7-max":{"draws":13,"losses":25,"wins":2},"qwen/qwen3.7-plus":{"draws":11,"losses":12,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":34,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":25,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":24,"wins":9},"qwen/qwen3.8-max":{"draws":26,"losses":27,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"stealth/ox-alpha":{"draws":33,"losses":103,"wins":30},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":16,"wins":7},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":13,"losses":40,"wins":7},"thinkingmachines/inkling":{"draws":38,"losses":26,"wins":20},"thinkingmachines/inkling-small":{"draws":26,"losses":30,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":33,"losses":67,"wins":10},"x-ai/grok-4.6":{"draws":18,"losses":34,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":13,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":26,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":21,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":2},"z-ai/glm-5.2":{"draws":28,"losses":43,"wins":25},"z-ai/glm-5.3":{"draws":9,"losses":39,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":39,"wins":3},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":48,"wins":32},"claude-fable-5":{"draws":22,"losses":64,"wins":20},"claude-fable-5-1":{"draws":5,"losses":97,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":41,"wins":8},"claude-opus-4-5":{"draws":57,"losses":135,"wins":45},"claude-opus-4-8":{"draws":20,"losses":44,"wins":13},"claude-opus-5":{"draws":21,"losses":112,"wins":18},"claude-opus-5-5":{"draws":6,"losses":69,"wins":5},"claude-sonnet-5":{"draws":57,"losses":114,"wins":23},"claude-sonnet-5-5":{"draws":9,"losses":46,"wins":17},"cohere/north-mini-code":{"draws":10,"losses":11,"wins":25},"deepseek/deepseek-v4-flash":{"draws":49,"losses":63,"wins":38},"deepseek/deepseek-v4-pro":{"draws":33,"losses":63,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":58,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":41,"wins":14},"fireworks/ember-1":{"draws":17,"losses":40,"wins":14},"gemini-3.1-pro-preview":{"draws":13,"losses":34,"wins":23},"google/gemini-3.1-flash-lite":{"draws":12,"losses":15,"wins":38},"google/gemini-3.5-flash":{"draws":33,"losses":81,"wins":24},"google/gemini-3.5-flash-lite":{"draws":100,"losses":164,"wins":173},"google/gemini-3.6-flash":{"draws":98,"losses":230,"wins":56},"google/gemini-3.8-flash":{"draws":28,"losses":59,"wins":18},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":14},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":24,"losses":37,"wins":11},"gpt-5.4":{"draws":50,"losses":99,"wins":27},"gpt-5.4-mini":{"draws":21,"losses":26,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":47,"wins":27},"gpt-5.5":{"draws":22,"losses":50,"wins":15},"gpt-5.6-luna":{"draws":58,"losses":83,"wins":57},"gpt-5.6-sol":{"draws":33,"losses":129,"wins":22},"gpt-5.6-terra":{"draws":35,"losses":59,"wins":30},"gpt-6-astra":{"draws":5,"losses":91,"wins":4},"gpt-6-luna":{"draws":13,"losses":38,"wins":16},"gpt-6-sol":{"draws":4,"losses":62,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":64,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":21,"wins":41},"inclusionai/ling-3.0-flash":{"draws":41,"losses":27,"wins":46},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":37,"wins":42},"meta/muse-glimmer-30b":{"draws":36,"losses":42,"wins":36},"meta/muse-spark-1.2":{"draws":35,"losses":67,"wins":44},"meta/muse-spark-1.3":{"draws":24,"losses":56,"wins":13},"meta/muse-wonder":{"draws":8,"losses":48,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":18,"wins":24},"mistralai/mistral-large-4-0":{"draws":11,"losses":16,"wins":7},"mistralai/mistral-medium-3-5":{"draws":32,"losses":15,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":5},"moonshotai/kimi-k3":{"draws":50,"losses":110,"wins":24},"nex-agi/nex-n2-pro":{"draws":11,"losses":18,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":24,"wins":28},"o3":{"draws":25,"losses":170,"wins":69},"openai/gpt-oss-120b":{"draws":42,"losses":22,"wins":48},"poolside/laguna-s-2.1":{"draws":53,"losses":42,"wins":65},"qwen/qwen3.7-max":{"draws":14,"losses":34,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":17,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":71,"wins":20},"qwen/qwen3.8-27b":{"draws":9,"losses":42,"wins":11},"qwen/qwen3.8-flash":{"draws":29,"losses":35,"wins":16},"qwen/qwen3.8-max":{"draws":41,"losses":68,"wins":18},"qwen/qwen3.8-max-0902":{"draws":11,"losses":47,"wins":9},"stealth/ox-alpha":{"draws":93,"losses":214,"wins":53},"stealth/space-bunny-alpha":{"draws":18,"losses":23,"wins":18},"stepfun/step-3.7-flash":{"draws":13,"losses":25,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":13},"tencent/hy4-preview":{"draws":36,"losses":65,"wins":15},"thinkingmachines/inkling":{"draws":38,"losses":62,"wins":52},"thinkingmachines/inkling-small":{"draws":35,"losses":42,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":8,"wins":7},"x-ai/grok-4.5":{"draws":45,"losses":129,"wins":34},"x-ai/grok-4.6":{"draws":29,"losses":65,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":56,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":16,"wins":10},"xiaomi/mimo-v2.5":{"draws":47,"losses":38,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":16,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":24,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":35,"wins":4},"z-ai/glm-5.2":{"draws":52,"losses":88,"wins":56},"z-ai/glm-5.3":{"draws":26,"losses":57,"wins":11},"z-ai/glm-5.3-flash":{"draws":24,"losses":65,"wins":23},"z-ai/glm-5.3-flashx":{"draws":20,"losses":44,"wins":7}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":28,"wins":24},"claude-fable-5":{"draws":18,"losses":40,"wins":4},"claude-fable-5-1":{"draws":5,"losses":55,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":26,"wins":4},"claude-opus-4-5":{"draws":37,"losses":49,"wins":16},"claude-opus-4-8":{"draws":13,"losses":26,"wins":5},"claude-opus-5":{"draws":4,"losses":71,"wins":9},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":33,"losses":40,"wins":11},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":57,"losses":41,"wins":14},"deepseek/deepseek-v4-pro":{"draws":26,"losses":38,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":43,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":31,"wins":3},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":20,"losses":24,"wins":4},"google/gemini-3.1-flash-lite":{"draws":14,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":30,"losses":50,"wins":12},"google/gemini-3.5-flash-lite":{"draws":77,"losses":62,"wins":27},"google/gemini-3.6-flash":{"draws":48,"losses":78,"wins":12},"google/gemini-3.8-flash":{"draws":21,"losses":41,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":21,"wins":9},"gpt-5.4":{"draws":21,"losses":35,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":22,"wins":17},"gpt-5.5":{"draws":14,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":36,"losses":34,"wins":18},"gpt-5.6-sol":{"draws":11,"losses":48,"wins":3},"gpt-5.6-terra":{"draws":28,"losses":40,"wins":14},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":14,"losses":27,"wins":5},"gpt-6-sol":{"draws":10,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":34,"losses":18,"wins":16},"inclusionai/ling-3.0-flash":{"draws":24,"losses":9,"wins":11},"meituan/longcat-2.0":{"draws":26,"losses":23,"wins":23},"meta/muse-glimmer-30b":{"draws":25,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":18,"losses":34,"wins":14},"meta/muse-spark-1.3":{"draws":24,"losses":35,"wins":7},"meta/muse-wonder":{"draws":8,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":12,"wins":8},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":6},"mistralai/mistral-medium-3-5":{"draws":26,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":41,"wins":9},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":14,"wins":7},"o3":{"draws":20,"losses":67,"wins":7},"openai/gpt-oss-120b":{"draws":40,"losses":26,"wins":14},"poolside/laguna-s-2.1":{"draws":37,"losses":22,"wins":13},"qwen/qwen3.7-max":{"draws":11,"losses":15,"wins":4},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":50,"wins":4},"qwen/qwen3.8-27b":{"draws":12,"losses":24,"wins":4},"qwen/qwen3.8-flash":{"draws":22,"losses":18,"wins":12},"qwen/qwen3.8-max":{"draws":24,"losses":37,"wins":15},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"stealth/ox-alpha":{"draws":72,"losses":149,"wins":25},"stealth/space-bunny-alpha":{"draws":14,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":10},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":23,"losses":48,"wins":5},"thinkingmachines/inkling":{"draws":27,"losses":22,"wins":23},"thinkingmachines/inkling-small":{"draws":42,"losses":26,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":16,"losses":45,"wins":7},"x-ai/grok-4.6":{"draws":24,"losses":38,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":24,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":3},"z-ai/glm-5.2":{"draws":58,"losses":50,"wins":22},"z-ai/glm-5.3":{"draws":13,"losses":40,"wins":7},"z-ai/glm-5.3-flash":{"draws":26,"losses":43,"wins":9},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":19,"wins":28},"claude-fable-5":{"draws":13,"losses":43,"wins":24},"claude-fable-5-1":{"draws":3,"losses":75,"wins":10},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":32,"losses":22,"wins":68},"claude-opus-4-8":{"draws":10,"losses":16,"wins":16},"claude-opus-5":{"draws":13,"losses":62,"wins":15},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":39,"losses":33,"wins":48},"claude-sonnet-5-5":{"draws":14,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":29,"losses":8,"wins":49},"deepseek/deepseek-v4-pro":{"draws":10,"losses":27,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":17,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":11,"wins":18},"fireworks/ember-1":{"draws":11,"losses":12,"wins":19},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":21,"losses":24,"wins":43},"google/gemini-3.5-flash-lite":{"draws":51,"losses":26,"wins":121},"google/gemini-3.6-flash":{"draws":29,"losses":49,"wins":112},"google/gemini-3.8-flash":{"draws":10,"losses":23,"wins":41},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":10},"gpt-4.1":{"draws":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":15,"losses":11,"wins":22},"gpt-5.4":{"draws":28,"losses":43,"wins":41},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":26},"gpt-5.5":{"draws":9,"losses":15,"wins":16},"gpt-5.6-luna":{"draws":36,"losses":17,"wins":65},"gpt-5.6-sol":{"draws":13,"losses":71,"wins":40},"gpt-5.6-terra":{"draws":33,"losses":16,"wins":31},"gpt-6-astra":{"draws":8,"losses":68,"wins":2},"gpt-6-luna":{"draws":15,"losses":7,"wins":18},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":19},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":24,"losses":13,"wins":43},"meta/muse-glimmer-30b":{"draws":17,"losses":4,"wins":41},"meta/muse-spark-1.2":{"draws":15,"losses":11,"wins":28},"meta/muse-spark-1.3":{"draws":15,"losses":18,"wins":29},"meta/muse-wonder":{"draws":8,"losses":17,"wins":15},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":10,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":20,"losses":33,"wins":33},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":2,"wins":23},"o3":{"draws":16,"losses":40,"wins":56},"openai/gpt-oss-120b":{"draws":22,"losses":4,"wins":38},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":46},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":23},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":26,"wins":28},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":11},"qwen/qwen3.8-flash":{"draws":18,"losses":13,"wins":19},"qwen/qwen3.8-max":{"draws":25,"losses":25,"wins":23},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":16},"stealth/ox-alpha":{"draws":68,"losses":106,"wins":75},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":24},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":16},"tencent/hy4-preview":{"draws":16,"losses":28,"wins":26},"thinkingmachines/inkling":{"draws":22,"losses":6,"wins":46},"thinkingmachines/inkling-small":{"draws":28,"losses":6,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":22,"losses":44,"wins":32},"x-ai/grok-4.6":{"draws":21,"losses":37,"wins":24},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":15},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":22,"losses":33,"wins":65},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":24},"z-ai/glm-5.3-flash":{"draws":13,"losses":29,"wins":32},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":11,"wins":42},"claude-fable-5":{"draws":16,"losses":42,"wins":32},"claude-fable-5-1":{"draws":7,"losses":90,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":19,"wins":23},"claude-opus-4-5":{"draws":18,"losses":18,"wins":74},"claude-opus-4-8":{"draws":8,"losses":15,"wins":25},"claude-opus-5":{"draws":16,"losses":57,"wins":27},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":22,"losses":17,"wins":45},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":74},"deepseek/deepseek-v4-pro":{"draws":8,"losses":15,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":23},"fireworks/ember-1":{"draws":11,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":10,"losses":19,"wins":71},"google/gemini-3.5-flash-lite":{"draws":16,"losses":20,"wins":88},"google/gemini-3.6-flash":{"draws":22,"losses":47,"wins":69},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":50},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":5,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":8,"losses":8,"wins":34},"gpt-5.4":{"draws":13,"losses":33,"wins":36},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":48},"gpt-5.6-sol":{"draws":19,"losses":40,"wins":35},"gpt-5.6-terra":{"draws":24,"losses":17,"wins":45},"gpt-6-astra":{"draws":11,"losses":77,"wins":8},"gpt-6-luna":{"draws":5,"losses":10,"wins":31},"gpt-6-sol":{"draws":8,"losses":33,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":34,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":28},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":51},"meta/muse-glimmer-30b":{"draws":14,"losses":1,"wins":41},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":34},"meta/muse-spark-1.3":{"draws":8,"losses":12,"wins":20},"meta/muse-wonder":{"draws":10,"losses":20,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":23},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":15,"wins":49},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":32},"o3":{"draws":5,"losses":18,"wins":75},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":43},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":41},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":10,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":36,"wins":39},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":26},"qwen/qwen3.8-flash":{"draws":15,"losses":12,"wins":31},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":50},"qwen/qwen3.8-max-0902":{"draws":9,"losses":14,"wins":25},"stealth/ox-alpha":{"draws":50,"losses":86,"wins":140},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":23},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":44},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":51},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":28,"wins":42},"x-ai/grok-4.6":{"draws":15,"losses":39,"wins":36},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":14,"losses":1,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":12},"z-ai/glm-5.2":{"draws":25,"losses":24,"wins":73},"z-ai/glm-5.3":{"draws":9,"losses":33,"wins":30},"z-ai/glm-5.3-flash":{"draws":16,"losses":33,"wins":39},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":9,"losses":15,"wins":22},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":11,"wins":25},"claude-opus-4-5":{"draws":11,"losses":20,"wins":43},"claude-opus-4-8":{"draws":5,"losses":15,"wins":20},"claude-opus-5":{"draws":7,"losses":48,"wins":19},"claude-opus-5-5":{"draws":5,"losses":32,"wins":7},"claude-sonnet-5":{"draws":7,"losses":12,"wins":25},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":15,"wins":19},"fireworks/ember-1":{"draws":8,"losses":15,"wins":23},"gemini-3.1-pro-preview":{"draws":6,"losses":4,"wins":32},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":8,"wins":38},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":53},"google/gemini-3.6-flash":{"draws":11,"losses":27,"wins":40},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":26},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":2,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":20},"gpt-5.4":{"draws":6,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":17},"gpt-5.4-nano":{"draws":3,"losses":8,"wins":29},"gpt-5.5":{"draws":11,"losses":12,"wins":19},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":26},"gpt-5.6-sol":{"draws":8,"losses":18,"wins":20},"gpt-5.6-terra":{"draws":3,"losses":16,"wins":23},"gpt-6-astra":{"draws":3,"losses":35,"wins":4},"gpt-6-luna":{"draws":9,"losses":12,"wins":25},"gpt-6-sol":{"draws":8,"losses":24,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":21},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":21},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-wonder":{"draws":5,"losses":13,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":16},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":25},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":24},"o3":{"draws":2,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":14,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":21},"qwen/qwen3.8-max-0902":{"draws":6,"losses":14,"wins":24},"stealth/ox-alpha":{"draws":29,"losses":45,"wins":72},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":14},"tencent/hy4-preview":{"draws":5,"losses":16,"wins":19},"thinkingmachines/inkling":{"draws":8,"losses":11,"wins":33},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":28},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":8,"wins":27},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":20},"x-ai/grok-4.7":{"draws":7,"losses":22,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":14},"z-ai/glm-5.2":{"draws":23,"losses":15,"wins":52},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":20},"z-ai/glm-5.3-flash":{"draws":8,"losses":12,"wins":24},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":22}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":15,"wins":9},"claude-fable-5":{"draws":10,"losses":31,"wins":1},"claude-fable-5-1":{"draws":1,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":29,"wins":5},"claude-opus-4-5":{"draws":34,"losses":62,"wins":6},"claude-opus-4-8":{"draws":25,"losses":37,"wins":4},"claude-opus-5":{"draws":9,"losses":76,"wins":5},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":13,"losses":28,"wins":5},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":2},"cohere/north-mini-code":{"draws":9,"losses":9,"wins":12},"deepseek/deepseek-v4-flash":{"draws":37,"losses":36,"wins":27},"deepseek/deepseek-v4-pro":{"draws":11,"losses":26,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":32,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":12,"losses":29,"wins":1},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":7},"google/gemini-3.1-flash-lite":{"draws":19,"losses":40,"wins":23},"google/gemini-3.5-flash":{"draws":22,"losses":28,"wins":8},"google/gemini-3.5-flash-lite":{"draws":31,"losses":46,"wins":19},"google/gemini-3.6-flash":{"draws":25,"losses":51,"wins":10},"google/gemini-3.8-flash":{"draws":15,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":7},"gpt-4.1":{"draws":14,"losses":12,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":26,"losses":30,"wins":12},"gpt-5.4":{"draws":13,"losses":25,"wins":2},"gpt-5.4-mini":{"draws":22,"losses":32,"wins":16},"gpt-5.4-nano":{"draws":27,"losses":56,"wins":17},"gpt-5.5":{"draws":25,"losses":31,"wins":6},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":11,"losses":24,"wins":5},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":36,"losses":15,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":41,"wins":21},"meta/muse-glimmer-30b":{"draws":16,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":31,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":2},"meta/muse-wonder":{"draws":7,"losses":27,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":2},"mistralai/mistral-large-4-0":{"draws":7,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":11,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":17,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":26,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":13,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":27,"wins":13},"o3":{"draws":19,"losses":49,"wins":12},"openai/gpt-oss-120b":{"draws":16,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":32,"losses":30,"wins":10},"qwen/qwen3.7-max":{"draws":21,"losses":24,"wins":13},"qwen/qwen3.7-plus":{"draws":11,"losses":22,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":13,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":30,"losses":87,"wins":9},"stealth/space-bunny-alpha":{"draws":11,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":24,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":31,"wins":14},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":46,"wins":2},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":16,"losses":18,"wins":4},"xiaomi/mimo-v2.5":{"draws":62,"losses":55,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":24,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":47,"losses":60,"wins":9},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":5},"z-ai/glm-5.3-flashx":{"draws":14,"losses":26,"wins":2}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":16},"claude-fable-5":{"draws":9,"losses":21,"wins":8},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":29,"losses":50,"wins":29},"claude-opus-4-8":{"draws":16,"losses":32,"wins":14},"claude-opus-5":{"draws":13,"losses":112,"wins":7},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"fireworks/ember-1":{"draws":12,"losses":13,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":36},"google/gemini-3.5-flash":{"draws":13,"losses":16,"wins":19},"google/gemini-3.5-flash-lite":{"draws":18,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":22,"losses":41,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":11,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":21,"wins":24},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":11,"wins":25},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":28},"gpt-5.5":{"draws":30,"losses":17,"wins":19},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":12},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":22},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":25},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":12,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":33},"o3":{"draws":7,"losses":29,"wins":32},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":17},"poolside/laguna-s-2.1":{"draws":17,"losses":28,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":16,"wins":12},"qwen/qwen3.7-plus":{"draws":21,"losses":4,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":9,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":25,"losses":50,"wins":31},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":15},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":8},"thinkingmachines/inkling":{"draws":13,"losses":17,"wins":30},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":22},"xiaomi/mimo-v2.5":{"draws":50,"losses":22,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":23,"losses":43,"wins":42},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":37},"claude-fable-5":{"draws":25,"losses":55,"wins":2},"claude-fable-5-1":{"draws":10,"losses":80,"wins":4},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":11},"claude-opus-4-5":{"draws":60,"losses":56,"wins":44},"claude-opus-4-8":{"draws":15,"losses":20,"wins":17},"claude-opus-5":{"draws":20,"losses":81,"wins":9},"claude-opus-5-5":{"draws":2,"losses":44,"wins":6},"claude-sonnet-5":{"draws":52,"losses":37,"wins":51},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":33,"losses":23,"wins":52},"deepseek/deepseek-v4-pro":{"draws":24,"losses":24,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":28,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":15,"wins":13},"fireworks/ember-1":{"draws":19,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":39,"losses":36,"wins":27},"google/gemini-3.5-flash-lite":{"draws":102,"losses":60,"wins":132},"google/gemini-3.6-flash":{"draws":91,"losses":113,"wins":78},"google/gemini-3.8-flash":{"draws":35,"losses":48,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":17,"wins":14},"gpt-5.4":{"draws":41,"losses":80,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":12,"wins":16},"gpt-5.4-nano":{"draws":16,"losses":18,"wins":30},"gpt-5.5":{"draws":26,"losses":17,"wins":15},"gpt-5.6-luna":{"draws":52,"losses":33,"wins":51},"gpt-5.6-sol":{"draws":24,"losses":86,"wins":24},"gpt-5.6-terra":{"draws":33,"losses":26,"wins":27},"gpt-6-astra":{"draws":3,"losses":76,"wins":7},"gpt-6-luna":{"draws":17,"losses":15,"wins":14},"gpt-6-sol":{"draws":6,"losses":34,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":38,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":4,"wins":30},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":41},"meituan/longcat-2.0":{"draws":40,"losses":10,"wins":66},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":28},"meta/muse-spark-1.2":{"draws":24,"losses":37,"wins":39},"meta/muse-spark-1.3":{"draws":18,"losses":38,"wins":18},"meta/muse-wonder":{"draws":10,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":17},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":25,"losses":5,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":11,"wins":3},"moonshotai/kimi-k3":{"draws":29,"losses":26,"wins":19},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":10,"wins":19},"o3":{"draws":26,"losses":76,"wins":64},"openai/gpt-oss-120b":{"draws":28,"losses":10,"wins":36},"poolside/laguna-s-2.1":{"draws":43,"losses":9,"wins":58},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":10,"losses":10,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":36,"wins":22},"qwen/qwen3.8-27b":{"draws":14,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":25,"losses":9,"wins":26},"qwen/qwen3.8-max":{"draws":32,"losses":27,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":77,"losses":121,"wins":89},"stealth/space-bunny-alpha":{"draws":16,"losses":7,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":28,"losses":30,"wins":26},"thinkingmachines/inkling":{"draws":37,"losses":10,"wins":57},"thinkingmachines/inkling-small":{"draws":34,"losses":8,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":38,"losses":65,"wins":29},"x-ai/grok-4.6":{"draws":39,"losses":32,"wins":15},"x-ai/grok-4.7":{"draws":7,"losses":29,"wins":6},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":15,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":48,"losses":37,"wins":45},"z-ai/glm-5.3":{"draws":17,"losses":35,"wins":18},"z-ai/glm-5.3-flash":{"draws":28,"losses":26,"wins":32},"z-ai/glm-5.3-flashx":{"draws":17,"losses":22,"wins":9}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":24,"wins":4},"claude-fable-5":{"draws":3,"losses":27,"wins":0},"claude-fable-5-1":{"draws":1,"losses":33,"wins":0},"claude-haiku-5-5":{"draws":1,"losses":24,"wins":3},"claude-opus-4-5":{"draws":6,"losses":64,"wins":4},"claude-opus-4-8":{"draws":8,"losses":36,"wins":0},"claude-opus-5":{"draws":0,"losses":59,"wins":1},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":9,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":13,"losses":16,"wins":9},"deepseek/deepseek-v4-flash":{"draws":5,"losses":37,"wins":30},"deepseek/deepseek-v4-pro":{"draws":2,"losses":23,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":27,"wins":2},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":24,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":32,"wins":8},"google/gemini-3.5-flash-lite":{"draws":9,"losses":43,"wins":14},"google/gemini-3.6-flash":{"draws":2,"losses":56,"wins":4},"google/gemini-3.8-flash":{"draws":1,"losses":27,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":14,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":3,"losses":37,"wins":10},"gpt-5.4":{"draws":4,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":19,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":38,"wins":23},"gpt-5.5":{"draws":2,"losses":49,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":21,"wins":5},"gpt-5.6-sol":{"draws":1,"losses":30,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":26,"wins":1},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":21,"wins":5},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":19,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":49,"wins":22},"meta/muse-glimmer-30b":{"draws":7,"losses":20,"wins":3},"meta/muse-spark-1.2":{"draws":1,"losses":27,"wins":2},"meta/muse-spark-1.3":{"draws":0,"losses":28,"wins":0},"meta/muse-wonder":{"draws":1,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":25,"wins":10},"mistralai/mistral-large-4-0":{"draws":1,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":14,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":39,"wins":12},"o3":{"draws":2,"losses":58,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":15,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":31,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":26,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":16,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":4,"losses":22,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":22,"wins":2},"stealth/ox-alpha":{"draws":14,"losses":86,"wins":12},"stealth/space-bunny-alpha":{"draws":3,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":12,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":23,"wins":14},"thinkingmachines/inkling-small":{"draws":5,"losses":20,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":6,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":35,"wins":2},"x-ai/grok-4.6":{"draws":4,"losses":28,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":15,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":55,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":27,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":16,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":47,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":29,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":26,"wins":3},"z-ai/glm-5.3-flashx":{"draws":2,"losses":27,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":8},"claude-fable-5":{"draws":5,"losses":22,"wins":3},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":16,"wins":7},"claude-opus-4-5":{"draws":33,"losses":25,"wins":20},"claude-opus-4-8":{"draws":10,"losses":37,"wins":1},"claude-opus-5":{"draws":6,"losses":65,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":11,"losses":12,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":26,"losses":16,"wins":20},"deepseek/deepseek-v4-pro":{"draws":8,"losses":16,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":6},"fireworks/ember-1":{"draws":11,"losses":13,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":7,"wins":23},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":6},"google/gemini-3.5-flash-lite":{"draws":24,"losses":18,"wins":20},"google/gemini-3.6-flash":{"draws":17,"losses":32,"wins":11},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":4},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":20,"wins":13},"gpt-5.4":{"draws":9,"losses":18,"wins":3},"gpt-5.4-mini":{"draws":22,"losses":10,"wins":14},"gpt-5.4-nano":{"draws":26,"losses":24,"wins":30},"gpt-5.5":{"draws":18,"losses":26,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":10},"gpt-6-astra":{"draws":3,"losses":26,"wins":1},"gpt-6-luna":{"draws":11,"losses":11,"wins":6},"gpt-6-sol":{"draws":2,"losses":26,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":11},"inclusionai/ling-3.0-flash":{"draws":16,"losses":14,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":13,"wins":21},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":7},"meta/muse-wonder":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":15,"losses":13,"wins":8},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":8,"wins":12},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":6,"wins":12},"o3":{"draws":13,"losses":30,"wins":9},"openai/gpt-oss-120b":{"draws":11,"losses":11,"wins":4},"poolside/laguna-s-2.1":{"draws":28,"losses":12,"wins":8},"qwen/qwen3.7-max":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":15,"wins":2},"stealth/ox-alpha":{"draws":22,"losses":40,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":14},"tencent/hy3-preview":{"draws":17,"losses":9,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":11,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":18,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":46,"losses":28,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":21,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":25,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":11},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":9}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":11,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":25,"wins":7},"claude-opus-4-5":{"draws":31,"losses":55,"wins":28},"claude-opus-4-8":{"draws":15,"losses":33,"wins":16},"claude-opus-5":{"draws":9,"losses":77,"wins":8},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":11,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":17},"deepseek/deepseek-v4-flash":{"draws":15,"losses":18,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":10},"fireworks/ember-1":{"draws":13,"losses":16,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":12,"wins":17},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":35},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":55},"google/gemini-3.6-flash":{"draws":26,"losses":39,"wins":31},"google/gemini-3.8-flash":{"draws":5,"losses":25,"wins":10},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":12},"gpt-4.1":{"draws":8,"losses":4,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":24,"wins":14},"gpt-5.4":{"draws":11,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":21,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":30,"wins":39},"gpt-5.5":{"draws":24,"losses":31,"wins":9},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":7},"gpt-6-astra":{"draws":1,"losses":39,"wins":0},"gpt-6-luna":{"draws":7,"losses":16,"wins":11},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":17,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":9},"meta/muse-wonder":{"draws":2,"losses":26,"wins":4},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":26},"mistralai/mistral-large-4-0":{"draws":7,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":14,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":10,"wins":18},"o3":{"draws":8,"losses":24,"wins":20},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":35},"qwen/qwen3.7-max":{"draws":15,"losses":15,"wins":20},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":3,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":9,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":20,"losses":64,"wins":29},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":7},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":18},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":21},"xiaomi/mimo-v2.5":{"draws":41,"losses":9,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":24,"losses":42,"wins":40},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":15,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":22,"wins":11}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":26,"wins":24},"claude-fable-5":{"draws":21,"losses":45,"wins":2},"claude-fable-5-1":{"draws":7,"losses":60,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":3},"claude-opus-4-5":{"draws":34,"losses":59,"wins":9},"claude-opus-4-8":{"draws":16,"losses":29,"wins":1},"claude-opus-5":{"draws":12,"losses":67,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":33,"losses":44,"wins":13},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":47,"losses":35,"wins":30},"deepseek/deepseek-v4-pro":{"draws":26,"losses":39,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":29,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":26,"wins":8},"fireworks/ember-1":{"draws":19,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":23,"wins":9},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":17},"google/gemini-3.5-flash":{"draws":29,"losses":47,"wins":16},"google/gemini-3.5-flash-lite":{"draws":56,"losses":63,"wins":43},"google/gemini-3.6-flash":{"draws":50,"losses":67,"wins":19},"google/gemini-3.8-flash":{"draws":19,"losses":49,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":22,"wins":5},"gpt-5.4":{"draws":36,"losses":36,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":20},"gpt-5.5":{"draws":21,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":40,"losses":36,"wins":16},"gpt-5.6-sol":{"draws":10,"losses":59,"wins":3},"gpt-5.6-terra":{"draws":32,"losses":48,"wins":4},"gpt-6-astra":{"draws":3,"losses":57,"wins":0},"gpt-6-luna":{"draws":14,"losses":23,"wins":9},"gpt-6-sol":{"draws":6,"losses":39,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":14,"wins":21},"inclusionai/ling-3.0-flash":{"draws":20,"losses":7,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":31,"wins":14},"meta/muse-glimmer-30b":{"draws":38,"losses":22,"wins":24},"meta/muse-spark-1.2":{"draws":22,"losses":39,"wins":7},"meta/muse-spark-1.3":{"draws":20,"losses":42,"wins":6},"meta/muse-wonder":{"draws":9,"losses":33,"wins":2},"minimax/minimax-m3":{"draws":11,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-medium-3-5":{"draws":25,"losses":14,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":40,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":13,"wins":14},"o3":{"draws":15,"losses":69,"wins":8},"openai/gpt-oss-120b":{"draws":20,"losses":18,"wins":10},"poolside/laguna-s-2.1":{"draws":30,"losses":25,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":25,"wins":8},"qwen/qwen3.8-flash":{"draws":23,"losses":21,"wins":10},"qwen/qwen3.8-max":{"draws":37,"losses":41,"wins":4},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":1},"stealth/ox-alpha":{"draws":77,"losses":160,"wins":25},"stealth/space-bunny-alpha":{"draws":14,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":15,"wins":6},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":31,"losses":35,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":23,"wins":24},"thinkingmachines/inkling-small":{"draws":39,"losses":27,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":24,"losses":45,"wins":3},"x-ai/grok-4.6":{"draws":30,"losses":39,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":26,"losses":25,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":21,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":50,"losses":58,"wins":28},"z-ai/glm-5.3":{"draws":17,"losses":41,"wins":4},"z-ai/glm-5.3-flash":{"draws":16,"losses":51,"wins":9},"z-ai/glm-5.3-flashx":{"draws":11,"losses":29,"wins":8}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":39,"wins":25},"claude-fable-5":{"draws":31,"losses":59,"wins":12},"claude-fable-5-1":{"draws":8,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":19,"losses":27,"wins":12},"claude-opus-4-5":{"draws":88,"losses":110,"wins":16},"claude-opus-4-8":{"draws":31,"losses":36,"wins":5},"claude-opus-5":{"draws":18,"losses":132,"wins":10},"claude-opus-5-5":{"draws":5,"losses":69,"wins":0},"claude-sonnet-5":{"draws":69,"losses":96,"wins":15},"claude-sonnet-5-5":{"draws":15,"losses":40,"wins":11},"cohere/north-mini-code":{"draws":14,"losses":14,"wins":4},"deepseek/deepseek-v4-flash":{"draws":81,"losses":48,"wins":31},"deepseek/deepseek-v4-pro":{"draws":49,"losses":40,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":32,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":25,"wins":9},"fireworks/ember-1":{"draws":30,"losses":27,"wins":9},"gemini-3.1-pro-preview":{"draws":27,"losses":28,"wins":11},"google/gemini-3.1-flash-lite":{"draws":17,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":51,"losses":61,"wins":20},"google/gemini-3.5-flash-lite":{"draws":208,"losses":110,"wins":118},"google/gemini-3.6-flash":{"draws":163,"losses":167,"wins":38},"google/gemini-3.8-flash":{"draws":31,"losses":63,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":8},"gpt-4.1":{"draws":13,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":1},"gpt-5":{"draws":34,"losses":25,"wins":11},"gpt-5.4":{"draws":64,"losses":85,"wins":11},"gpt-5.4-mini":{"draws":34,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":32,"losses":28,"wins":28},"gpt-5.5":{"draws":29,"losses":32,"wins":13},"gpt-5.6-luna":{"draws":82,"losses":67,"wins":41},"gpt-5.6-sol":{"draws":34,"losses":144,"wins":2},"gpt-5.6-terra":{"draws":49,"losses":50,"wins":7},"gpt-6-astra":{"draws":13,"losses":83,"wins":0},"gpt-6-luna":{"draws":21,"losses":34,"wins":7},"gpt-6-sol":{"draws":12,"losses":51,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":61,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":50,"losses":20,"wins":20},"inclusionai/ling-3.0-flash":{"draws":54,"losses":12,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":72,"losses":65,"wins":53},"meta/muse-glimmer-30b":{"draws":63,"losses":20,"wins":33},"meta/muse-spark-1.2":{"draws":43,"losses":82,"wins":11},"meta/muse-spark-1.3":{"draws":37,"losses":44,"wins":13},"meta/muse-wonder":{"draws":12,"losses":42,"wins":6},"minimax/minimax-m3":{"draws":22,"losses":12,"wins":16},"mistralai/mistral-large-4-0":{"draws":18,"losses":18,"wins":4},"mistralai/mistral-medium-3-5":{"draws":44,"losses":14,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":71,"losses":99,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":8,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":17,"wins":9},"o3":{"draws":51,"losses":100,"wins":49},"openai/gpt-oss-120b":{"draws":67,"losses":29,"wins":20},"poolside/laguna-s-2.1":{"draws":63,"losses":39,"wins":30},"qwen/qwen3.7-max":{"draws":25,"losses":20,"wins":11},"qwen/qwen3.7-plus":{"draws":25,"losses":10,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":55,"wins":10},"qwen/qwen3.8-27b":{"draws":16,"losses":29,"wins":7},"qwen/qwen3.8-flash":{"draws":38,"losses":27,"wins":9},"qwen/qwen3.8-max":{"draws":50,"losses":45,"wins":19},"qwen/qwen3.8-max-0902":{"draws":26,"losses":35,"wins":5},"stealth/ox-alpha":{"draws":127,"losses":196,"wins":45},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":12},"stepfun/step-3.7-flash":{"draws":16,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":8},"tencent/hy4-preview":{"draws":43,"losses":50,"wins":17},"thinkingmachines/inkling":{"draws":67,"losses":42,"wins":57},"thinkingmachines/inkling-small":{"draws":67,"losses":19,"wins":47},"unbiased/pareto-26.10-preview":{"draws":0,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":68,"losses":96,"wins":22},"x-ai/grok-4.6":{"draws":37,"losses":63,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":46,"wins":5},"x-ai/grok-build-0.1":{"draws":25,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":56,"losses":28,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":17,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":26,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":27,"wins":5},"z-ai/glm-5.2":{"draws":105,"losses":57,"wins":32},"z-ai/glm-5.3":{"draws":32,"losses":52,"wins":10},"z-ai/glm-5.3-flash":{"draws":46,"losses":52,"wins":14},"z-ai/glm-5.3-flashx":{"draws":27,"losses":31,"wins":8}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":6,"wins":19},"claude-fable-5":{"draws":7,"losses":28,"wins":7},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":12},"claude-opus-4-5":{"draws":49,"losses":51,"wins":34},"claude-opus-4-8":{"draws":27,"losses":30,"wins":24},"claude-opus-5":{"draws":12,"losses":90,"wins":20},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":11},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":12,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":39,"losses":13,"wins":26},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":13,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":12,"wins":12},"fireworks/ember-1":{"draws":13,"losses":17,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":16},"google/gemini-3.1-flash-lite":{"draws":25,"losses":6,"wins":23},"google/gemini-3.5-flash":{"draws":24,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":34,"losses":29,"wins":33},"google/gemini-3.6-flash":{"draws":24,"losses":44,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":10},"gpt-4.1":{"draws":18,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":30,"losses":26,"wins":14},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":18,"losses":14,"wins":20},"gpt-5.4-nano":{"draws":25,"losses":27,"wins":40},"gpt-5.5":{"draws":28,"losses":35,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":29,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":23,"wins":12},"gpt-6-astra":{"draws":5,"losses":38,"wins":1},"gpt-6-luna":{"draws":9,"losses":19,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":28,"losses":6,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":9,"wins":41},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":14},"meta/muse-spark-1.2":{"draws":5,"losses":32,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":19,"wins":13},"meta/muse-wonder":{"draws":6,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":19,"losses":15,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":14,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":11,"losses":23,"wins":12},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":15,"wins":23},"o3":{"draws":24,"losses":25,"wins":33},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":26,"losses":8,"wins":26},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":13,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":36,"losses":58,"wins":32},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":27},"tencent/hy3-preview":{"draws":16,"losses":9,"wins":15},"tencent/hy4-preview":{"draws":8,"losses":25,"wins":11},"thinkingmachines/inkling":{"draws":25,"losses":9,"wins":38},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":19,"losses":28,"wins":17},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":18,"losses":10,"wins":10},"xiaomi/mimo-v2.5":{"draws":58,"losses":25,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":12,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":37,"losses":53,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":18,"wins":11},"z-ai/glm-5.3-flash":{"draws":16,"losses":14,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":13},"claude-fable-5":{"draws":7,"losses":24,"wins":5},"claude-fable-5-1":{"draws":0,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":22,"wins":7},"claude-opus-4-5":{"draws":23,"losses":36,"wins":33},"claude-opus-4-8":{"draws":15,"losses":38,"wins":15},"claude-opus-5":{"draws":16,"losses":71,"wins":1},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":11,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":16},"deepseek/deepseek-v4-flash":{"draws":24,"losses":25,"wins":27},"deepseek/deepseek-v4-pro":{"draws":8,"losses":16,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":18,"wins":5},"fireworks/ember-1":{"draws":11,"losses":16,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":30},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":13},"google/gemini-3.5-flash-lite":{"draws":29,"losses":13,"wins":38},"google/gemini-3.6-flash":{"draws":19,"losses":45,"wins":20},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":10,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":23,"wins":15},"gpt-5.4":{"draws":8,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":28},"gpt-5.4-nano":{"draws":18,"losses":23,"wins":47},"gpt-5.5":{"draws":31,"losses":25,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":10,"wins":10},"gpt-6-astra":{"draws":2,"losses":36,"wins":0},"gpt-6-luna":{"draws":9,"losses":15,"wins":10},"gpt-6-sol":{"draws":3,"losses":27,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":21,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":20,"losses":16,"wins":36},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":11},"meta/muse-spark-1.2":{"draws":6,"losses":32,"wins":8},"meta/muse-spark-1.3":{"draws":10,"losses":15,"wins":11},"meta/muse-wonder":{"draws":11,"losses":25,"wins":0},"minimax/minimax-m3":{"draws":11,"losses":12,"wins":23},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":1},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":15},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":16,"wins":26},"o3":{"draws":11,"losses":33,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":15},"poolside/laguna-s-2.1":{"draws":32,"losses":18,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":19,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":22,"losses":66,"wins":20},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":31},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":37,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":10,"losses":2,"wins":18},"xiaomi/mimo-v2.5":{"draws":42,"losses":9,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":12,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":43,"wins":28},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":18,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":9}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":24,"wins":26},"claude-fable-5":{"draws":25,"losses":51,"wins":8},"claude-fable-5-1":{"draws":12,"losses":76,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":22,"wins":8},"claude-opus-4-5":{"draws":54,"losses":37,"wins":17},"claude-opus-4-8":{"draws":23,"losses":20,"wins":9},"claude-opus-5":{"draws":10,"losses":66,"wins":12},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":39,"losses":38,"wins":17},"claude-sonnet-5-5":{"draws":14,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":48,"losses":29,"wins":35},"deepseek/deepseek-v4-pro":{"draws":29,"losses":33,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":38,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":22,"wins":10},"fireworks/ember-1":{"draws":27,"losses":19,"wins":2},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":31,"losses":45,"wins":26},"google/gemini-3.5-flash-lite":{"draws":61,"losses":38,"wins":53},"google/gemini-3.6-flash":{"draws":47,"losses":63,"wins":36},"google/gemini-3.8-flash":{"draws":25,"losses":43,"wins":14},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":8},"gpt-4.1":{"draws":10,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":19,"losses":14,"wins":9},"gpt-5.4":{"draws":27,"losses":43,"wins":14},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":20,"losses":17,"wins":19},"gpt-5.5":{"draws":19,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":45,"losses":18,"wins":25},"gpt-5.6-sol":{"draws":15,"losses":61,"wins":12},"gpt-5.6-terra":{"draws":44,"losses":22,"wins":24},"gpt-6-astra":{"draws":5,"losses":73,"wins":2},"gpt-6-luna":{"draws":14,"losses":18,"wins":14},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":22,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":15,"wins":36},"meta/muse-glimmer-30b":{"draws":46,"losses":4,"wins":30},"meta/muse-spark-1.2":{"draws":22,"losses":29,"wins":15},"meta/muse-spark-1.3":{"draws":24,"losses":42,"wins":10},"meta/muse-wonder":{"draws":8,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":25,"losses":2,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":24,"losses":38,"wins":14},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":9,"wins":11},"o3":{"draws":23,"losses":44,"wins":35},"openai/gpt-oss-120b":{"draws":45,"losses":7,"wins":30},"poolside/laguna-s-2.1":{"draws":29,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":17,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":26,"wins":11},"qwen/qwen3.8-27b":{"draws":18,"losses":13,"wins":11},"qwen/qwen3.8-flash":{"draws":24,"losses":19,"wins":13},"qwen/qwen3.8-max":{"draws":38,"losses":25,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":97,"losses":125,"wins":59},"stealth/space-bunny-alpha":{"draws":18,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":27,"losses":36,"wins":23},"thinkingmachines/inkling":{"draws":27,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":38,"losses":12,"wins":42},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":43,"wins":13},"x-ai/grok-4.6":{"draws":27,"losses":42,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":41,"losses":19,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":15,"wins":6},"z-ai/glm-5.2":{"draws":66,"losses":39,"wins":31},"z-ai/glm-5.3":{"draws":16,"losses":42,"wins":10},"z-ai/glm-5.3-flash":{"draws":22,"losses":44,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":26,"wins":12}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":16},"claude-fable-5":{"draws":12,"losses":27,"wins":3},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":9},"claude-opus-4-5":{"draws":26,"losses":14,"wins":28},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":14,"losses":51,"wins":5},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":14,"losses":14,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":28,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":14},"fireworks/ember-1":{"draws":14,"losses":13,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":17,"wins":37},"google/gemini-3.6-flash":{"draws":18,"losses":36,"wins":20},"google/gemini-3.8-flash":{"draws":6,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":13},"gpt-5.4":{"draws":10,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":20},"gpt-5.5":{"draws":17,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":6},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":5,"losses":32,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":10},"meta/muse-wonder":{"draws":10,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":16},"o3":{"draws":7,"losses":20,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":15,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"stealth/ox-alpha":{"draws":40,"losses":59,"wins":41},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":15,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":15,"losses":6,"wins":29},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":16,"losses":17,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":6}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":8,"wins":40},"claude-fable-5":{"draws":28,"losses":32,"wins":26},"claude-fable-5-1":{"draws":3,"losses":90,"wins":7},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":17},"claude-opus-4-5":{"draws":33,"losses":19,"wins":52},"claude-opus-4-8":{"draws":21,"losses":12,"wins":17},"claude-opus-5":{"draws":14,"losses":70,"wins":12},"claude-opus-5-5":{"draws":6,"losses":44,"wins":2},"claude-sonnet-5":{"draws":24,"losses":17,"wins":41},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":40,"losses":8,"wins":54},"deepseek/deepseek-v4-pro":{"draws":18,"losses":14,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":11,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":15,"wins":15},"fireworks/ember-1":{"draws":17,"losses":10,"wins":21},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":14,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":38,"losses":22,"wins":42},"google/gemini-3.5-flash-lite":{"draws":52,"losses":8,"wins":70},"google/gemini-3.6-flash":{"draws":47,"losses":43,"wins":56},"google/gemini-3.8-flash":{"draws":25,"losses":21,"wins":40},"google/gemma-4-31b-it":{"draws":12,"losses":1,"wins":13},"gpt-4.1":{"draws":6,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":20,"losses":8,"wins":22},"gpt-5.4":{"draws":22,"losses":30,"wins":30},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":27},"gpt-5.5":{"draws":16,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":28,"losses":11,"wins":45},"gpt-5.6-sol":{"draws":25,"losses":41,"wins":24},"gpt-5.6-terra":{"draws":33,"losses":15,"wins":34},"gpt-6-astra":{"draws":13,"losses":72,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":28,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":26},"meituan/longcat-2.0":{"draws":23,"losses":8,"wins":35},"meta/muse-glimmer-30b":{"draws":25,"losses":16,"wins":21},"meta/muse-spark-1.2":{"draws":19,"losses":21,"wins":32},"meta/muse-spark-1.3":{"draws":24,"losses":20,"wins":32},"meta/muse-wonder":{"draws":13,"losses":24,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":24},"mistralai/mistral-large-4-0":{"draws":7,"losses":3,"wins":16},"mistralai/mistral-medium-3-5":{"draws":18,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":22,"losses":12,"wins":36},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":4,"wins":19},"o3":{"draws":15,"losses":22,"wins":59},"openai/gpt-oss-120b":{"draws":28,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":29,"losses":2,"wins":31},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":22},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":22,"wins":44},"qwen/qwen3.8-27b":{"draws":13,"losses":10,"wins":19},"qwen/qwen3.8-flash":{"draws":16,"losses":0,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":23,"wins":34},"qwen/qwen3.8-max-0902":{"draws":17,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":82,"losses":66,"wins":125},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":18},"tencent/hy4-preview":{"draws":26,"losses":17,"wins":39},"thinkingmachines/inkling":{"draws":22,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":39,"losses":7,"wins":32},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":19,"losses":28,"wins":23},"x-ai/grok-4.6":{"draws":33,"losses":31,"wins":24},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":4,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":5,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":12},"z-ai/glm-5.2":{"draws":48,"losses":13,"wins":63},"z-ai/glm-5.3":{"draws":25,"losses":31,"wins":20},"z-ai/glm-5.3-flash":{"draws":18,"losses":24,"wins":46},"z-ai/glm-5.3-flashx":{"draws":13,"losses":16,"wins":19}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":16,"wins":33},"claude-fable-5":{"draws":8,"losses":54,"wins":22},"claude-fable-5-1":{"draws":7,"losses":85,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":25,"wins":10},"claude-opus-4-5":{"draws":31,"losses":25,"wins":55},"claude-opus-4-8":{"draws":15,"losses":23,"wins":16},"claude-opus-5":{"draws":17,"losses":67,"wins":8},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":27,"losses":23,"wins":38},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":29,"losses":17,"wins":56},"deepseek/deepseek-v4-pro":{"draws":21,"losses":21,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":22,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":18,"wins":13},"fireworks/ember-1":{"draws":19,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":28,"losses":43,"wins":27},"google/gemini-3.5-flash-lite":{"draws":50,"losses":30,"wins":60},"google/gemini-3.6-flash":{"draws":52,"losses":63,"wins":44},"google/gemini-3.8-flash":{"draws":24,"losses":34,"wins":28},"google/gemma-4-31b-it":{"draws":9,"losses":1,"wins":16},"gpt-4.1":{"draws":9,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":8,"wins":20},"gpt-5.4":{"draws":25,"losses":40,"wins":23},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":27},"gpt-5.5":{"draws":16,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":35,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":15,"losses":47,"wins":26},"gpt-5.6-terra":{"draws":36,"losses":27,"wins":23},"gpt-6-astra":{"draws":14,"losses":68,"wins":2},"gpt-6-luna":{"draws":15,"losses":14,"wins":17},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":6,"wins":23},"inclusionai/ling-3.0-flash":{"draws":22,"losses":8,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":19,"wins":32},"meta/muse-glimmer-30b":{"draws":22,"losses":15,"wins":27},"meta/muse-spark-1.2":{"draws":22,"losses":18,"wins":34},"meta/muse-spark-1.3":{"draws":20,"losses":41,"wins":13},"meta/muse-wonder":{"draws":11,"losses":27,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":1,"wins":17},"mistralai/mistral-large-4-0":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":25,"losses":25,"wins":26},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":22},"o3":{"draws":17,"losses":30,"wins":58},"openai/gpt-oss-120b":{"draws":28,"losses":6,"wins":36},"poolside/laguna-s-2.1":{"draws":25,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":21,"wins":36},"qwen/qwen3.8-27b":{"draws":12,"losses":19,"wins":11},"qwen/qwen3.8-flash":{"draws":27,"losses":19,"wins":12},"qwen/qwen3.8-max":{"draws":28,"losses":21,"wins":36},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":66,"losses":101,"wins":100},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":36,"wins":24},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":35},"thinkingmachines/inkling-small":{"draws":39,"losses":41,"wins":53},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":19,"losses":39,"wins":20},"x-ai/grok-4.6":{"draws":21,"losses":41,"wins":24},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":15,"wins":5},"z-ai/glm-5.2":{"draws":43,"losses":33,"wins":50},"z-ai/glm-5.3":{"draws":25,"losses":27,"wins":16},"z-ai/glm-5.3-flash":{"draws":23,"losses":33,"wins":22},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":22},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":18,"wins":10},"claude-opus-4-5":{"draws":23,"losses":39,"wins":16},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":16,"losses":57,"wins":9},"claude-opus-5-5":{"draws":6,"losses":45,"wins":1},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":14,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":25,"wins":19},"google/gemini-3.5-flash-lite":{"draws":32,"losses":20,"wins":32},"google/gemini-3.6-flash":{"draws":19,"losses":47,"wins":18},"google/gemini-3.8-flash":{"draws":13,"losses":30,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":15,"wins":14},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":14},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"wins":9},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":30},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":21,"wins":10},"meta/muse-wonder":{"draws":7,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":18},"o3":{"draws":13,"losses":28,"wins":25},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":13,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":13,"losses":19,"wins":16},"qwen/qwen3.8-max-0902":{"draws":6,"losses":19,"wins":5},"stealth/ox-alpha":{"draws":37,"losses":74,"wins":45},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":12},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":26},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":28,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":29,"losses":16,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":13},"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":34,"losses":29,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":53,"losses":62,"wins":129},"claude-fable-5":{"draws":67,"losses":149,"wins":58},"claude-fable-5-1":{"draws":23,"losses":299,"wins":10},"claude-haiku-5-5":{"draws":29,"losses":55,"wins":48},"claude-opus-4-5":{"draws":106,"losses":110,"wins":126},"claude-opus-4-8":{"draws":36,"losses":50,"wins":52},"claude-opus-5":{"draws":53,"losses":206,"wins":49},"claude-opus-5-5":{"draws":21,"losses":140,"wins":7},"claude-sonnet-5":{"draws":71,"losses":82,"wins":131},"claude-sonnet-5-5":{"draws":37,"losses":70,"wins":49},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":43},"deepseek/deepseek-v4-flash":{"draws":87,"losses":77,"wins":170},"deepseek/deepseek-v4-pro":{"draws":61,"losses":83,"wins":100},"deepseek/deepseek-v4-pro-0813":{"draws":62,"losses":91,"wins":93},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":62,"wins":52},"fireworks/ember-1":{"draws":41,"losses":61,"wins":54},"gemini-3.1-pro-preview":{"draws":37,"losses":47,"wins":72},"google/gemini-3.1-flash-lite":{"draws":20,"losses":14,"wins":56},"google/gemini-3.5-flash":{"draws":74,"losses":102,"wins":126},"google/gemini-3.5-flash-lite":{"draws":106,"losses":99,"wins":259},"google/gemini-3.6-flash":{"draws":108,"losses":192,"wins":148},"google/gemini-3.8-flash":{"draws":65,"losses":136,"wins":81},"google/gemma-4-31b-it":{"draws":16,"losses":17,"wins":43},"gpt-4.1":{"draws":14,"losses":9,"wins":31},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":34,"losses":48,"wins":70},"gpt-5.4":{"draws":75,"losses":103,"wins":84},"gpt-5.4-mini":{"draws":31,"losses":21,"wins":58},"gpt-5.4-nano":{"draws":31,"losses":35,"wins":78},"gpt-5.5":{"draws":46,"losses":57,"wins":51},"gpt-5.6-luna":{"draws":84,"losses":58,"wins":114},"gpt-5.6-sol":{"draws":41,"losses":197,"wins":52},"gpt-5.6-terra":{"draws":82,"losses":67,"wins":115},"gpt-6-astra":{"draws":27,"losses":244,"wins":11},"gpt-6-luna":{"draws":38,"losses":56,"wins":62},"gpt-6-sol":{"draws":24,"losses":115,"wins":17},"gpt-6.1-sol":{"draws":16,"losses":133,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":58,"losses":27,"wins":87},"inclusionai/ling-3.0-flash":{"draws":25,"losses":14,"wins":91},"meituan/longcat-2.0":{"draws":45,"losses":33,"wins":140},"meta/muse-glimmer-30b":{"draws":52,"losses":41,"wins":139},"meta/muse-spark-1.2":{"draws":51,"losses":83,"wins":94},"meta/muse-spark-1.3":{"draws":51,"losses":94,"wins":81},"meta/muse-wonder":{"draws":36,"losses":74,"wins":40},"minimax/minimax-m3":{"draws":21,"losses":19,"wins":48},"mistralai/mistral-large-4-0":{"draws":28,"losses":24,"wins":38},"mistralai/mistral-medium-3-5":{"draws":33,"losses":32,"wins":91},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":16},"moonshotai/kimi-k3":{"draws":64,"losses":101,"wins":75},"nex-agi/nex-n2-pro":{"draws":21,"losses":14,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":17,"wins":71},"o3":{"draws":35,"losses":118,"wins":133},"openai/gpt-oss-120b":{"draws":54,"losses":42,"wins":138},"poolside/laguna-s-2.1":{"draws":55,"losses":41,"wins":124},"qwen/qwen3.7-max":{"draws":23,"losses":22,"wins":45},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":85,"losses":109,"wins":88},"qwen/qwen3.8-27b":{"draws":29,"losses":57,"wins":50},"qwen/qwen3.8-flash":{"draws":48,"losses":62,"wins":64},"qwen/qwen3.8-max":{"draws":88,"losses":87,"wins":94},"qwen/qwen3.8-max-0902":{"draws":35,"losses":72,"wins":47},"stealth/ox-alpha":{"draws":209,"losses":471,"wins":366},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":59},"stepfun/step-3.7-flash":{"draws":12,"losses":22,"wins":70},"tencent/hy3-preview":{"draws":31,"losses":15,"wins":40},"tencent/hy4-preview":{"draws":58,"losses":126,"wins":80},"thinkingmachines/inkling":{"draws":51,"losses":49,"wins":132},"thinkingmachines/inkling-small":{"draws":79,"losses":64,"wins":125},"unbiased/pareto-26.10-preview":{"draws":0,"losses":44,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":53,"losses":107,"wins":72},"x-ai/grok-4.6":{"draws":73,"losses":118,"wins":89},"x-ai/grok-4.7":{"draws":17,"losses":98,"wins":17},"x-ai/grok-build-0.1":{"draws":15,"losses":5,"wins":36},"xiaomi/mimo-v2.5":{"draws":64,"losses":30,"wins":124},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":24,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":35,"wins":42},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":46,"wins":36},"z-ai/glm-5.2":{"draws":112,"losses":106,"wins":198},"z-ai/glm-5.3":{"draws":53,"losses":125,"wins":54},"z-ai/glm-5.3-flash":{"draws":61,"losses":128,"wins":89},"z-ai/glm-5.3-flashx":{"draws":24,"losses":78,"wins":54}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":6},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":18,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":11,"losses":22,"wins":5},"claude-opus-5":{"draws":8,"losses":57,"wins":5},"claude-opus-5-5":{"draws":1,"losses":41,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":9,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"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":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":16,"losses":28,"wins":30},"google/gemini-3.6-flash":{"draws":21,"losses":38,"wins":15},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":15},"gpt-5.4":{"draws":11,"losses":23,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":10,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":20,"wins":5},"gpt-6-sol":{"draws":9,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":18,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":31,"wins":4},"meta/muse-wonder":{"draws":14,"losses":21,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":8},"o3":{"draws":6,"losses":26,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":31,"losses":74,"wins":35},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":14,"wins":20},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":11},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":23},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":12,"wins":13},"claude-fable-5":{"draws":2,"losses":26,"wins":4},"claude-fable-5-1":{"draws":0,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":22,"wins":7},"claude-opus-4-5":{"draws":10,"losses":27,"wins":15},"claude-opus-4-8":{"draws":1,"losses":17,"wins":10},"claude-opus-5":{"draws":2,"losses":50,"wins":2},"claude-opus-5-5":{"draws":1,"losses":31,"wins":0},"claude-sonnet-5":{"draws":5,"losses":19,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":22,"wins":19},"deepseek/deepseek-v4-pro":{"draws":4,"losses":16,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":17,"wins":9},"fireworks/ember-1":{"draws":3,"losses":20,"wins":9},"gemini-3.1-pro-preview":{"draws":2,"losses":19,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":3,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":7,"losses":23,"wins":28},"google/gemini-3.6-flash":{"draws":8,"losses":38,"wins":16},"google/gemini-3.8-flash":{"draws":1,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":9},"gpt-4.1":{"draws":1,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":12},"gpt-5.5":{"draws":5,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":5,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":27,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":19,"wins":7},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":4,"losses":19,"wins":9},"gpt-6-sol":{"draws":4,"losses":28,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":34,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":3,"losses":11,"wins":14},"meta/muse-spark-1.2":{"draws":0,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":3,"losses":24,"wins":9},"meta/muse-wonder":{"draws":1,"losses":32,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":13,"wins":9},"o3":{"draws":6,"losses":30,"wins":18},"openai/gpt-oss-120b":{"draws":4,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":6,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":20,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":16,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":22,"wins":4},"stealth/ox-alpha":{"draws":10,"losses":79,"wins":19},"stealth/space-bunny-alpha":{"draws":4,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":5,"losses":20,"wins":7},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":18},"thinkingmachines/inkling-small":{"draws":8,"losses":11,"wins":15},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":25,"wins":9},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":8,"losses":14,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":12,"losses":35,"wins":17},"z-ai/glm-5.3":{"draws":1,"losses":27,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":1,"losses":23,"wins":6}},"stepfun/step-5-preview":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-fable-5-1":{"draws":0,"losses":0,"wins":2},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":10},"claude-opus-4-8":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":1,"wins":3},"claude-sonnet-5-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"wins":2},"fireworks/ember-1":{"draws":0,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":5},"google/gemini-3.8-flash":{"draws":0,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":6},"gpt-6-astra":{"draws":0,"losses":1,"wins":1},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":1,"losses":1,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":2},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":3},"meta/muse-wonder":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":1,"wins":5},"stealth/ox-alpha":{"draws":0,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":44},"claude-fable-5":{"draws":6,"losses":50,"wins":22},"claude-fable-5-1":{"draws":1,"losses":72,"wins":7},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":20},"claude-opus-4-5":{"draws":18,"losses":17,"wins":59},"claude-opus-4-8":{"draws":7,"losses":17,"wins":18},"claude-opus-5":{"draws":2,"losses":58,"wins":12},"claude-opus-5-5":{"draws":4,"losses":35,"wins":7},"claude-sonnet-5":{"draws":19,"losses":23,"wins":38},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":56},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":35,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"fireworks/ember-1":{"draws":8,"losses":15,"wins":19},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":10,"losses":25,"wins":47},"google/gemini-3.5-flash-lite":{"draws":19,"losses":34,"wins":85},"google/gemini-3.6-flash":{"draws":16,"losses":67,"wins":61},"google/gemini-3.8-flash":{"draws":13,"losses":25,"wins":32},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":12},"gpt-4.1":{"draws":3,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":19},"gpt-5.4":{"draws":8,"losses":35,"wins":37},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":35},"gpt-5.5":{"draws":10,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":18,"wins":38},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":36},"gpt-5.6-terra":{"draws":17,"losses":21,"wins":36},"gpt-6-astra":{"draws":5,"losses":65,"wins":4},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":3,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":28},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":44},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":42},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":23,"wins":31},"meta/muse-wonder":{"draws":6,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":2,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":31,"wins":22},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":29},"o3":{"draws":7,"losses":19,"wins":70},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":37},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":34},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":31},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":21},"qwen/qwen3.8-flash":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max":{"draws":11,"losses":31,"wins":32},"qwen/qwen3.8-max-0902":{"draws":6,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":53,"losses":90,"wins":100},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":17},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":51},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":31},"x-ai/grok-4.6":{"draws":14,"losses":38,"wins":24},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":25,"losses":33,"wins":60},"z-ai/glm-5.3":{"draws":8,"losses":41,"wins":9},"z-ai/glm-5.3-flash":{"draws":2,"losses":30,"wins":34},"z-ai/glm-5.3-flashx":{"draws":5,"losses":18,"wins":19}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":24,"wins":2},"claude-opus-4-5":{"draws":18,"losses":37,"wins":3},"claude-opus-4-8":{"draws":6,"losses":25,"wins":1},"claude-opus-5":{"draws":10,"losses":43,"wins":5},"claude-opus-5-5":{"draws":5,"losses":31,"wins":0},"claude-sonnet-5":{"draws":10,"losses":23,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":26,"wins":13},"deepseek/deepseek-v4-pro":{"draws":13,"losses":21,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":1},"fireworks/ember-1":{"draws":8,"losses":27,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":36,"wins":3},"google/gemini-3.5-flash-lite":{"draws":16,"losses":32,"wins":18},"google/gemini-3.6-flash":{"draws":13,"losses":51,"wins":4},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":23,"wins":2},"gpt-5.4":{"draws":9,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":10},"gpt-5.5":{"draws":13,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":21,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":22,"wins":3},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":24,"wins":2},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":23,"wins":7},"meta/muse-glimmer-30b":{"draws":9,"losses":17,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-wonder":{"draws":8,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":6},"o3":{"draws":5,"losses":46,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":28,"wins":1},"qwen/qwen3.8-27b":{"draws":6,"losses":19,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":8,"losses":28,"wins":0},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":75,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":25,"wins":4},"thinkingmachines/inkling":{"draws":12,"losses":15,"wins":7},"thinkingmachines/inkling-small":{"draws":11,"losses":13,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":27,"wins":1},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":43,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":31,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":1}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":32,"wins":22},"claude-fable-5":{"draws":22,"losses":46,"wins":8},"claude-fable-5-1":{"draws":5,"losses":71,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":31,"wins":3},"claude-opus-4-5":{"draws":31,"losses":68,"wins":10},"claude-opus-4-8":{"draws":14,"losses":26,"wins":4},"claude-opus-5":{"draws":12,"losses":66,"wins":6},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":27,"losses":48,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":55,"losses":40,"wins":21},"deepseek/deepseek-v4-pro":{"draws":24,"losses":50,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":38,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":25,"wins":9},"fireworks/ember-1":{"draws":17,"losses":26,"wins":5},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":25,"losses":44,"wins":21},"google/gemini-3.5-flash-lite":{"draws":67,"losses":76,"wins":30},"google/gemini-3.6-flash":{"draws":42,"losses":69,"wins":31},"google/gemini-3.8-flash":{"draws":28,"losses":34,"wins":16},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":16,"losses":19,"wins":9},"gpt-5.4":{"draws":38,"losses":33,"wins":4},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":25,"wins":11},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":31,"losses":31,"wins":30},"gpt-5.6-sol":{"draws":8,"losses":56,"wins":12},"gpt-5.6-terra":{"draws":27,"losses":36,"wins":17},"gpt-6-astra":{"draws":5,"losses":65,"wins":0},"gpt-6-luna":{"draws":10,"losses":28,"wins":8},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":18,"wins":21},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":32,"wins":24},"meta/muse-glimmer-30b":{"draws":35,"losses":31,"wins":14},"meta/muse-spark-1.2":{"draws":17,"losses":38,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":45,"wins":9},"meta/muse-wonder":{"draws":9,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":24,"losses":14,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":24,"losses":40,"wins":11},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":17,"wins":6},"o3":{"draws":20,"losses":62,"wins":20},"openai/gpt-oss-120b":{"draws":32,"losses":33,"wins":15},"poolside/laguna-s-2.1":{"draws":29,"losses":35,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":57,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":32,"wins":4},"qwen/qwen3.8-flash":{"draws":24,"losses":23,"wins":9},"qwen/qwen3.8-max":{"draws":45,"losses":69,"wins":23},"qwen/qwen3.8-max-0902":{"draws":14,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":89,"losses":142,"wins":41},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":26,"losses":48,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":40,"wins":11},"thinkingmachines/inkling-small":{"draws":35,"losses":34,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":19,"losses":48,"wins":11},"x-ai/grok-4.6":{"draws":25,"losses":45,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":32,"losses":24,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":15,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":50,"losses":59,"wins":31},"z-ai/glm-5.3":{"draws":14,"losses":43,"wins":11},"z-ai/glm-5.3-flash":{"draws":20,"losses":47,"wins":15},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":7,"wins":5},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":10,"wins":2},"claude-opus-4-5":{"draws":1,"losses":18,"wins":1},"claude-opus-4-8":{"draws":0,"losses":12,"wins":0},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"claude-sonnet-5-5":{"draws":0,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":11,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":10,"wins":1},"fireworks/ember-1":{"draws":0,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":20,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":2},"gpt-4.1":{"draws":0,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":11,"wins":3},"gpt-5.5":{"draws":0,"losses":9,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":11,"wins":1},"gpt-6-sol":{"draws":1,"losses":9,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":12,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":9,"wins":1},"meta/muse-wonder":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":7,"wins":3},"o3":{"draws":5,"losses":16,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":3,"losses":26,"wins":3},"stealth/space-bunny-alpha":{"draws":0,"losses":7,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":8,"wins":3},"thinkingmachines/inkling-small":{"draws":0,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":10,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":33},"claude-fable-5":{"draws":5,"losses":26,"wins":17},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":15,"wins":18},"claude-opus-4-5":{"draws":34,"losses":31,"wins":57},"claude-opus-4-8":{"draws":15,"losses":30,"wins":41},"claude-opus-5":{"draws":22,"losses":111,"wins":33},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":12,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":18,"losses":11,"wins":69},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":27},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":36},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":35},"google/gemini-3.5-flash-lite":{"draws":23,"losses":21,"wins":82},"google/gemini-3.6-flash":{"draws":34,"losses":50,"wins":62},"google/gemini-3.8-flash":{"draws":9,"losses":17,"wins":32},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":13,"wins":43},"gpt-5.4":{"draws":15,"losses":19,"wins":18},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":32},"gpt-5.4-nano":{"draws":13,"losses":24,"wins":47},"gpt-5.5":{"draws":27,"losses":25,"wins":36},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":29},"gpt-6-astra":{"draws":4,"losses":42,"wins":4},"gpt-6-luna":{"draws":11,"losses":13,"wins":24},"gpt-6-sol":{"draws":8,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":52},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":73},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":11,"losses":12,"wins":25},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":25},"meta/muse-wonder":{"draws":9,"losses":24,"wins":13},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":40},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":24,"losses":19,"wins":29},"nex-agi/nex-n2-pro":{"draws":13,"losses":1,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":49},"o3":{"draws":11,"losses":23,"wins":46},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":20,"losses":14,"wins":56},"qwen/qwen3.7-max":{"draws":18,"losses":11,"wins":19},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":24},"qwen/qwen3.8-flash":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"stealth/ox-alpha":{"draws":32,"losses":51,"wins":93},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":23},"tencent/hy4-preview":{"draws":11,"losses":13,"wins":22},"thinkingmachines/inkling":{"draws":24,"losses":9,"wins":45},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":15,"wins":23},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":7,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":14,"losses":0,"wins":26},"xiaomi/mimo-v2.5":{"draws":44,"losses":12,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":14},"z-ai/glm-5.2":{"draws":34,"losses":30,"wins":68},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":24},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":23}},"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-haiku-5-5":{"draws":7,"losses":9,"wins":26},"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},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"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},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"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":3,"losses":1,"wins":24},"gpt-4.1":{"draws":6,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"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":8,"losses":2,"wins":36},"gpt-6-sol":{"draws":9,"losses":26,"wins":13},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":33},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":29},"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":12,"losses":8,"wins":44},"meta/muse-spark-1.3":{"draws":10,"losses":19,"wins":41},"meta/muse-wonder":{"draws":10,"losses":16,"wins":18},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":18},"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":18,"losses":16,"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":11,"losses":4,"wins":71},"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":9,"losses":6,"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":11,"losses":8,"wins":27},"stealth/ox-alpha":{"draws":54,"losses":55,"wins":175},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":26},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":20},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":48},"thinkingmachines/inkling":{"draws":20,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":12,"losses":2,"wins":54},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":14,"wins":36},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":25},"x-ai/grok-4.7":{"draws":6,"losses":19,"wins":17},"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":7,"losses":9,"wins":16},"z-ai/glm-5.2":{"draws":30,"losses":12,"wins":82},"z-ai/glm-5.3":{"draws":14,"losses":29,"wins":31},"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":36},"claude-fable-5":{"draws":1,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":30,"wins":16},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":36},"claude-opus-4-5":{"draws":3,"losses":3,"wins":62},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":7,"losses":27,"wins":46},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":3,"losses":4,"wins":35},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":28},"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":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":7,"wins":59},"google/gemini-3.6-flash":{"draws":1,"losses":6,"wins":65},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":38},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":20},"gpt-4.1":{"draws":1,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":0,"wins":37},"gpt-5.4":{"draws":2,"losses":5,"wins":33},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":34},"gpt-5.5":{"draws":0,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":29},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":35},"gpt-6-astra":{"draws":5,"losses":28,"wins":9},"gpt-6-luna":{"draws":3,"losses":1,"wins":36},"gpt-6-sol":{"draws":3,"losses":13,"wins":26},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":31},"meta/muse-wonder":{"draws":1,"losses":9,"wins":26},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"o3":{"draws":3,"losses":2,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":24},"qwen/qwen3.8-max":{"draws":2,"losses":5,"wins":35},"qwen/qwen3.8-max-0902":{"draws":3,"losses":4,"wins":35},"stealth/ox-alpha":{"draws":14,"losses":12,"wins":114},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":20},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":44},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":34},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":34},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":20},"z-ai/glm-5.2":{"draws":3,"losses":5,"wins":76},"z-ai/glm-5.3":{"draws":2,"losses":9,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":34}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":8},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":27,"wins":4},"claude-opus-4-5":{"draws":47,"losses":65,"wins":18},"claude-opus-4-8":{"draws":24,"losses":50,"wins":14},"claude-opus-5":{"draws":22,"losses":84,"wins":8},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":21,"losses":28,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":40,"losses":38,"wins":26},"deepseek/deepseek-v4-pro":{"draws":18,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":38},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":10},"google/gemini-3.5-flash-lite":{"draws":47,"losses":30,"wins":34},"google/gemini-3.6-flash":{"draws":31,"losses":62,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":9},"gpt-4.1":{"draws":14,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":27,"losses":33,"wins":16},"gpt-5.4":{"draws":12,"losses":29,"wins":7},"gpt-5.4-mini":{"draws":28,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":20,"losses":51,"wins":27},"gpt-5.5":{"draws":51,"losses":21,"wins":14},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":26,"wins":7},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":24,"losses":4,"wins":36},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":28,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":33,"wins":11},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":20,"losses":17,"wins":25},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":16,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":22,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":31,"wins":6},"nex-agi/nex-n2-pro":{"draws":21,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":18,"wins":20},"o3":{"draws":20,"losses":51,"wins":13},"openai/gpt-oss-120b":{"draws":19,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":37,"losses":18,"wins":27},"qwen/qwen3.7-max":{"draws":27,"losses":15,"wins":22},"qwen/qwen3.7-plus":{"draws":17,"losses":22,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":19,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":21,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":44,"losses":105,"wins":19},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":21,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":28,"losses":18,"wins":30},"thinkingmachines/inkling-small":{"draws":22,"losses":14,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":23,"losses":46,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":69,"losses":37,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":26,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":47,"losses":48,"wins":23},"z-ai/glm-5.3":{"draws":13,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":28,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":36,"wins":13},"claude-fable-5":{"draws":21,"losses":68,"wins":3},"claude-fable-5-1":{"draws":6,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":47,"wins":10},"claude-opus-4-5":{"draws":115,"losses":123,"wins":38},"claude-opus-4-8":{"draws":59,"losses":84,"wins":13},"claude-opus-5":{"draws":39,"losses":175,"wins":20},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":44,"losses":41,"wins":15},"claude-sonnet-5-5":{"draws":23,"losses":56,"wins":11},"cohere/north-mini-code":{"draws":19,"losses":27,"wins":16},"deepseek/deepseek-v4-flash":{"draws":80,"losses":52,"wins":70},"deepseek/deepseek-v4-pro":{"draws":36,"losses":43,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":39,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":47,"wins":8},"fireworks/ember-1":{"draws":34,"losses":48,"wins":8},"gemini-3.1-pro-preview":{"draws":35,"losses":37,"wins":18},"google/gemini-3.1-flash-lite":{"draws":44,"losses":29,"wins":65},"google/gemini-3.5-flash":{"draws":45,"losses":59,"wins":20},"google/gemini-3.5-flash-lite":{"draws":78,"losses":55,"wins":61},"google/gemini-3.6-flash":{"draws":80,"losses":96,"wins":12},"google/gemini-3.8-flash":{"draws":32,"losses":55,"wins":7},"google/gemma-4-31b-it":{"draws":24,"losses":15,"wins":13},"gpt-4.1":{"draws":24,"losses":16,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":52,"losses":57,"wins":29},"gpt-5.4":{"draws":33,"losses":49,"wins":6},"gpt-5.4-mini":{"draws":53,"losses":47,"wins":18},"gpt-5.4-nano":{"draws":53,"losses":73,"wins":64},"gpt-5.5":{"draws":75,"losses":69,"wins":8},"gpt-5.6-luna":{"draws":41,"losses":35,"wins":18},"gpt-5.6-sol":{"draws":18,"losses":72,"wins":2},"gpt-5.6-terra":{"draws":38,"losses":53,"wins":5},"gpt-6-astra":{"draws":4,"losses":85,"wins":1},"gpt-6-luna":{"draws":38,"losses":39,"wins":13},"gpt-6-sol":{"draws":16,"losses":70,"wins":4},"gpt-6.1-sol":{"draws":8,"losses":80,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":10,"wins":24},"inclusionai/ling-3.0-flash":{"draws":41,"losses":25,"wins":32},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":60,"losses":50,"wins":50},"meta/muse-glimmer-30b":{"draws":34,"losses":30,"wins":22},"meta/muse-spark-1.2":{"draws":31,"losses":51,"wins":8},"meta/muse-spark-1.3":{"draws":28,"losses":56,"wins":8},"meta/muse-wonder":{"draws":25,"losses":55,"wins":4},"minimax/minimax-m3":{"draws":52,"losses":31,"wins":33},"mistralai/mistral-large-4-0":{"draws":20,"losses":26,"wins":6},"mistralai/mistral-medium-3-5":{"draws":27,"losses":8,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":29,"losses":36,"wins":7},"moonshotai/kimi-k3":{"draws":35,"losses":46,"wins":13},"nex-agi/nex-n2-pro":{"draws":17,"losses":25,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":72,"losses":56,"wins":26},"o3":{"draws":39,"losses":103,"wins":14},"openai/gpt-oss-120b":{"draws":32,"losses":24,"wins":24},"poolside/laguna-s-2.1":{"draws":46,"losses":43,"wins":37},"qwen/qwen3.7-max":{"draws":47,"losses":48,"wins":21},"qwen/qwen3.7-plus":{"draws":53,"losses":38,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":7},"qwen/qwen3.8-27b":{"draws":23,"losses":32,"wins":7},"qwen/qwen3.8-flash":{"draws":27,"losses":22,"wins":13},"qwen/qwen3.8-max":{"draws":41,"losses":42,"wins":11},"qwen/qwen3.8-max-0902":{"draws":30,"losses":46,"wins":12},"stealth/ox-alpha":{"draws":79,"losses":150,"wins":33},"stealth/space-bunny-alpha":{"draws":32,"losses":29,"wins":13},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":19},"tencent/hy3-preview":{"draws":41,"losses":25,"wins":24},"tencent/hy4-preview":{"draws":29,"losses":47,"wins":8},"thinkingmachines/inkling":{"draws":52,"losses":34,"wins":58},"thinkingmachines/inkling-small":{"draws":41,"losses":29,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":3},"x-ai/grok-4.5":{"draws":47,"losses":76,"wins":7},"x-ai/grok-4.6":{"draws":35,"losses":55,"wins":6},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":33,"losses":21,"wins":14},"xiaomi/mimo-v2.5":{"draws":142,"losses":64,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":37,"losses":39,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":31,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":36,"wins":4},"z-ai/glm-5.2":{"draws":96,"losses":111,"wins":45},"z-ai/glm-5.3":{"draws":27,"losses":60,"wins":1},"z-ai/glm-5.3-flash":{"draws":32,"losses":49,"wins":13},"z-ai/glm-5.3-flashx":{"draws":35,"losses":50,"wins":5}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":11,"wins":19},"claude-fable-5":{"draws":3,"losses":37,"wins":2},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":10},"claude-opus-4-5":{"draws":24,"losses":43,"wins":47},"claude-opus-4-8":{"draws":14,"losses":43,"wins":19},"claude-opus-5":{"draws":19,"losses":70,"wins":5},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":3,"losses":22,"wins":23},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":20,"losses":17,"wins":35},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":12,"wins":15},"fireworks/ember-1":{"draws":10,"losses":14,"wins":12},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":15},"google/gemini-3.1-flash-lite":{"draws":13,"losses":6,"wins":45},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":24},"google/gemini-3.5-flash-lite":{"draws":27,"losses":21,"wins":50},"google/gemini-3.6-flash":{"draws":22,"losses":50,"wins":28},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":12},"gpt-4.1":{"draws":4,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":23,"wins":16},"gpt-5.4":{"draws":5,"losses":36,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":15,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":29,"wins":43},"gpt-5.5":{"draws":13,"losses":33,"wins":14},"gpt-5.6-luna":{"draws":9,"losses":16,"wins":21},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":23,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":2},"gpt-6-luna":{"draws":8,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":28,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":6,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":26},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":36},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":15},"meta/muse-spark-1.2":{"draws":2,"losses":26,"wins":20},"meta/muse-spark-1.3":{"draws":5,"losses":21,"wins":12},"meta/muse-wonder":{"draws":3,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":11,"losses":15,"wins":18},"mistralai/mistral-large-4-0":{"draws":3,"losses":11,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":25},"nex-agi/nex-n2-pro":{"draws":6,"losses":9,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":13,"wins":32},"o3":{"draws":12,"losses":34,"wins":52},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":27},"qwen/qwen3.7-max":{"draws":13,"losses":23,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":16},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":14},"qwen/qwen3.8-max":{"draws":2,"losses":22,"wins":14},"qwen/qwen3.8-max-0902":{"draws":4,"losses":18,"wins":12},"stealth/ox-alpha":{"draws":16,"losses":57,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":15},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":26,"wins":33},"x-ai/grok-4.6":{"draws":11,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":33,"losses":13,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":11},"z-ai/glm-5.2":{"draws":31,"losses":31,"wins":38},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":32},"claude-fable-5":{"draws":6,"losses":24,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":17},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":7,"losses":9,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":12,"losses":12,"wins":48},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":20,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":5,"losses":18,"wins":25},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":18,"wins":33},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.6-flash":{"draws":9,"losses":33,"wins":42},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":20},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":11,"wins":25},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":29},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":7,"losses":16,"wins":22},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":8,"losses":13,"wins":27},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":25},"meituan/longcat-2.0":{"draws":11,"losses":10,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":19},"meta/muse-wonder":{"draws":1,"losses":27,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":26},"o3":{"draws":9,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":16,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":17,"wins":25},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":25},"stealth/ox-alpha":{"draws":22,"losses":60,"wins":74},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":30},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":37},"thinkingmachines/inkling-small":{"draws":13,"losses":1,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":26},"x-ai/grok-4.6":{"draws":8,"losses":19,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":12},"z-ai/glm-5.2":{"draws":12,"losses":20,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":21},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":36},"claude-fable-5":{"draws":2,"losses":13,"wins":29},"claude-fable-5-1":{"draws":9,"losses":34,"wins":7},"claude-haiku-5-5":{"draws":4,"losses":11,"wins":29},"claude-opus-4-5":{"draws":11,"losses":8,"wins":53},"claude-opus-4-8":{"draws":2,"losses":12,"wins":26},"claude-opus-5":{"draws":16,"losses":36,"wins":24},"claude-opus-5-5":{"draws":4,"losses":35,"wins":5},"claude-sonnet-5":{"draws":0,"losses":9,"wins":33},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":3,"losses":8,"wins":55},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":24},"fireworks/ember-1":{"draws":7,"losses":11,"wins":26},"gemini-3.1-pro-preview":{"draws":2,"losses":8,"wins":32},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":36},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":68},"google/gemini-3.6-flash":{"draws":10,"losses":17,"wins":51},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":28},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":2,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":8,"wins":30},"gpt-5.4":{"draws":5,"losses":14,"wins":25},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":38},"gpt-5.5":{"draws":8,"losses":9,"wins":23},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":36},"gpt-5.6-sol":{"draws":9,"losses":13,"wins":20},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":26},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":20,"wins":18},"gpt-6.1-sol":{"draws":8,"losses":26,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":6,"wins":40},"meta/muse-glimmer-30b":{"draws":0,"losses":7,"wins":31},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":33},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":30},"meta/muse-wonder":{"draws":9,"losses":15,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":20},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":29},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":24},"o3":{"draws":1,"losses":8,"wins":49},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":34},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":25},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":33},"qwen/qwen3.8-max-0902":{"draws":4,"losses":11,"wins":29},"stealth/ox-alpha":{"draws":14,"losses":36,"wins":96},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":9,"wins":25},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":42},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":41},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":28},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":24},"x-ai/grok-4.7":{"draws":1,"losses":21,"wins":14},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":7,"losses":9,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":9,"losses":15,"wins":64},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":22},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":26}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":23,"wins":59},"claude-fable-5":{"draws":31,"losses":72,"wins":25},"claude-fable-5-1":{"draws":15,"losses":122,"wins":5},"claude-haiku-5-5":{"draws":21,"losses":36,"wins":29},"claude-opus-4-5":{"draws":75,"losses":70,"wins":83},"claude-opus-4-8":{"draws":47,"losses":64,"wins":33},"claude-opus-5":{"draws":31,"losses":167,"wins":10},"claude-opus-5-5":{"draws":5,"losses":95,"wins":4},"claude-sonnet-5":{"draws":38,"losses":49,"wins":47},"claude-sonnet-5-5":{"draws":19,"losses":52,"wins":25},"cohere/north-mini-code":{"draws":16,"losses":11,"wins":17},"deepseek/deepseek-v4-flash":{"draws":83,"losses":38,"wins":81},"deepseek/deepseek-v4-pro":{"draws":58,"losses":36,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":45,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":23},"fireworks/ember-1":{"draws":33,"losses":40,"wins":23},"gemini-3.1-pro-preview":{"draws":32,"losses":29,"wins":35},"google/gemini-3.1-flash-lite":{"draws":27,"losses":7,"wins":50},"google/gemini-3.5-flash":{"draws":57,"losses":50,"wins":59},"google/gemini-3.5-flash-lite":{"draws":103,"losses":40,"wins":97},"google/gemini-3.6-flash":{"draws":58,"losses":87,"wins":81},"google/gemini-3.8-flash":{"draws":30,"losses":66,"wins":42},"google/gemma-4-31b-it":{"draws":20,"losses":7,"wins":23},"gpt-4.1":{"draws":18,"losses":9,"wins":21},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":47,"losses":36,"wins":39},"gpt-5.4":{"draws":45,"losses":45,"wins":34},"gpt-5.4-mini":{"draws":58,"losses":11,"wins":29},"gpt-5.4-nano":{"draws":43,"losses":37,"wins":50},"gpt-5.5":{"draws":57,"losses":50,"wins":21},"gpt-5.6-luna":{"draws":62,"losses":24,"wins":44},"gpt-5.6-sol":{"draws":17,"losses":77,"wins":34},"gpt-5.6-terra":{"draws":59,"losses":39,"wins":36},"gpt-6-astra":{"draws":12,"losses":106,"wins":8},"gpt-6-luna":{"draws":29,"losses":33,"wins":30},"gpt-6-sol":{"draws":14,"losses":71,"wins":11},"gpt-6.1-sol":{"draws":15,"losses":77,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":46,"losses":4,"wins":44},"inclusionai/ling-3.0-flash":{"draws":51,"losses":7,"wins":32},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":46,"losses":32,"wins":62},"meta/muse-glimmer-30b":{"draws":52,"losses":22,"wins":42},"meta/muse-spark-1.2":{"draws":27,"losses":51,"wins":34},"meta/muse-spark-1.3":{"draws":31,"losses":43,"wins":36},"meta/muse-wonder":{"draws":26,"losses":48,"wins":18},"minimax/minimax-m3":{"draws":25,"losses":12,"wins":31},"mistralai/mistral-large-4-0":{"draws":27,"losses":17,"wins":12},"mistralai/mistral-medium-3-5":{"draws":32,"losses":9,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":10,"wins":19},"moonshotai/kimi-k3":{"draws":44,"losses":33,"wins":33},"nex-agi/nex-n2-pro":{"draws":32,"losses":3,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":19,"wins":46},"o3":{"draws":32,"losses":61,"wins":81},"openai/gpt-oss-120b":{"draws":58,"losses":16,"wins":40},"poolside/laguna-s-2.1":{"draws":75,"losses":18,"wins":43},"qwen/qwen3.7-max":{"draws":27,"losses":14,"wins":35},"qwen/qwen3.7-plus":{"draws":24,"losses":9,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":55,"wins":39},"qwen/qwen3.8-27b":{"draws":23,"losses":23,"wins":30},"qwen/qwen3.8-flash":{"draws":31,"losses":30,"wins":25},"qwen/qwen3.8-max":{"draws":41,"losses":50,"wins":39},"qwen/qwen3.8-max-0902":{"draws":32,"losses":42,"wins":22},"stealth/ox-alpha":{"draws":122,"losses":189,"wins":121},"stealth/space-bunny-alpha":{"draws":31,"losses":19,"wins":26},"stepfun/step-3.7-flash":{"draws":20,"losses":8,"wins":42},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":20,"wins":22},"tencent/hy4-preview":{"draws":32,"losses":61,"wins":31},"thinkingmachines/inkling":{"draws":47,"losses":22,"wins":69},"thinkingmachines/inkling-small":{"draws":51,"losses":18,"wins":63},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":36,"losses":49,"wins":41},"x-ai/grok-4.6":{"draws":38,"losses":72,"wins":28},"x-ai/grok-4.7":{"draws":9,"losses":62,"wins":13},"x-ai/grok-build-0.1":{"draws":18,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":88,"losses":25,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":17,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":29,"wins":15},"z-ai/glm-5.2":{"draws":96,"losses":57,"wins":71},"z-ai/glm-5.3":{"draws":29,"losses":59,"wins":28},"z-ai/glm-5.3-flash":{"draws":50,"losses":55,"wins":33},"z-ai/glm-5.3-flashx":{"draws":31,"losses":40,"wins":25}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":44},"claude-fable-5":{"draws":14,"losses":32,"wins":44},"claude-fable-5-1":{"draws":8,"losses":77,"wins":23},"claude-haiku-5-5":{"draws":9,"losses":7,"wins":28},"claude-opus-4-5":{"draws":22,"losses":14,"wins":76},"claude-opus-4-8":{"draws":8,"losses":12,"wins":28},"claude-opus-5":{"draws":16,"losses":60,"wins":16},"claude-opus-5-5":{"draws":3,"losses":36,"wins":13},"claude-sonnet-5":{"draws":10,"losses":12,"wins":60},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":19,"losses":3,"wins":74},"deepseek/deepseek-v4-pro":{"draws":10,"losses":15,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":15,"losses":17,"wins":66},"google/gemini-3.5-flash-lite":{"draws":18,"losses":4,"wins":100},"google/gemini-3.6-flash":{"draws":23,"losses":29,"wins":90},"google/gemini-3.8-flash":{"draws":17,"losses":20,"wins":53},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":30},"gpt-5.4":{"draws":10,"losses":24,"wins":48},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":38},"gpt-5.5":{"draws":15,"losses":12,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":58},"gpt-5.6-sol":{"draws":18,"losses":43,"wins":33},"gpt-5.6-terra":{"draws":27,"losses":8,"wins":47},"gpt-6-astra":{"draws":17,"losses":74,"wins":5},"gpt-6-luna":{"draws":10,"losses":7,"wins":29},"gpt-6-sol":{"draws":6,"losses":23,"wins":19},"gpt-6.1-sol":{"draws":12,"losses":29,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":34},"meituan/longcat-2.0":{"draws":14,"losses":3,"wins":45},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":47},"meta/muse-spark-1.2":{"draws":9,"losses":19,"wins":40},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":42},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":24,"wins":40},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":33},"o3":{"draws":9,"losses":14,"wins":73},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":41},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":22,"wins":49},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":22},"qwen/qwen3.8-flash":{"draws":13,"losses":7,"wins":38},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":49},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":39,"losses":69,"wins":171},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":53},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":50},"thinkingmachines/inkling-small":{"draws":11,"losses":0,"wins":59},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":41},"x-ai/grok-4.6":{"draws":18,"losses":28,"wins":44},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":16,"losses":1,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":26,"losses":23,"wins":73},"z-ai/glm-5.3":{"draws":12,"losses":6,"wins":24},"z-ai/glm-5.3-flash":{"draws":20,"losses":19,"wins":47},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":11,"wins":34},"claude-fable-5":{"draws":13,"losses":42,"wins":31},"claude-fable-5-1":{"draws":9,"losses":85,"wins":10},"claude-haiku-5-5":{"draws":7,"losses":13,"wins":24},"claude-opus-4-5":{"draws":28,"losses":19,"wins":59},"claude-opus-4-8":{"draws":8,"losses":15,"wins":23},"claude-opus-5":{"draws":8,"losses":67,"wins":23},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":17,"losses":12,"wins":55},"claude-sonnet-5-5":{"draws":5,"losses":24,"wins":19},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":26,"losses":9,"wins":63},"deepseek/deepseek-v4-pro":{"draws":21,"losses":25,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":16,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"fireworks/ember-1":{"draws":10,"losses":13,"wins":25},"gemini-3.1-pro-preview":{"draws":12,"losses":10,"wins":26},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":21,"losses":26,"wins":53},"google/gemini-3.5-flash-lite":{"draws":35,"losses":4,"wins":97},"google/gemini-3.6-flash":{"draws":29,"losses":37,"wins":74},"google/gemini-3.8-flash":{"draws":19,"losses":37,"wins":32},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":17},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":22,"losses":38,"wins":28},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":21},"gpt-5.6-luna":{"draws":19,"losses":16,"wins":43},"gpt-5.6-sol":{"draws":12,"losses":41,"wins":39},"gpt-5.6-terra":{"draws":22,"losses":25,"wins":35},"gpt-6-astra":{"draws":14,"losses":71,"wins":9},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":24},"meituan/longcat-2.0":{"draws":15,"losses":4,"wins":41},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":40},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":30},"meta/muse-spark-1.3":{"draws":17,"losses":21,"wins":34},"meta/muse-wonder":{"draws":7,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":18,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":16,"losses":25,"wins":29},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":23},"o3":{"draws":17,"losses":26,"wins":53},"openai/gpt-oss-120b":{"draws":22,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":22,"losses":9,"wins":33},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":29,"wins":31},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":22},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":21},"qwen/qwen3.8-max":{"draws":18,"losses":29,"wins":35},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":53,"losses":95,"wins":139},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":30,"wins":38},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":53},"thinkingmachines/inkling-small":{"draws":27,"losses":4,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":29,"wins":32},"x-ai/grok-4.6":{"draws":19,"losses":32,"wins":37},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":2,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":39,"losses":16,"wins":75},"z-ai/glm-5.3":{"draws":18,"losses":31,"wins":25},"z-ai/glm-5.3-flash":{"draws":15,"losses":8,"wins":37},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":23}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":12,"losses":27,"wins":9},"claude-fable-5-1":{"draws":4,"losses":45,"wins":5},"claude-haiku-5-5":{"draws":7,"losses":24,"wins":13},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":21,"wins":14},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":23},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":27},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":15,"losses":26,"wins":43},"google/gemini-3.6-flash":{"draws":16,"losses":39,"wins":29},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":12},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":12},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":17,"wins":15},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":22},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":12,"losses":16,"wins":20},"gpt-6-sol":{"draws":4,"losses":34,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":20},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-wonder":{"draws":11,"losses":23,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":4,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":15},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":26},"o3":{"draws":4,"losses":30,"wins":30},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"stealth/ox-alpha":{"draws":31,"losses":64,"wins":61},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":16,"losses":4,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":17},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":11,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":43},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":10},"z-ai/glm-5.3-flash":{"draws":14,"losses":16,"wins":18},"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":18,"losses":22,"wins":10},"claude-fable-5":{"draws":9,"losses":41,"wins":6},"claude-fable-5-1":{"draws":1,"losses":57,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":30,"wins":3},"claude-opus-4-5":{"draws":25,"losses":54,"wins":11},"claude-opus-4-8":{"draws":7,"losses":31,"wins":0},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":20,"losses":48,"wins":8},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":33,"losses":41,"wins":22},"deepseek/deepseek-v4-pro":{"draws":22,"losses":44,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":36,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":13,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":24,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":20,"losses":50,"wins":14},"google/gemini-3.5-flash-lite":{"draws":42,"losses":68,"wins":36},"google/gemini-3.6-flash":{"draws":34,"losses":77,"wins":15},"google/gemini-3.8-flash":{"draws":17,"losses":40,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":11,"losses":18,"wins":9},"gpt-5.4":{"draws":18,"losses":32,"wins":12},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":15},"gpt-5.5":{"draws":14,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":16,"losses":34,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":54,"wins":2},"gpt-5.6-terra":{"draws":18,"losses":45,"wins":7},"gpt-6-astra":{"draws":1,"losses":47,"wins":2},"gpt-6-luna":{"draws":13,"losses":22,"wins":7},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":13,"wins":21},"inclusionai/ling-3.0-flash":{"draws":17,"losses":10,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":24,"wins":19},"meta/muse-glimmer-30b":{"draws":33,"losses":29,"wins":14},"meta/muse-spark-1.2":{"draws":16,"losses":36,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":41,"wins":7},"meta/muse-wonder":{"draws":5,"losses":33,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":4},"mistralai/mistral-medium-3-5":{"draws":22,"losses":14,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":32,"wins":14},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":10},"o3":{"draws":21,"losses":60,"wins":19},"openai/gpt-oss-120b":{"draws":22,"losses":29,"wins":17},"poolside/laguna-s-2.1":{"draws":22,"losses":24,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":43,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":22,"losses":24,"wins":4},"qwen/qwen3.8-max":{"draws":29,"losses":34,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":4},"stealth/ox-alpha":{"draws":47,"losses":152,"wins":33},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":6},"stepfun/step-3.7-flash":{"draws":8,"losses":14,"wins":12},"tencent/hy3-preview":{"draws":5,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":26,"losses":39,"wins":7},"thinkingmachines/inkling":{"draws":18,"losses":25,"wins":23},"thinkingmachines/inkling-small":{"draws":31,"losses":22,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":45,"wins":8},"x-ai/grok-4.6":{"draws":20,"losses":37,"wins":9},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":24,"losses":24,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":55,"losses":45,"wins":20},"z-ai/glm-5.3":{"draws":13,"losses":36,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":36,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":29,"wins":6}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":8,"wins":44},"claude-fable-5":{"draws":9,"losses":32,"wins":17},"claude-fable-5-1":{"draws":3,"losses":84,"wins":7},"claude-haiku-5-5":{"draws":7,"losses":14,"wins":23},"claude-opus-4-5":{"draws":23,"losses":22,"wins":59},"claude-opus-4-8":{"draws":10,"losses":17,"wins":19},"claude-opus-5":{"draws":17,"losses":66,"wins":13},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":26,"losses":18,"wins":44},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":27,"losses":11,"wins":72},"deepseek/deepseek-v4-pro":{"draws":29,"losses":18,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":14,"losses":10,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":28,"losses":23,"wins":43},"google/gemini-3.5-flash-lite":{"draws":41,"losses":22,"wins":75},"google/gemini-3.6-flash":{"draws":33,"losses":47,"wins":64},"google/gemini-3.8-flash":{"draws":18,"losses":38,"wins":32},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":4,"wins":25},"gpt-5.4":{"draws":28,"losses":28,"wins":36},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":35},"gpt-5.5":{"draws":16,"losses":12,"wins":20},"gpt-5.6-luna":{"draws":31,"losses":12,"wins":39},"gpt-5.6-sol":{"draws":17,"losses":40,"wins":29},"gpt-5.6-terra":{"draws":24,"losses":19,"wins":47},"gpt-6-astra":{"draws":4,"losses":65,"wins":17},"gpt-6-luna":{"draws":11,"losses":10,"wins":25},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":38},"meta/muse-glimmer-30b":{"draws":25,"losses":2,"wins":37},"meta/muse-spark-1.2":{"draws":17,"losses":21,"wins":32},"meta/muse-spark-1.3":{"draws":14,"losses":23,"wins":31},"meta/muse-wonder":{"draws":11,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":19,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":23,"losses":12,"wins":37},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":4,"wins":31},"o3":{"draws":11,"losses":14,"wins":69},"openai/gpt-oss-120b":{"draws":24,"losses":6,"wins":36},"poolside/laguna-s-2.1":{"draws":21,"losses":10,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":19},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":26,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":19},"qwen/qwen3.8-flash":{"draws":17,"losses":12,"wins":25},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":40},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"stealth/ox-alpha":{"draws":68,"losses":79,"wins":129},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":23},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":28,"wins":42},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":44},"thinkingmachines/inkling-small":{"draws":26,"losses":9,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":32,"wins":30},"x-ai/grok-4.6":{"draws":20,"losses":28,"wins":40},"x-ai/grok-4.7":{"draws":1,"losses":28,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":41,"losses":27,"wins":58},"z-ai/glm-5.3":{"draws":12,"losses":42,"wins":18},"z-ai/glm-5.3-flash":{"draws":11,"losses":42,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":19,"wins":21}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":4,"wins":54},"claude-fable-5":{"draws":5,"losses":20,"wins":65},"claude-fable-5-1":{"draws":5,"losses":53,"wins":18},"claude-haiku-5-5":{"draws":2,"losses":6,"wins":36},"claude-opus-4-5":{"draws":7,"losses":2,"wins":97},"claude-opus-4-8":{"draws":4,"losses":3,"wins":37},"claude-opus-5":{"draws":14,"losses":26,"wins":48},"claude-opus-5-5":{"draws":2,"losses":28,"wins":22},"claude-sonnet-5":{"draws":9,"losses":3,"wins":72},"claude-sonnet-5-5":{"draws":4,"losses":12,"wins":32},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":89},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":2,"wins":36},"fireworks/ember-1":{"draws":4,"losses":2,"wins":42},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":45},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":33},"google/gemini-3.5-flash":{"draws":13,"losses":6,"wins":77},"google/gemini-3.5-flash-lite":{"draws":14,"losses":0,"wins":102},"google/gemini-3.6-flash":{"draws":15,"losses":6,"wins":111},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":74},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":21},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":1,"wins":38},"gpt-5.4":{"draws":7,"losses":16,"wins":61},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":49},"gpt-5.5":{"draws":2,"losses":6,"wins":36},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":55},"gpt-5.6-sol":{"draws":13,"losses":15,"wins":66},"gpt-5.6-terra":{"draws":12,"losses":0,"wins":68},"gpt-6-astra":{"draws":11,"losses":65,"wins":20},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":6,"losses":15,"wins":27},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":54},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":5,"losses":0,"wins":61},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":56},"meta/muse-wonder":{"draws":6,"losses":10,"wins":28},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":1,"losses":1,"wins":26},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":3,"wins":59},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"o3":{"draws":2,"losses":6,"wins":82},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":51},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":54},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":29},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":3,"wins":70},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":38},"qwen/qwen3.8-flash":{"draws":5,"losses":3,"wins":46},"qwen/qwen3.8-max":{"draws":9,"losses":3,"wins":68},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":37,"losses":15,"wins":228},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":7,"losses":10,"wins":63},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":64},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":62},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":71},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":6,"wins":19},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":101},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":49},"z-ai/glm-5.3-flash":{"draws":17,"losses":5,"wins":66},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":39}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":10,"wins":14},"claude-fable-5":{"draws":7,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":18,"wins":6},"claude-opus-4-5":{"draws":27,"losses":29,"wins":16},"claude-opus-4-8":{"draws":15,"losses":25,"wins":2},"claude-opus-5":{"draws":10,"losses":60,"wins":6},"claude-opus-5-5":{"draws":3,"losses":41,"wins":0},"claude-sonnet-5":{"draws":16,"losses":19,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":28,"losses":18,"wins":22},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":20,"wins":11},"fireworks/ember-1":{"draws":14,"losses":16,"wins":12},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":11},"google/gemini-3.8-flash":{"draws":12,"losses":30,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1":{"draws":6,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":14,"wins":11},"gpt-5.4":{"draws":13,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":22,"wins":13},"gpt-5.5":{"draws":19,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":15,"wins":9},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":11},"gpt-6-astra":{"draws":3,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":22,"wins":12},"gpt-6-sol":{"draws":6,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":4,"wins":14},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":10,"wins":19},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":28,"wins":9},"meta/muse-wonder":{"draws":11,"losses":36,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":12},"mistralai/mistral-large-4-0":{"draws":16,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":17,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":11},"o3":{"draws":12,"losses":35,"wins":15},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":17,"losses":17,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":17,"wins":11},"qwen/qwen3.8-max-0902":{"draws":18,"losses":22,"wins":6},"stealth/ox-alpha":{"draws":41,"losses":74,"wins":31},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":20,"losses":11,"wins":19},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":6},"x-ai/grok-4.6":{"draws":16,"losses":25,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":16,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":29,"losses":32,"wins":25},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":29,"wins":6},"z-ai/glm-5.3-flashx":{"draws":9,"losses":26,"wins":7}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":17,"wins":15},"claude-fable-5":{"draws":11,"losses":30,"wins":11},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":18,"wins":11},"claude-opus-4-5":{"draws":46,"losses":26,"wins":34},"claude-opus-4-8":{"draws":21,"losses":48,"wins":25},"claude-opus-5":{"draws":26,"losses":117,"wins":15},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":17,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":38},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":20,"wins":16},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":36},"google/gemini-3.5-flash":{"draws":20,"losses":26,"wins":20},"google/gemini-3.5-flash-lite":{"draws":45,"losses":24,"wins":39},"google/gemini-3.6-flash":{"draws":37,"losses":43,"wins":34},"google/gemini-3.8-flash":{"draws":20,"losses":24,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":9},"gpt-4.1":{"draws":16,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":24,"losses":13,"wins":17},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":29,"losses":16,"wins":21},"gpt-5.4-nano":{"draws":24,"losses":26,"wins":44},"gpt-5.5":{"draws":44,"losses":29,"wins":11},"gpt-5.6-luna":{"draws":21,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":34,"wins":8},"gpt-5.6-terra":{"draws":26,"losses":15,"wins":9},"gpt-6-astra":{"draws":3,"losses":41,"wins":6},"gpt-6-luna":{"draws":15,"losses":19,"wins":12},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":28,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":32,"losses":11,"wins":41},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":14},"meta/muse-spark-1.3":{"draws":11,"losses":31,"wins":8},"meta/muse-wonder":{"draws":8,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":8,"wins":24},"mistralai/mistral-large-4-0":{"draws":10,"losses":6,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":6,"wins":13},"moonshotai/kimi-k3":{"draws":28,"losses":21,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":8,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":10,"wins":37},"o3":{"draws":12,"losses":21,"wins":45},"openai/gpt-oss-120b":{"draws":17,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":32,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":26},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":15,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"stealth/ox-alpha":{"draws":54,"losses":79,"wins":39},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":25},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":15},"thinkingmachines/inkling":{"draws":30,"losses":17,"wins":35},"thinkingmachines/inkling-small":{"draws":18,"losses":6,"wins":26},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":27,"wins":23},"x-ai/grok-4.6":{"draws":13,"losses":24,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":43,"losses":22,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":21,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":39,"losses":43,"wins":66},"z-ai/glm-5.3":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":19},"claude-fable-5":{"draws":5,"losses":31,"wins":6},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":15},"claude-opus-4-5":{"draws":36,"losses":28,"wins":48},"claude-opus-4-8":{"draws":15,"losses":22,"wins":13},"claude-opus-5":{"draws":23,"losses":81,"wins":20},"claude-opus-5-5":{"draws":1,"losses":40,"wins":5},"claude-sonnet-5":{"draws":12,"losses":14,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":9,"wins":50},"deepseek/deepseek-v4-pro":{"draws":9,"losses":20,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"fireworks/ember-1":{"draws":15,"losses":15,"wins":12},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":36},"google/gemini-3.5-flash":{"draws":21,"losses":26,"wins":25},"google/gemini-3.5-flash-lite":{"draws":31,"losses":18,"wins":47},"google/gemini-3.6-flash":{"draws":28,"losses":45,"wins":25},"google/gemini-3.8-flash":{"draws":8,"losses":25,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":11},"gpt-4.1":{"draws":9,"losses":3,"wins":18},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":20,"wins":14},"gpt-5.4":{"draws":9,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":15,"losses":15,"wins":28},"gpt-5.4-nano":{"draws":17,"losses":28,"wins":45},"gpt-5.5":{"draws":21,"losses":39,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":13},"gpt-6-astra":{"draws":3,"losses":39,"wins":4},"gpt-6-luna":{"draws":9,"losses":16,"wins":15},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":15},"inclusionai/ling-3.0-flash":{"draws":24,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":40},"meta/muse-glimmer-30b":{"draws":13,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":15,"losses":14,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":12},"meta/muse-wonder":{"draws":8,"losses":21,"wins":9},"minimax/minimax-m3":{"draws":10,"losses":6,"wins":26},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":23,"wins":14},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":12,"wins":40},"o3":{"draws":8,"losses":34,"wins":28},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":24,"wins":17},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":18,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":13},"stealth/ox-alpha":{"draws":23,"losses":70,"wins":37},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":22},"tencent/hy4-preview":{"draws":9,"losses":25,"wins":10},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":20,"losses":37,"wins":11},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":43,"losses":22,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":20,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":44,"losses":40,"wins":44},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":23,"wins":13}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":59},"claude-fable-5":{"draws":28,"losses":29,"wins":47},"claude-fable-5-1":{"draws":13,"losses":67,"wins":20},"claude-haiku-5-5":{"draws":19,"losses":13,"wins":44},"claude-opus-4-5":{"draws":65,"losses":46,"wins":149},"claude-opus-4-8":{"draws":41,"losses":24,"wins":87},"claude-opus-5":{"draws":48,"losses":166,"wins":96},"claude-opus-5-5":{"draws":14,"losses":62,"wins":16},"claude-sonnet-5":{"draws":19,"losses":26,"wins":55},"claude-sonnet-5-5":{"draws":15,"losses":32,"wins":37},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":28,"losses":14,"wins":112},"deepseek/deepseek-v4-pro":{"draws":17,"losses":16,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":13,"wins":52},"fireworks/ember-1":{"draws":15,"losses":14,"wins":55},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":55},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":51},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":86},"google/gemini-3.5-flash-lite":{"draws":33,"losses":21,"wins":150},"google/gemini-3.6-flash":{"draws":46,"losses":53,"wins":129},"google/gemini-3.8-flash":{"draws":21,"losses":25,"wins":54},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":28},"gpt-4.1":{"draws":15,"losses":4,"wins":42},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":28,"losses":12,"wins":80},"gpt-5.4":{"draws":16,"losses":13,"wins":65},"gpt-5.4-mini":{"draws":32,"losses":10,"wins":54},"gpt-5.4-nano":{"draws":24,"losses":12,"wins":118},"gpt-5.5":{"draws":36,"losses":36,"wins":104},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":66},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":63},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":67},"gpt-6-astra":{"draws":11,"losses":63,"wins":16},"gpt-6-luna":{"draws":20,"losses":9,"wins":53},"gpt-6-sol":{"draws":14,"losses":37,"wins":33},"gpt-6.1-sol":{"draws":13,"losses":53,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"inclusionai/ling-3.0-flash":{"draws":31,"losses":3,"wins":58},"meituan/longcat-2.0":{"draws":25,"losses":9,"wins":108},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":60},"meta/muse-spark-1.2":{"draws":18,"losses":14,"wins":58},"meta/muse-spark-1.3":{"draws":22,"losses":24,"wins":42},"meta/muse-wonder":{"draws":14,"losses":26,"wins":38},"minimax/minimax-m3":{"draws":17,"losses":0,"wins":55},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":30},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":34},"moonshotai/kimi-k3":{"draws":25,"losses":33,"wins":54},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":1,"wins":75},"o3":{"draws":17,"losses":7,"wins":110},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":54},"poolside/laguna-s-2.1":{"draws":24,"losses":12,"wins":114},"qwen/qwen3.7-max":{"draws":13,"losses":13,"wins":66},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":61},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":41},"qwen/qwen3.8-flash":{"draws":15,"losses":9,"wins":34},"qwen/qwen3.8-max":{"draws":23,"losses":21,"wins":52},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":46},"stealth/ox-alpha":{"draws":75,"losses":76,"wins":157},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":42},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":27,"losses":4,"wins":57},"tencent/hy4-preview":{"draws":17,"losses":16,"wins":57},"thinkingmachines/inkling":{"draws":21,"losses":26,"wins":81},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":67},"unbiased/pareto-26.10-preview":{"draws":1,"losses":18,"wins":7},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":31,"losses":27,"wins":96},"x-ai/grok-4.6":{"draws":19,"losses":28,"wins":51},"x-ai/grok-4.7":{"draws":9,"losses":38,"wins":27},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":25},"xiaomi/mimo-v2.5":{"draws":36,"losses":15,"wins":139},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":2,"wins":64},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":16,"wins":27},"z-ai/glm-5.2":{"draws":64,"losses":18,"wins":158},"z-ai/glm-5.3":{"draws":16,"losses":32,"wins":34},"z-ai/glm-5.3-flash":{"draws":18,"losses":24,"wins":50},"z-ai/glm-5.3-flashx":{"draws":17,"losses":24,"wins":43}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":8,"losses":15,"wins":31},"claude-fable-5-1":{"draws":7,"losses":37,"wins":16},"claude-haiku-5-5":{"draws":12,"losses":5,"wins":29},"claude-opus-4-5":{"draws":16,"losses":15,"wins":57},"claude-opus-4-8":{"draws":9,"losses":14,"wins":27},"claude-opus-5":{"draws":16,"losses":50,"wins":28},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":11,"losses":10,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":66},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":36},"fireworks/ember-1":{"draws":8,"losses":11,"wins":35},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":42},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":49},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":17,"losses":9,"wins":68},"google/gemini-3.8-flash":{"draws":12,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":19},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":4,"wins":35},"gpt-5.4":{"draws":10,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":49},"gpt-5.5":{"draws":11,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":10,"losses":12,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":42},"gpt-6-astra":{"draws":8,"losses":34,"wins":12},"gpt-6-luna":{"draws":13,"losses":1,"wins":38},"gpt-6-sol":{"draws":8,"losses":26,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":11,"losses":3,"wins":34},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":36},"meta/muse-wonder":{"draws":6,"losses":17,"wins":25},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-large-4-0":{"draws":9,"losses":1,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":38},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":45},"o3":{"draws":8,"losses":2,"wins":62},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":9,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":29},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":31},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":12,"losses":4,"wins":36},"stealth/ox-alpha":{"draws":39,"losses":24,"wins":109},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":12,"losses":0,"wins":46},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":11,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":13,"wins":28},"x-ai/grok-4.7":{"draws":8,"losses":22,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":7,"wins":17},"z-ai/glm-5.2":{"draws":17,"losses":10,"wins":81},"z-ai/glm-5.3":{"draws":6,"losses":15,"wins":29},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":41},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":28,"wins":29},"claude-fable-5":{"draws":24,"losses":53,"wins":9},"claude-fable-5-1":{"draws":6,"losses":81,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":21,"wins":9},"claude-opus-4-5":{"draws":49,"losses":62,"wins":27},"claude-opus-4-8":{"draws":15,"losses":23,"wins":8},"claude-opus-5":{"draws":12,"losses":63,"wins":13},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":24,"losses":44,"wins":20},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":37,"losses":32,"wins":51},"deepseek/deepseek-v4-pro":{"draws":30,"losses":31,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":31,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"fireworks/ember-1":{"draws":19,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"google/gemini-3.1-flash-lite":{"draws":11,"losses":5,"wins":20},"google/gemini-3.5-flash":{"draws":33,"losses":46,"wins":23},"google/gemini-3.5-flash-lite":{"draws":74,"losses":62,"wins":106},"google/gemini-3.6-flash":{"draws":55,"losses":106,"wins":63},"google/gemini-3.8-flash":{"draws":22,"losses":49,"wins":17},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":13},"gpt-4.1":{"draws":5,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":18,"wins":11},"gpt-5.4":{"draws":43,"losses":64,"wins":17},"gpt-5.4-mini":{"draws":15,"losses":15,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":21},"gpt-5.5":{"draws":19,"losses":21,"wins":6},"gpt-5.6-luna":{"draws":52,"losses":37,"wins":53},"gpt-5.6-sol":{"draws":24,"losses":107,"wins":13},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":17},"gpt-6-astra":{"draws":4,"losses":76,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":45,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":28,"losses":6,"wins":34},"inclusionai/ling-3.0-flash":{"draws":20,"losses":7,"wins":35},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":18,"wins":45},"meta/muse-glimmer-30b":{"draws":31,"losses":16,"wins":35},"meta/muse-spark-1.2":{"draws":32,"losses":47,"wins":21},"meta/muse-spark-1.3":{"draws":27,"losses":37,"wins":10},"meta/muse-wonder":{"draws":8,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":23,"losses":4,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":38,"losses":47,"wins":25},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":12,"wins":16},"o3":{"draws":16,"losses":66,"wins":54},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":40},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":44},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":37,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":20,"wins":14},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":19},"qwen/qwen3.8-max":{"draws":34,"losses":38,"wins":14},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":10},"stealth/ox-alpha":{"draws":66,"losses":140,"wins":70},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":14},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":11},"tencent/hy4-preview":{"draws":28,"losses":42,"wins":16},"thinkingmachines/inkling":{"draws":26,"losses":13,"wins":53},"thinkingmachines/inkling-small":{"draws":26,"losses":20,"wins":44},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":36,"losses":57,"wins":17},"x-ai/grok-4.6":{"draws":28,"losses":44,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":15,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":19,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":9},"z-ai/glm-5.2":{"draws":44,"losses":48,"wins":54},"z-ai/glm-5.3":{"draws":19,"losses":41,"wins":8},"z-ai/glm-5.3-flash":{"draws":20,"losses":38,"wins":26},"z-ai/glm-5.3-flashx":{"draws":14,"losses":27,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":18,"wins":18},"claude-fable-5":{"draws":8,"losses":32,"wins":8},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":22,"wins":13},"claude-opus-4-5":{"draws":18,"losses":34,"wins":26},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":21,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":25,"wins":10},"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":8,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":26,"wins":21},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":42},"google/gemini-3.6-flash":{"draws":17,"losses":49,"wins":18},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":11},"google/gemma-4-31b-it":{"draws":6,"losses":10,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":14,"wins":18},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":23},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":25,"wins":10},"gpt-6-sol":{"draws":4,"losses":42,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":19},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":8},"meta/muse-wonder":{"draws":5,"losses":30,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":25,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":19},"o3":{"draws":8,"losses":29,"wins":27},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":14},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":25,"wins":11},"qwen/qwen3.8-max-0902":{"draws":9,"losses":28,"wins":9},"stealth/ox-alpha":{"draws":42,"losses":89,"wins":25},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":28,"wins":8},"thinkingmachines/inkling":{"draws":13,"losses":21,"wins":20},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":30,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":16,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":27,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":27,"wins":10}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":8,"wins":2},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":3,"losses":23,"wins":0},"claude-opus-4-8":{"draws":0,"losses":11,"wins":1},"claude-opus-5":{"draws":0,"losses":26,"wins":0},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":12,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":13,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":10,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":10,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":11,"wins":1},"fireworks/ember-1":{"draws":0,"losses":10,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":15,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":11,"wins":11},"google/gemini-3.6-flash":{"draws":2,"losses":22,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":14,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":1},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":12,"wins":0},"gpt-5.4":{"draws":0,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":14,"wins":2},"gpt-5.5":{"draws":1,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":11,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":11,"wins":0},"gpt-6-astra":{"draws":0,"losses":14,"wins":0},"gpt-6-luna":{"draws":2,"losses":10,"wins":2},"gpt-6-sol":{"draws":0,"losses":14,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":13,"wins":3},"meta/muse-glimmer-30b":{"draws":4,"losses":9,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":14,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":14,"wins":0},"meta/muse-wonder":{"draws":0,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":2},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":8,"wins":2},"o3":{"draws":2,"losses":25,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":10,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":8,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":12,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":14,"wins":0},"stealth/ox-alpha":{"draws":3,"losses":40,"wins":1},"stealth/space-bunny-alpha":{"draws":2,"losses":12,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":12,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":8,"wins":8},"thinkingmachines/inkling-small":{"draws":2,"losses":9,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":16,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":12,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":13,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.3":{"draws":0,"losses":14,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":12,"wins":0}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":22,"wins":30},"claude-fable-5":{"draws":14,"losses":50,"wins":0},"claude-fable-5-1":{"draws":3,"losses":55,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":4},"claude-opus-4-5":{"draws":29,"losses":50,"wins":17},"claude-opus-4-8":{"draws":8,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":61,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":21,"losses":41,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":31,"wins":26},"deepseek/deepseek-v4-pro":{"draws":17,"losses":31,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":28,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"fireworks/ember-1":{"draws":14,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":23,"losses":38,"wins":21},"google/gemini-3.5-flash-lite":{"draws":44,"losses":49,"wins":49},"google/gemini-3.6-flash":{"draws":23,"losses":85,"wins":16},"google/gemini-3.8-flash":{"draws":13,"losses":50,"wins":5},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":10},"gpt-4.1":{"draws":2,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":25,"wins":9},"gpt-5.4":{"draws":19,"losses":40,"wins":7},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":10,"losses":22,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":34,"wins":24},"gpt-5.6-sol":{"draws":10,"losses":39,"wins":13},"gpt-5.6-terra":{"draws":22,"losses":36,"wins":12},"gpt-6-astra":{"draws":6,"losses":48,"wins":0},"gpt-6-luna":{"draws":12,"losses":20,"wins":8},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":13,"losses":11,"wins":14},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":15,"losses":22,"wins":27},"meta/muse-glimmer-30b":{"draws":33,"losses":23,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":27,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":46,"wins":8},"meta/muse-wonder":{"draws":6,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":6},"mistralai/mistral-large-4-0":{"draws":6,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":12,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":27,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":12,"wins":15},"o3":{"draws":11,"losses":48,"wins":33},"openai/gpt-oss-120b":{"draws":28,"losses":24,"wins":20},"poolside/laguna-s-2.1":{"draws":26,"losses":23,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":36,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":18,"losses":24,"wins":8},"qwen/qwen3.8-max":{"draws":22,"losses":35,"wins":15},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"stealth/ox-alpha":{"draws":57,"losses":120,"wins":57},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":38,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":17,"wins":28},"thinkingmachines/inkling-small":{"draws":34,"losses":16,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":32,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":41,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":42,"losses":54,"wins":30},"z-ai/glm-5.3":{"draws":16,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":27,"losses":31,"wins":10},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":22,"wins":18},"claude-fable-5":{"draws":13,"losses":30,"wins":7},"claude-fable-5-1":{"draws":3,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":12,"wins":7},"claude-opus-4-5":{"draws":21,"losses":42,"wins":11},"claude-opus-4-8":{"draws":8,"losses":18,"wins":6},"claude-opus-5":{"draws":8,"losses":53,"wins":9},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":23,"losses":20,"wins":19},"claude-sonnet-5-5":{"draws":7,"losses":22,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":33,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":21,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"fireworks/ember-1":{"draws":12,"losses":18,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":22},"google/gemini-3.5-flash-lite":{"draws":50,"losses":33,"wins":43},"google/gemini-3.6-flash":{"draws":45,"losses":44,"wins":17},"google/gemini-3.8-flash":{"draws":20,"losses":27,"wins":11},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":15,"losses":11,"wins":10},"gpt-5.4":{"draws":17,"losses":23,"wins":18},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":13,"losses":17,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":28,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":38,"wins":5},"gpt-5.6-terra":{"draws":29,"losses":15,"wins":14},"gpt-6-astra":{"draws":3,"losses":43,"wins":0},"gpt-6-luna":{"draws":10,"losses":16,"wins":8},"gpt-6-sol":{"draws":3,"losses":29,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":12},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":27},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":20},"meta/muse-spark-1.2":{"draws":4,"losses":28,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":33,"wins":10},"meta/muse-wonder":{"draws":2,"losses":23,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":10,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":8},"o3":{"draws":14,"losses":29,"wins":27},"openai/gpt-oss-120b":{"draws":25,"losses":15,"wins":22},"poolside/laguna-s-2.1":{"draws":27,"losses":19,"wins":10},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":24,"wins":14},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":17,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":20,"losses":31,"wins":9},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"stealth/ox-alpha":{"draws":60,"losses":86,"wins":50},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":25,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":25,"losses":9,"wins":24},"thinkingmachines/inkling-small":{"draws":34,"losses":18,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":19,"losses":21,"wins":12},"x-ai/grok-4.6":{"draws":24,"losses":32,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":25,"losses":11,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":48,"losses":34,"wins":30},"z-ai/glm-5.3":{"draws":12,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":17,"losses":32,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":4}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":22,"wins":12},"claude-fable-5":{"draws":14,"losses":34,"wins":6},"claude-fable-5-1":{"draws":3,"losses":55,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":3},"claude-opus-4-5":{"draws":27,"losses":40,"wins":11},"claude-opus-4-8":{"draws":5,"losses":28,"wins":5},"claude-opus-5":{"draws":6,"losses":47,"wins":7},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":21,"losses":26,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":36,"losses":21,"wins":27},"deepseek/deepseek-v4-pro":{"draws":34,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":22,"losses":44,"wins":10},"google/gemini-3.5-flash-lite":{"draws":51,"losses":42,"wins":23},"google/gemini-3.6-flash":{"draws":39,"losses":50,"wins":21},"google/gemini-3.8-flash":{"draws":18,"losses":39,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":9},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":15,"wins":5},"gpt-5.4":{"draws":22,"losses":31,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":12},"gpt-5.5":{"draws":14,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":24,"losses":20,"wins":22},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":26,"losses":28,"wins":10},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":9},"gpt-6-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":4,"wins":14},"inclusionai/ling-3.0-flash":{"draws":18,"losses":11,"wins":9},"meituan/longcat-2.0":{"draws":25,"losses":9,"wins":16},"meta/muse-glimmer-30b":{"draws":28,"losses":14,"wins":20},"meta/muse-spark-1.2":{"draws":14,"losses":23,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":33,"wins":7},"meta/muse-wonder":{"draws":6,"losses":19,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":8,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":19},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":16},"o3":{"draws":15,"losses":23,"wins":34},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":10},"poolside/laguna-s-2.1":{"draws":28,"losses":14,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":9,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":32,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":20,"losses":8,"wins":10},"qwen/qwen3.8-max":{"draws":17,"losses":29,"wins":12},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":70,"losses":94,"wins":40},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":25,"losses":27,"wins":10},"thinkingmachines/inkling":{"draws":27,"losses":15,"wins":10},"thinkingmachines/inkling-small":{"draws":30,"losses":14,"wins":20},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":30,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":30,"losses":12,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":7},"z-ai/glm-5.2":{"draws":48,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":34,"wins":6},"z-ai/glm-5.3-flash":{"draws":21,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":11,"losses":32,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":25,"wins":5},"claude-opus-4-5":{"draws":29,"losses":34,"wins":15},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":2},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":18,"wins":23},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":14,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":6},"fireworks/ember-1":{"draws":18,"losses":26,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":27,"wins":5},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":18,"losses":29,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":34,"wins":15},"google/gemini-3.6-flash":{"draws":28,"losses":46,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":33,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":14,"losses":15,"wins":13},"gpt-5.4":{"draws":17,"losses":27,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":14,"wins":3},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":15},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":18,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":23,"wins":8},"gpt-6-sol":{"draws":9,"losses":32,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":18,"wins":19},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":29,"wins":9},"meta/muse-wonder":{"draws":9,"losses":31,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":17,"losses":33,"wins":14},"openai/gpt-oss-120b":{"draws":20,"losses":15,"wins":7},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":43,"losses":82,"wins":31},"stealth/space-bunny-alpha":{"draws":16,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":19,"losses":11,"wins":24},"thinkingmachines/inkling-small":{"draws":18,"losses":15,"wins":14},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":31,"wins":6},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":30,"wins":4},"z-ai/glm-5.3-flashx":{"draws":14,"losses":30,"wins":4}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":7},"claude-opus-4-5":{"draws":34,"losses":28,"wins":16},"claude-opus-4-8":{"draws":17,"losses":24,"wins":3},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":22},"deepseek/deepseek-v4-pro":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":20,"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":11,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":23,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":40,"losses":24,"wins":20},"google/gemini-3.6-flash":{"draws":29,"losses":39,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":15,"wins":8},"gpt-5.4":{"draws":18,"losses":26,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":21},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":18,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":35,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":18,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":21,"wins":12},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":21,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":24,"losses":8,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":5,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":29,"wins":9},"meta/muse-wonder":{"draws":15,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":10,"wins":10},"o3":{"draws":20,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":26,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":7},"stealth/ox-alpha":{"draws":53,"losses":83,"wins":20},"stealth/space-bunny-alpha":{"draws":16,"losses":10,"wins":12},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":15},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":20,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":18,"wins":16},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":25,"wins":7},"x-ai/grok-4.7":{"draws":6,"losses":33,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":32,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":28,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":25,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":18,"wins":12},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":7},"claude-opus-4-5":{"draws":25,"losses":44,"wins":9},"claude-opus-4-8":{"draws":12,"losses":29,"wins":3},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":28,"losses":26,"wins":18},"deepseek/deepseek-v4-pro":{"draws":16,"losses":24,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":20,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":23,"wins":8},"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":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":30,"wins":21},"google/gemini-3.6-flash":{"draws":27,"losses":50,"wins":7},"google/gemini-3.8-flash":{"draws":10,"losses":37,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":9},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":19,"losses":18,"wins":5},"gpt-5.4":{"draws":14,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":16},"gpt-5.5":{"draws":18,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":39,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":23,"wins":12},"gpt-6-sol":{"draws":8,"losses":36,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":23,"wins":12},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":35,"wins":4},"meta/muse-wonder":{"draws":8,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":6},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":23,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":13,"wins":12},"o3":{"draws":12,"losses":46,"wins":6},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":18,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":27,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-max-0902":{"draws":15,"losses":29,"wins":2},"stealth/ox-alpha":{"draws":39,"losses":104,"wins":13},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":11,"losses":19,"wins":4},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":15,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":14},"thinkingmachines/inkling-small":{"draws":19,"losses":16,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":36,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":40,"wins":18},"z-ai/glm-5.3":{"draws":10,"losses":33,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":29,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":34,"wins":4}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":18,"wins":5},"claude-fable-5":{"draws":4,"losses":26,"wins":0},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":25,"wins":0},"claude-opus-4-5":{"draws":19,"losses":44,"wins":3},"claude-opus-4-8":{"draws":5,"losses":34,"wins":1},"claude-opus-5":{"draws":7,"losses":46,"wins":1},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":6,"losses":23,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":11,"wins":3},"deepseek/deepseek-v4-flash":{"draws":20,"losses":42,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":3},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":18,"wins":14},"google/gemini-3.5-flash":{"draws":6,"losses":34,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":41,"wins":5},"google/gemini-3.6-flash":{"draws":10,"losses":42,"wins":2},"google/gemini-3.8-flash":{"draws":5,"losses":25,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":4},"gpt-4.1":{"draws":7,"losses":15,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":29,"wins":0},"gpt-5.4":{"draws":4,"losses":26,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":21,"wins":2},"gpt-5.4-nano":{"draws":9,"losses":31,"wins":16},"gpt-5.5":{"draws":12,"losses":26,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":20,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":22,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":6,"losses":20,"wins":4},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":15,"wins":10},"meituan/longcat-2.0":{"draws":7,"losses":38,"wins":7},"meta/muse-glimmer-30b":{"draws":12,"losses":14,"wins":4},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":0},"meta/muse-wonder":{"draws":3,"losses":26,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":19,"wins":13},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":12,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":18,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":38,"wins":6},"o3":{"draws":2,"losses":50,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":24,"wins":7},"qwen/qwen3.7-max":{"draws":13,"losses":18,"wins":3},"qwen/qwen3.7-plus":{"draws":12,"losses":27,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":1},"qwen/qwen3.8-max":{"draws":8,"losses":22,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"stealth/ox-alpha":{"draws":12,"losses":68,"wins":8},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":29,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":19,"wins":3},"tencent/hy4-preview":{"draws":2,"losses":28,"wins":0},"thinkingmachines/inkling":{"draws":19,"losses":22,"wins":13},"thinkingmachines/inkling-small":{"draws":10,"losses":19,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":28,"wins":2},"x-ai/grok-4.6":{"draws":3,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":25,"losses":57,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":27,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":19,"losses":58,"wins":7},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":40,"wins":39},"claude-fable-5":{"draws":25,"losses":76,"wins":9},"claude-fable-5-1":{"draws":4,"losses":100,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":41,"wins":19},"claude-opus-4-5":{"draws":51,"losses":88,"wins":39},"claude-opus-4-8":{"draws":31,"losses":56,"wins":9},"claude-opus-5":{"draws":18,"losses":128,"wins":10},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":44,"losses":51,"wins":31},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":57,"losses":59,"wins":64},"deepseek/deepseek-v4-pro":{"draws":39,"losses":52,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":46,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":43,"wins":12},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":24,"losses":38,"wins":22},"google/gemini-3.1-flash-lite":{"draws":21,"losses":15,"wins":42},"google/gemini-3.5-flash":{"draws":25,"losses":63,"wins":16},"google/gemini-3.5-flash-lite":{"draws":78,"losses":93,"wins":61},"google/gemini-3.6-flash":{"draws":65,"losses":108,"wins":43},"google/gemini-3.8-flash":{"draws":30,"losses":74,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":12,"wins":20},"gpt-4.1":{"draws":12,"losses":15,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":29,"losses":39,"wins":24},"gpt-5.4":{"draws":21,"losses":65,"wins":22},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":21},"gpt-5.4-nano":{"draws":25,"losses":41,"wins":54},"gpt-5.5":{"draws":31,"losses":43,"wins":12},"gpt-5.6-luna":{"draws":41,"losses":46,"wins":37},"gpt-5.6-sol":{"draws":10,"losses":83,"wins":11},"gpt-5.6-terra":{"draws":40,"losses":48,"wins":18},"gpt-6-astra":{"draws":4,"losses":92,"wins":2},"gpt-6-luna":{"draws":27,"losses":34,"wins":21},"gpt-6-sol":{"draws":14,"losses":64,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":79,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":16,"wins":34},"inclusionai/ling-3.0-flash":{"draws":32,"losses":11,"wins":35},"meituan/longcat-2.0":{"draws":30,"losses":27,"wins":61},"meta/muse-glimmer-30b":{"draws":48,"losses":29,"wins":39},"meta/muse-spark-1.2":{"draws":26,"losses":56,"wins":20},"meta/muse-spark-1.3":{"draws":25,"losses":68,"wins":15},"meta/muse-wonder":{"draws":10,"losses":65,"wins":5},"minimax/minimax-m3":{"draws":15,"losses":23,"wins":18},"mistralai/mistral-large-4-0":{"draws":16,"losses":23,"wins":9},"mistralai/mistral-medium-3-5":{"draws":27,"losses":15,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":41,"losses":38,"wins":23},"nex-agi/nex-n2-pro":{"draws":16,"losses":12,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":24,"wins":29},"o3":{"draws":29,"losses":73,"wins":64},"openai/gpt-oss-120b":{"draws":43,"losses":36,"wins":33},"poolside/laguna-s-2.1":{"draws":45,"losses":29,"wins":32},"qwen/qwen3.7-max":{"draws":20,"losses":28,"wins":12},"qwen/qwen3.7-plus":{"draws":16,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":67,"wins":12},"qwen/qwen3.8-27b":{"draws":10,"losses":37,"wins":17},"qwen/qwen3.8-flash":{"draws":34,"losses":29,"wins":19},"qwen/qwen3.8-max":{"draws":41,"losses":40,"wins":33},"qwen/qwen3.8-max-0902":{"draws":24,"losses":45,"wins":13},"stealth/ox-alpha":{"draws":75,"losses":216,"wins":61},"stealth/space-bunny-alpha":{"draws":23,"losses":27,"wins":18},"stepfun/step-3.7-flash":{"draws":15,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":20,"wins":13},"tencent/hy4-preview":{"draws":37,"losses":63,"wins":16},"thinkingmachines/inkling":{"draws":29,"losses":41,"wins":50},"thinkingmachines/inkling-small":{"draws":49,"losses":30,"wins":49},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":27,"losses":70,"wins":17},"x-ai/grok-4.6":{"draws":34,"losses":74,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":56,"losses":43,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":25,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":35,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":32,"wins":13},"z-ai/glm-5.2":{"draws":82,"losses":86,"wins":52},"z-ai/glm-5.3":{"draws":20,"losses":69,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":63,"wins":15},"z-ai/glm-5.3-flashx":{"draws":16,"losses":54,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":43,"wins":56},"claude-fable-5":{"draws":32,"losses":95,"wins":25},"claude-fable-5-1":{"draws":11,"losses":149,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":53,"wins":17},"claude-opus-4-5":{"draws":100,"losses":107,"wins":91},"claude-opus-4-8":{"draws":28,"losses":55,"wins":19},"claude-opus-5":{"draws":28,"losses":170,"wins":18},"claude-opus-5-5":{"draws":3,"losses":93,"wins":2},"claude-sonnet-5":{"draws":79,"losses":119,"wins":62},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":14},"deepseek/deepseek-v4-flash":{"draws":75,"losses":59,"wins":80},"deepseek/deepseek-v4-pro":{"draws":52,"losses":67,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":61,"losses":59,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":18},"fireworks/ember-1":{"draws":32,"losses":36,"wins":22},"gemini-3.1-pro-preview":{"draws":32,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":20,"losses":9,"wins":39},"google/gemini-3.5-flash":{"draws":58,"losses":76,"wins":54},"google/gemini-3.5-flash-lite":{"draws":172,"losses":137,"wins":155},"google/gemini-3.6-flash":{"draws":176,"losses":221,"wins":121},"google/gemini-3.8-flash":{"draws":38,"losses":105,"wins":11},"google/gemma-4-31b-it":{"draws":16,"losses":9,"wins":25},"gpt-4.1":{"draws":17,"losses":9,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":33,"losses":30,"wins":25},"gpt-5.4":{"draws":71,"losses":132,"wins":31},"gpt-5.4-mini":{"draws":27,"losses":23,"wins":26},"gpt-5.4-nano":{"draws":38,"losses":40,"wins":54},"gpt-5.5":{"draws":46,"losses":40,"wins":16},"gpt-5.6-luna":{"draws":85,"losses":84,"wins":95},"gpt-5.6-sol":{"draws":25,"losses":184,"wins":33},"gpt-5.6-terra":{"draws":55,"losses":53,"wins":50},"gpt-6-astra":{"draws":5,"losses":141,"wins":0},"gpt-6-luna":{"draws":33,"losses":35,"wins":22},"gpt-6-sol":{"draws":14,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":83,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":66,"losses":10,"wins":52},"inclusionai/ling-3.0-flash":{"draws":74,"losses":8,"wins":88},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":67,"losses":60,"wins":124},"meta/muse-glimmer-30b":{"draws":72,"losses":27,"wins":51},"meta/muse-spark-1.2":{"draws":58,"losses":82,"wins":48},"meta/muse-spark-1.3":{"draws":36,"losses":65,"wins":31},"meta/muse-wonder":{"draws":18,"losses":54,"wins":12},"minimax/minimax-m3":{"draws":18,"losses":18,"wins":20},"mistralai/mistral-large-4-0":{"draws":14,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":40,"losses":16,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":12,"wins":10},"moonshotai/kimi-k3":{"draws":81,"losses":103,"wins":50},"nex-agi/nex-n2-pro":{"draws":23,"losses":14,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":16,"wins":30},"o3":{"draws":49,"losses":126,"wins":111},"openai/gpt-oss-120b":{"draws":52,"losses":35,"wins":55},"poolside/laguna-s-2.1":{"draws":100,"losses":66,"wins":74},"qwen/qwen3.7-max":{"draws":20,"losses":20,"wins":24},"qwen/qwen3.7-plus":{"draws":17,"losses":20,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":55,"losses":67,"wins":34},"qwen/qwen3.8-27b":{"draws":15,"losses":43,"wins":24},"qwen/qwen3.8-flash":{"draws":39,"losses":40,"wins":29},"qwen/qwen3.8-max":{"draws":52,"losses":61,"wins":47},"qwen/qwen3.8-max-0902":{"draws":29,"losses":42,"wins":15},"stealth/ox-alpha":{"draws":124,"losses":237,"wins":121},"stealth/space-bunny-alpha":{"draws":25,"losses":19,"wins":28},"stepfun/step-3.7-flash":{"draws":21,"losses":11,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":23,"wins":10},"tencent/hy4-preview":{"draws":52,"losses":70,"wins":32},"thinkingmachines/inkling":{"draws":81,"losses":61,"wins":92},"thinkingmachines/inkling-small":{"draws":66,"losses":38,"wins":70},"unbiased/pareto-26.10-preview":{"draws":2,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":12},"x-ai/grok-4.5":{"draws":64,"losses":133,"wins":67},"x-ai/grok-4.6":{"draws":38,"losses":86,"wins":28},"x-ai/grok-4.7":{"draws":9,"losses":59,"wins":12},"x-ai/grok-build-0.1":{"draws":15,"losses":5,"wins":11},"xiaomi/mimo-v2.5":{"draws":55,"losses":35,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":23,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":35,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":105,"losses":83,"wins":76},"z-ai/glm-5.3":{"draws":23,"losses":97,"wins":14},"z-ai/glm-5.3-flash":{"draws":46,"losses":90,"wins":30},"z-ai/glm-5.3-flashx":{"draws":28,"losses":41,"wins":21}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":48,"wins":61},"claude-fable-5":{"draws":39,"losses":85,"wins":20},"claude-fable-5-1":{"draws":13,"losses":144,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":17},"claude-opus-4-5":{"draws":107,"losses":127,"wins":78},"claude-opus-4-8":{"draws":32,"losses":43,"wins":29},"claude-opus-5":{"draws":25,"losses":170,"wins":23},"claude-opus-5-5":{"draws":4,"losses":99,"wins":1},"claude-sonnet-5":{"draws":91,"losses":118,"wins":65},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":13,"losses":4,"wins":19},"deepseek/deepseek-v4-flash":{"draws":86,"losses":57,"wins":81},"deepseek/deepseek-v4-pro":{"draws":54,"losses":66,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":67,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":40,"wins":22},"fireworks/ember-1":{"draws":35,"losses":45,"wins":16},"gemini-3.1-pro-preview":{"draws":32,"losses":38,"wins":26},"google/gemini-3.1-flash-lite":{"draws":25,"losses":9,"wins":30},"google/gemini-3.5-flash":{"draws":60,"losses":88,"wins":40},"google/gemini-3.5-flash-lite":{"draws":241,"losses":171,"wins":182},"google/gemini-3.6-flash":{"draws":121,"losses":223,"wins":78},"google/gemini-3.8-flash":{"draws":43,"losses":93,"wins":21},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":22},"gpt-4.1":{"draws":18,"losses":16,"wins":14},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":29,"losses":41,"wins":20},"gpt-5.4":{"draws":79,"losses":118,"wins":49},"gpt-5.4-mini":{"draws":31,"losses":20,"wins":31},"gpt-5.4-nano":{"draws":41,"losses":43,"wins":42},"gpt-5.5":{"draws":49,"losses":41,"wins":22},"gpt-5.6-luna":{"draws":114,"losses":72,"wins":90},"gpt-5.6-sol":{"draws":41,"losses":182,"wins":25},"gpt-5.6-terra":{"draws":61,"losses":60,"wins":35},"gpt-6-astra":{"draws":13,"losses":125,"wins":0},"gpt-6-luna":{"draws":30,"losses":31,"wins":31},"gpt-6-sol":{"draws":13,"losses":76,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":90,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":64,"losses":10,"wins":58},"inclusionai/ling-3.0-flash":{"draws":95,"losses":40,"wins":65},"meituan/longcat-2.0":{"draws":81,"losses":63,"wins":114},"meta/muse-glimmer-30b":{"draws":80,"losses":32,"wins":54},"meta/muse-spark-1.2":{"draws":47,"losses":112,"wins":39},"meta/muse-spark-1.3":{"draws":39,"losses":70,"wins":31},"meta/muse-wonder":{"draws":14,"losses":62,"wins":12},"minimax/minimax-m3":{"draws":20,"losses":15,"wins":35},"mistralai/mistral-large-4-0":{"draws":14,"losses":23,"wins":17},"mistralai/mistral-medium-3-5":{"draws":58,"losses":16,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":14,"wins":6},"moonshotai/kimi-k3":{"draws":100,"losses":118,"wins":34},"nex-agi/nex-n2-pro":{"draws":28,"losses":8,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":17,"wins":28},"o3":{"draws":51,"losses":181,"wins":80},"openai/gpt-oss-120b":{"draws":76,"losses":34,"wins":52},"poolside/laguna-s-2.1":{"draws":135,"losses":62,"wins":77},"qwen/qwen3.7-max":{"draws":26,"losses":22,"wins":26},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":60,"losses":70,"wins":38},"qwen/qwen3.8-27b":{"draws":20,"losses":42,"wins":22},"qwen/qwen3.8-flash":{"draws":57,"losses":32,"wins":29},"qwen/qwen3.8-max":{"draws":58,"losses":81,"wins":45},"qwen/qwen3.8-max-0902":{"draws":29,"losses":40,"wins":23},"stealth/ox-alpha":{"draws":144,"losses":259,"wins":136},"stealth/space-bunny-alpha":{"draws":25,"losses":26,"wins":25},"stepfun/step-3.7-flash":{"draws":21,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":14,"wins":23},"tencent/hy4-preview":{"draws":47,"losses":92,"wins":31},"thinkingmachines/inkling":{"draws":91,"losses":33,"wins":124},"thinkingmachines/inkling-small":{"draws":79,"losses":57,"wins":51},"unbiased/pareto-26.10-preview":{"draws":0,"losses":29,"wins":1},"upstage/solar-mini4":{"draws":7,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":67,"losses":138,"wins":73},"x-ai/grok-4.6":{"draws":51,"losses":83,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":71,"wins":11},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":15},"xiaomi/mimo-v2.5":{"draws":68,"losses":37,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":35,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":100,"losses":105,"wins":63},"z-ai/glm-5.3":{"draws":32,"losses":92,"wins":10},"z-ai/glm-5.3-flash":{"draws":51,"losses":86,"wins":31},"z-ai/glm-5.3-flashx":{"draws":27,"losses":48,"wins":21}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":19,"wins":30},"claude-fable-5":{"draws":15,"losses":55,"wins":18},"claude-fable-5-1":{"draws":7,"losses":87,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":15},"claude-opus-4-5":{"draws":39,"losses":23,"wins":50},"claude-opus-4-8":{"draws":10,"losses":23,"wins":15},"claude-opus-5":{"draws":18,"losses":64,"wins":14},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":27,"losses":20,"wins":39},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":26,"losses":18,"wins":62},"deepseek/deepseek-v4-pro":{"draws":18,"losses":19,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":24,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":16,"wins":18},"fireworks/ember-1":{"draws":13,"losses":18,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":20,"losses":42,"wins":36},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":88},"google/gemini-3.6-flash":{"draws":36,"losses":52,"wins":58},"google/gemini-3.8-flash":{"draws":20,"losses":24,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":12},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":11,"wins":22},"gpt-5.4":{"draws":21,"losses":32,"wins":31},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":34},"gpt-5.5":{"draws":15,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":22,"losses":19,"wins":39},"gpt-5.6-sol":{"draws":13,"losses":47,"wins":27},"gpt-5.6-terra":{"draws":32,"losses":21,"wins":31},"gpt-6-astra":{"draws":10,"losses":73,"wins":5},"gpt-6-luna":{"draws":16,"losses":14,"wins":16},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":39,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":2,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":43},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":38},"meta/muse-spark-1.2":{"draws":17,"losses":24,"wins":27},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":35},"meta/muse-wonder":{"draws":12,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":18},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":21,"losses":19,"wins":34},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":26},"o3":{"draws":12,"losses":27,"wins":59},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":40},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":42},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":26,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":14,"losses":14,"wins":24},"qwen/qwen3.8-max":{"draws":26,"losses":24,"wins":34},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":73,"losses":113,"wins":93},"stealth/space-bunny-alpha":{"draws":14,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":22,"losses":33,"wins":23},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":37},"thinkingmachines/inkling-small":{"draws":29,"losses":11,"wins":44},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":23},"x-ai/grok-4.6":{"draws":30,"losses":34,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":2,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":43,"losses":37,"wins":54},"z-ai/glm-5.3":{"draws":16,"losses":34,"wins":14},"z-ai/glm-5.3-flash":{"draws":14,"losses":36,"wins":30},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":18}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":7},"claude-fable-5":{"draws":7,"losses":24,"wins":1},"claude-fable-5-1":{"draws":3,"losses":32,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":3},"claude-opus-4-5":{"draws":16,"losses":34,"wins":2},"claude-opus-4-8":{"draws":9,"losses":19,"wins":2},"claude-opus-5":{"draws":8,"losses":43,"wins":3},"claude-opus-5-5":{"draws":1,"losses":31,"wins":0},"claude-sonnet-5":{"draws":11,"losses":19,"wins":2},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":15,"losses":21,"wins":8},"deepseek/deepseek-v4-pro":{"draws":8,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":19,"wins":3},"fireworks/ember-1":{"draws":12,"losses":18,"wins":4},"gemini-3.1-pro-preview":{"draws":9,"losses":17,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":5},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":19,"losses":34,"wins":5},"google/gemini-3.8-flash":{"draws":12,"losses":18,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":15,"wins":1},"gpt-5.4":{"draws":8,"losses":18,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":21,"wins":5},"gpt-5.5":{"draws":7,"losses":18,"wins":1},"gpt-5.6-luna":{"draws":10,"losses":16,"wins":4},"gpt-5.6-sol":{"draws":6,"losses":27,"wins":1},"gpt-5.6-terra":{"draws":11,"losses":19,"wins":0},"gpt-6-astra":{"draws":1,"losses":31,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":32,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":9},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":2},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":2},"meta/muse-wonder":{"draws":7,"losses":27,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":3},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":10,"wins":8},"o3":{"draws":6,"losses":34,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":16,"wins":2},"poolside/laguna-s-2.1":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":1},"qwen/qwen3.8-max":{"draws":9,"losses":20,"wins":3},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"stealth/ox-alpha":{"draws":23,"losses":66,"wins":5},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":15,"wins":2},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":2},"thinkingmachines/inkling":{"draws":10,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":24,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":22,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":0},"z-ai/glm-5.2":{"draws":20,"losses":37,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":2},"z-ai/glm-5.3-flashx":{"draws":11,"losses":21,"wins":0}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":11,"wins":17},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":8},"claude-opus-4-5":{"draws":58,"losses":37,"wins":27},"claude-opus-4-8":{"draws":29,"losses":42,"wins":9},"claude-opus-5":{"draws":20,"losses":126,"wins":11},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":11,"losses":5,"wins":16},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":43},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":38,"losses":39,"wins":35},"google/gemini-3.6-flash":{"draws":32,"losses":53,"wins":25},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":7},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":24,"losses":21,"wins":25},"gpt-5.4":{"draws":15,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":29,"losses":27,"wins":12},"gpt-5.4-nano":{"draws":21,"losses":37,"wins":34},"gpt-5.5":{"draws":27,"losses":38,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"gpt-6-astra":{"draws":5,"losses":45,"wins":0},"gpt-6-luna":{"draws":11,"losses":18,"wins":17},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":28,"losses":1,"wins":34},"meituan/longcat-2.0":{"draws":26,"losses":16,"wins":42},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":16},"meta/muse-spark-1.2":{"draws":17,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":18,"losses":30,"wins":4},"meta/muse-wonder":{"draws":7,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":28},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":15,"wins":33},"o3":{"draws":17,"losses":35,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":24,"losses":20,"wins":30},"qwen/qwen3.7-max":{"draws":26,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":19,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":77,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":20},"tencent/hy4-preview":{"draws":13,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":20,"losses":32,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":36,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":14,"losses":8,"wins":12},"xiaomi/mimo-v2.5":{"draws":60,"losses":30,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":14,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":49,"losses":54,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":32,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":13,"wins":11},"claude-fable-5":{"draws":8,"losses":27,"wins":3},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":16,"wins":10},"claude-opus-4-5":{"draws":18,"losses":27,"wins":19},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":13,"losses":69,"wins":6},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":10,"losses":22,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":25,"losses":20,"wins":23},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":10},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":10},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":15,"losses":23,"wins":14},"google/gemini-3.5-flash-lite":{"draws":23,"losses":15,"wins":28},"google/gemini-3.6-flash":{"draws":14,"losses":26,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":7},"gpt-4.1":{"draws":7,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":12,"wins":11},"gpt-5.4":{"draws":9,"losses":22,"wins":5},"gpt-5.4-mini":{"draws":17,"losses":14,"wins":7},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":19},"gpt-5.5":{"draws":20,"losses":28,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":23,"wins":7},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":4,"losses":28,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"inception/mercury-2.5-preview":{"draws":9,"losses":4,"wins":9},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":20,"losses":15,"wins":17},"meta/muse-glimmer-30b":{"draws":12,"losses":10,"wins":18},"meta/muse-spark-1.2":{"draws":7,"losses":25,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":5},"meta/muse-wonder":{"draws":7,"losses":23,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":8,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":16},"o3":{"draws":12,"losses":18,"wins":24},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":1,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-max":{"draws":10,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":17,"wins":9},"stealth/ox-alpha":{"draws":28,"losses":71,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":12},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":14},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":12,"wins":24},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":18,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":25,"losses":10,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":27,"losses":35,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":9,"losses":19,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":23},"claude-fable-5":{"draws":17,"losses":51,"wins":20},"claude-fable-5-1":{"draws":6,"losses":84,"wins":4},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":13},"claude-opus-4-5":{"draws":44,"losses":45,"wins":45},"claude-opus-4-8":{"draws":13,"losses":21,"wins":14},"claude-opus-5":{"draws":15,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":44,"losses":32,"wins":56},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":48,"losses":19,"wins":43},"deepseek/deepseek-v4-pro":{"draws":25,"losses":31,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":25,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"fireworks/ember-1":{"draws":19,"losses":15,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":41,"wins":32},"google/gemini-3.5-flash-lite":{"draws":81,"losses":45,"wins":100},"google/gemini-3.6-flash":{"draws":55,"losses":87,"wins":74},"google/gemini-3.8-flash":{"draws":27,"losses":40,"wins":19},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":16},"gpt-5.4":{"draws":25,"losses":78,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":19},"gpt-5.5":{"draws":19,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":69,"losses":31,"wins":48},"gpt-5.6-sol":{"draws":27,"losses":69,"wins":30},"gpt-5.6-terra":{"draws":37,"losses":25,"wins":18},"gpt-6-astra":{"draws":1,"losses":74,"wins":7},"gpt-6-luna":{"draws":20,"losses":15,"wins":13},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":26},"meituan/longcat-2.0":{"draws":35,"losses":20,"wins":37},"meta/muse-glimmer-30b":{"draws":28,"losses":24,"wins":22},"meta/muse-spark-1.2":{"draws":21,"losses":52,"wins":25},"meta/muse-spark-1.3":{"draws":15,"losses":39,"wins":18},"meta/muse-wonder":{"draws":9,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":7,"wins":8},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":30,"losses":29,"wins":47},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":3,"wins":23},"o3":{"draws":23,"losses":49,"wins":56},"openai/gpt-oss-120b":{"draws":32,"losses":14,"wins":28},"poolside/laguna-s-2.1":{"draws":50,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":37,"wins":24},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":15},"qwen/qwen3.8-flash":{"draws":20,"losses":26,"wins":8},"qwen/qwen3.8-max":{"draws":28,"losses":33,"wins":21},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"stealth/ox-alpha":{"draws":82,"losses":123,"wins":69},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":39,"wins":19},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":45},"thinkingmachines/inkling-small":{"draws":41,"losses":11,"wins":24},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":25,"losses":50,"wins":37},"x-ai/grok-4.6":{"draws":29,"losses":44,"wins":17},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":50,"losses":37,"wins":47},"z-ai/glm-5.3":{"draws":18,"losses":34,"wins":16},"z-ai/glm-5.3-flash":{"draws":20,"losses":38,"wins":28},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":20,"wins":5},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":28,"wins":2},"claude-opus-4-5":{"draws":56,"losses":55,"wins":17},"claude-opus-4-8":{"draws":26,"losses":45,"wins":7},"claude-opus-5":{"draws":32,"losses":76,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":23,"losses":19,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":5},"deepseek/deepseek-v4-flash":{"draws":49,"losses":38,"wins":19},"deepseek/deepseek-v4-pro":{"draws":18,"losses":21,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":20,"wins":5},"fireworks/ember-1":{"draws":23,"losses":22,"wins":3},"gemini-3.1-pro-preview":{"draws":23,"losses":19,"wins":6},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":34},"google/gemini-3.5-flash":{"draws":29,"losses":37,"wins":4},"google/gemini-3.5-flash-lite":{"draws":44,"losses":41,"wins":19},"google/gemini-3.6-flash":{"draws":43,"losses":61,"wins":10},"google/gemini-3.8-flash":{"draws":18,"losses":30,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":7},"gpt-4.1":{"draws":15,"losses":5,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":34,"losses":27,"wins":5},"gpt-5.4":{"draws":20,"losses":26,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":4},"gpt-5.4-nano":{"draws":32,"losses":50,"wins":14},"gpt-5.5":{"draws":36,"losses":30,"wins":10},"gpt-5.6-luna":{"draws":20,"losses":22,"wins":8},"gpt-5.6-sol":{"draws":14,"losses":35,"wins":1},"gpt-5.6-terra":{"draws":22,"losses":22,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":22,"losses":23,"wins":3},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":44,"losses":16,"wins":12},"meituan/longcat-2.0":{"draws":42,"losses":30,"wins":14},"meta/muse-glimmer-30b":{"draws":24,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":28,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":35,"wins":1},"meta/muse-wonder":{"draws":13,"losses":31,"wins":2},"minimax/minimax-m3":{"draws":13,"losses":32,"wins":9},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":0},"moonshotai/kimi-k3":{"draws":23,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":22,"losses":18,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":23,"wins":9},"o3":{"draws":21,"losses":41,"wins":8},"openai/gpt-oss-120b":{"draws":25,"losses":16,"wins":7},"poolside/laguna-s-2.1":{"draws":41,"losses":22,"wins":7},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":24,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":28,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":22,"losses":23,"wins":1},"stealth/ox-alpha":{"draws":59,"losses":89,"wins":12},"stealth/space-bunny-alpha":{"draws":16,"losses":22,"wins":0},"stepfun/step-3.7-flash":{"draws":18,"losses":18,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":20,"wins":6},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":0},"thinkingmachines/inkling":{"draws":36,"losses":25,"wins":19},"thinkingmachines/inkling-small":{"draws":26,"losses":19,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":28,"losses":33,"wins":3},"x-ai/grok-4.6":{"draws":21,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":73,"losses":51,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":16,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":81,"losses":53,"wins":8},"z-ai/glm-5.3":{"draws":17,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":26,"wins":5},"z-ai/glm-5.3-flashx":{"draws":16,"losses":31,"wins":1}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":30,"wins":21},"claude-fable-5":{"draws":11,"losses":58,"wins":3},"claude-fable-5-1":{"draws":1,"losses":75,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":34,"wins":13},"claude-opus-4-5":{"draws":51,"losses":97,"wins":40},"claude-opus-4-8":{"draws":29,"losses":75,"wins":26},"claude-opus-5":{"draws":26,"losses":165,"wins":5},"claude-opus-5-5":{"draws":4,"losses":76,"wins":0},"claude-sonnet-5":{"draws":26,"losses":36,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":53,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":21},"deepseek/deepseek-v4-flash":{"draws":39,"losses":65,"wins":52},"deepseek/deepseek-v4-pro":{"draws":17,"losses":29,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":14},"fireworks/ember-1":{"draws":18,"losses":44,"wins":10},"gemini-3.1-pro-preview":{"draws":22,"losses":34,"wins":16},"google/gemini-3.1-flash-lite":{"draws":18,"losses":30,"wins":50},"google/gemini-3.5-flash":{"draws":26,"losses":67,"wins":19},"google/gemini-3.5-flash-lite":{"draws":60,"losses":56,"wins":50},"google/gemini-3.6-flash":{"draws":43,"losses":85,"wins":32},"google/gemini-3.8-flash":{"draws":18,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":15},"gpt-4.1":{"draws":16,"losses":17,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":20,"losses":47,"wins":19},"gpt-5.4":{"draws":13,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":38,"losses":24,"wins":34},"gpt-5.4-nano":{"draws":35,"losses":52,"wins":43},"gpt-5.5":{"draws":40,"losses":56,"wins":30},"gpt-5.6-luna":{"draws":26,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":59,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":39,"wins":14},"gpt-6-astra":{"draws":3,"losses":71,"wins":0},"gpt-6-luna":{"draws":14,"losses":42,"wins":14},"gpt-6-sol":{"draws":7,"losses":57,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":65,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":11,"wins":25},"inclusionai/ling-3.0-flash":{"draws":40,"losses":12,"wins":44},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":41,"wins":54},"meta/muse-glimmer-30b":{"draws":18,"losses":20,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":39,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":49,"wins":7},"meta/muse-wonder":{"draws":5,"losses":49,"wins":10},"minimax/minimax-m3":{"draws":26,"losses":28,"wins":34},"mistralai/mistral-large-4-0":{"draws":8,"losses":23,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":9,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":7,"wins":10},"moonshotai/kimi-k3":{"draws":22,"losses":53,"wins":15},"nex-agi/nex-n2-pro":{"draws":21,"losses":31,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":29,"wins":44},"o3":{"draws":14,"losses":66,"wins":42},"openai/gpt-oss-120b":{"draws":26,"losses":22,"wins":16},"poolside/laguna-s-2.1":{"draws":52,"losses":41,"wins":31},"qwen/qwen3.7-max":{"draws":34,"losses":36,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":28,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":45,"wins":15},"qwen/qwen3.8-27b":{"draws":15,"losses":24,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":24,"wins":12},"qwen/qwen3.8-max":{"draws":17,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":22,"losses":33,"wins":13},"stealth/ox-alpha":{"draws":51,"losses":134,"wins":51},"stealth/space-bunny-alpha":{"draws":13,"losses":27,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":25,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":38,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":48,"wins":10},"thinkingmachines/inkling":{"draws":26,"losses":42,"wins":32},"thinkingmachines/inkling-small":{"draws":28,"losses":23,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":19,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":19,"losses":62,"wins":13},"x-ai/grok-4.6":{"draws":15,"losses":45,"wins":12},"x-ai/grok-4.7":{"draws":10,"losses":54,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":22},"xiaomi/mimo-v2.5":{"draws":58,"losses":86,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":43,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":25,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":68,"losses":84,"wins":46},"z-ai/glm-5.3":{"draws":13,"losses":46,"wins":11},"z-ai/glm-5.3-flash":{"draws":15,"losses":43,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":40,"wins":14}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":10,"wins":13},"claude-fable-5":{"draws":13,"losses":23,"wins":8},"claude-fable-5-1":{"draws":2,"losses":45,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":15,"wins":6},"claude-opus-4-5":{"draws":64,"losses":39,"wins":19},"claude-opus-4-8":{"draws":31,"losses":29,"wins":8},"claude-opus-5":{"draws":30,"losses":105,"wins":1},"claude-opus-5-5":{"draws":8,"losses":38,"wins":0},"claude-sonnet-5":{"draws":22,"losses":10,"wins":12},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":44,"losses":8,"wins":22},"deepseek/deepseek-v4-pro":{"draws":21,"losses":13,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":8},"fireworks/ember-1":{"draws":17,"losses":17,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":11},"google/gemini-3.1-flash-lite":{"draws":17,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":24,"losses":18,"wins":10},"google/gemini-3.5-flash-lite":{"draws":56,"losses":18,"wins":24},"google/gemini-3.6-flash":{"draws":40,"losses":45,"wins":19},"google/gemini-3.8-flash":{"draws":19,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":8},"gpt-4.1":{"draws":14,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":30,"losses":18,"wins":8},"gpt-5.4":{"draws":14,"losses":17,"wins":9},"gpt-5.4-mini":{"draws":31,"losses":11,"wins":10},"gpt-5.4-nano":{"draws":32,"losses":12,"wins":28},"gpt-5.5":{"draws":30,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":25,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":13,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":14,"losses":15,"wins":11},"gpt-6-sol":{"draws":10,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":47,"losses":2,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":15,"wins":17},"meta/muse-glimmer-30b":{"draws":24,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":6},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":14,"wins":14},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":16,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":24,"losses":23,"wins":11},"nex-agi/nex-n2-pro":{"draws":18,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":6,"wins":15},"o3":{"draws":24,"losses":17,"wins":23},"openai/gpt-oss-120b":{"draws":22,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":39,"losses":19,"wins":12},"qwen/qwen3.7-max":{"draws":27,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":19,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":17,"wins":8},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":17,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":18,"wins":5},"stealth/ox-alpha":{"draws":51,"losses":68,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":7,"wins":9},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":13,"wins":7},"tencent/hy4-preview":{"draws":20,"losses":20,"wins":4},"thinkingmachines/inkling":{"draws":33,"losses":9,"wins":32},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":30,"wins":2},"x-ai/grok-4.6":{"draws":19,"losses":24,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":19,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":78,"losses":14,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":11,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":57,"losses":38,"wins":35},"z-ai/glm-5.3":{"draws":9,"losses":23,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":8},"z-ai/glm-5.3-flashx":{"draws":18,"losses":18,"wins":6}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":45,"wins":16},"claude-fable-5":{"draws":16,"losses":39,"wins":5},"claude-fable-5-1":{"draws":2,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":29,"wins":2},"claude-opus-4-5":{"draws":42,"losses":79,"wins":13},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":9,"losses":72,"wins":5},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":41,"losses":83,"wins":14},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":47,"losses":49,"wins":16},"deepseek/deepseek-v4-pro":{"draws":27,"losses":43,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":35,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":28,"wins":6},"fireworks/ember-1":{"draws":15,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":26,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":16,"wins":9},"google/gemini-3.5-flash":{"draws":20,"losses":56,"wins":10},"google/gemini-3.5-flash-lite":{"draws":61,"losses":127,"wins":58},"google/gemini-3.6-flash":{"draws":66,"losses":132,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":55,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":13,"wins":3},"gpt-4.1":{"draws":4,"losses":11,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":27,"wins":4},"gpt-5.4":{"draws":40,"losses":74,"wins":10},"gpt-5.4-mini":{"draws":11,"losses":17,"wins":4},"gpt-5.4-nano":{"draws":15,"losses":27,"wins":10},"gpt-5.5":{"draws":13,"losses":28,"wins":3},"gpt-5.6-luna":{"draws":41,"losses":41,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":92,"wins":10},"gpt-5.6-terra":{"draws":26,"losses":38,"wins":16},"gpt-6-astra":{"draws":5,"losses":47,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":26,"wins":10},"inclusionai/ling-3.0-flash":{"draws":25,"losses":25,"wins":6},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":51,"wins":18},"meta/muse-glimmer-30b":{"draws":34,"losses":44,"wins":6},"meta/muse-spark-1.2":{"draws":31,"losses":51,"wins":16},"meta/muse-spark-1.3":{"draws":17,"losses":44,"wins":5},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":17,"wins":3},"mistralai/mistral-medium-3-5":{"draws":20,"losses":20,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":32,"losses":59,"wins":11},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":24,"wins":6},"o3":{"draws":14,"losses":106,"wins":14},"openai/gpt-oss-120b":{"draws":36,"losses":28,"wins":16},"poolside/laguna-s-2.1":{"draws":32,"losses":48,"wins":12},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":0},"qwen/qwen3.8-27b":{"draws":13,"losses":23,"wins":4},"qwen/qwen3.8-flash":{"draws":22,"losses":20,"wins":10},"qwen/qwen3.8-max":{"draws":24,"losses":46,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":31,"wins":3},"stealth/ox-alpha":{"draws":84,"losses":146,"wins":14},"stealth/space-bunny-alpha":{"draws":15,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":16,"wins":7},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":18,"wins":0},"tencent/hy4-preview":{"draws":20,"losses":46,"wins":8},"thinkingmachines/inkling":{"draws":34,"losses":32,"wins":24},"thinkingmachines/inkling-small":{"draws":35,"losses":47,"wins":14},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":33,"losses":62,"wins":5},"x-ai/grok-4.6":{"draws":16,"losses":51,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":35,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":17,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":49,"losses":72,"wins":9},"z-ai/glm-5.3":{"draws":14,"losses":42,"wins":2},"z-ai/glm-5.3-flash":{"draws":23,"losses":37,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":34,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":6,"wins":49},"claude-fable-5":{"draws":15,"losses":58,"wins":23},"claude-fable-5-1":{"draws":5,"losses":95,"wins":8},"claude-haiku-5-5":{"draws":4,"losses":22,"wins":20},"claude-opus-4-5":{"draws":36,"losses":27,"wins":81},"claude-opus-4-8":{"draws":16,"losses":26,"wins":16},"claude-opus-5":{"draws":9,"losses":73,"wins":8},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":47,"losses":27,"wins":80},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":10},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":65},"deepseek/deepseek-v4-pro":{"draws":20,"losses":29,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":31,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":10,"losses":13,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":19,"losses":34,"wins":51},"google/gemini-3.5-flash-lite":{"draws":62,"losses":28,"wins":146},"google/gemini-3.6-flash":{"draws":47,"losses":82,"wins":103},"google/gemini-3.8-flash":{"draws":19,"losses":41,"wins":34},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":14,"wins":22},"gpt-5.4":{"draws":43,"losses":64,"wins":37},"gpt-5.4-mini":{"draws":16,"losses":9,"wins":13},"gpt-5.4-nano":{"draws":13,"losses":7,"wins":30},"gpt-5.5":{"draws":14,"losses":22,"wins":10},"gpt-5.6-luna":{"draws":41,"losses":27,"wins":64},"gpt-5.6-sol":{"draws":14,"losses":59,"wins":29},"gpt-5.6-terra":{"draws":34,"losses":23,"wins":33},"gpt-6-astra":{"draws":5,"losses":83,"wins":8},"gpt-6-luna":{"draws":12,"losses":11,"wins":23},"gpt-6-sol":{"draws":3,"losses":36,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":0,"wins":37},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":37},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":22,"losses":8,"wins":74},"meta/muse-glimmer-30b":{"draws":24,"losses":8,"wins":40},"meta/muse-spark-1.2":{"draws":23,"losses":36,"wins":43},"meta/muse-spark-1.3":{"draws":11,"losses":31,"wins":28},"meta/muse-wonder":{"draws":10,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":12},"mistralai/mistral-medium-3-5":{"draws":16,"losses":3,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":25,"losses":31,"wins":46},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":28},"o3":{"draws":8,"losses":29,"wins":103},"openai/gpt-oss-120b":{"draws":22,"losses":2,"wins":58},"poolside/laguna-s-2.1":{"draws":30,"losses":5,"wins":61},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":38,"wins":33},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":25},"qwen/qwen3.8-flash":{"draws":23,"losses":16,"wins":21},"qwen/qwen3.8-max":{"draws":23,"losses":31,"wins":39},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":18},"stealth/ox-alpha":{"draws":62,"losses":116,"wins":117},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":22},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":18},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":36},"thinkingmachines/inkling":{"draws":23,"losses":8,"wins":57},"thinkingmachines/inkling-small":{"draws":24,"losses":8,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":56,"wins":40},"x-ai/grok-4.6":{"draws":25,"losses":42,"wins":29},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":5,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":14,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":38,"wins":71},"z-ai/glm-5.3":{"draws":12,"losses":40,"wins":22},"z-ai/glm-5.3-flash":{"draws":18,"losses":38,"wins":38},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"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-haiku-5-5":{"draws":13,"losses":18,"wins":5},"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},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"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},"fireworks/ember-1":{"draws":16,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":18,"losses":17,"wins":7},"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":13,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":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":24,"losses":11,"wins":15},"gpt-6-astra":{"draws":8,"losses":61,"wins":3},"gpt-6-luna":{"draws":16,"losses":18,"wins":6},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":24},"inclusionai/ling-3.0-flash":{"draws":18,"losses":9,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"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":29,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":20,"losses":28,"wins":16},"meta/muse-wonder":{"draws":10,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":5,"wins":7},"mistralai/mistral-large-4-0":{"draws":12,"losses":7,"wins":3},"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":25,"losses":29,"wins":8},"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":26,"losses":38,"wins":18},"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":19,"losses":18,"wins":3},"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":17,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":101,"losses":104,"wins":41},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":3},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":27,"losses":30,"wins":11},"thinkingmachines/inkling":{"draws":22,"losses":13,"wins":21},"thinkingmachines/inkling-small":{"draws":30,"losses":16,"wins":30},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":21,"losses":39,"wins":6},"x-ai/grok-4.6":{"draws":29,"losses":42,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"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":8,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":66,"losses":25,"wins":31},"z-ai/glm-5.3":{"draws":22,"losses":29,"wins":5},"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":8,"losses":8,"wins":46},"claude-fable-5":{"draws":9,"losses":21,"wins":62},"claude-fable-5-1":{"draws":10,"losses":49,"wins":49},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":34},"claude-opus-4-5":{"draws":12,"losses":10,"wins":88},"claude-opus-4-8":{"draws":8,"losses":7,"wins":35},"claude-opus-5":{"draws":15,"losses":28,"wins":47},"claude-opus-5-5":{"draws":7,"losses":27,"wins":18},"claude-sonnet-5":{"draws":10,"losses":12,"wins":64},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":32},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":82},"deepseek/deepseek-v4-pro":{"draws":9,"losses":9,"wins":52},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":0,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":2,"wins":35},"fireworks/ember-1":{"draws":9,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":18,"losses":1,"wins":77},"google/gemini-3.5-flash-lite":{"draws":12,"losses":2,"wins":112},"google/gemini-3.6-flash":{"draws":22,"losses":11,"wins":99},"google/gemini-3.8-flash":{"draws":13,"losses":11,"wins":66},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":20},"gpt-4.1":{"draws":4,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":0,"wins":37},"gpt-5.4":{"draws":11,"losses":13,"wins":58},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":47},"gpt-5.5":{"draws":3,"losses":3,"wins":38},"gpt-5.6-luna":{"draws":13,"losses":1,"wins":52},"gpt-5.6-sol":{"draws":13,"losses":6,"wins":75},"gpt-5.6-terra":{"draws":16,"losses":5,"wins":61},"gpt-6-astra":{"draws":9,"losses":31,"wins":24},"gpt-6-luna":{"draws":8,"losses":4,"wins":34},"gpt-6-sol":{"draws":3,"losses":15,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":23,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":36},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":52},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":49},"meta/muse-spark-1.2":{"draws":6,"losses":4,"wins":54},"meta/muse-spark-1.3":{"draws":11,"losses":9,"wins":44},"meta/muse-wonder":{"draws":8,"losses":6,"wins":32},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":27},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":54},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":36},"o3":{"draws":4,"losses":0,"wins":86},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":47},"poolside/laguna-s-2.1":{"draws":13,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":7,"wins":69},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":41},"qwen/qwen3.8-flash":{"draws":15,"losses":1,"wins":36},"qwen/qwen3.8-max":{"draws":14,"losses":4,"wins":62},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":35},"stealth/ox-alpha":{"draws":43,"losses":20,"wins":217},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":33},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":29},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":14,"losses":4,"wins":64},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":54},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":62},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":8},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":51},"x-ai/grok-4.6":{"draws":13,"losses":14,"wins":65},"x-ai/grok-4.7":{"draws":6,"losses":9,"wins":27},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":17,"losses":9,"wins":90},"z-ai/glm-5.3":{"draws":17,"losses":5,"wins":52},"z-ai/glm-5.3-flash":{"draws":13,"losses":9,"wins":64},"z-ai/glm-5.3-flashx":{"draws":10,"losses":3,"wins":35}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":8,"wins":16},"claude-fable-5":{"draws":12,"losses":25,"wins":5},"claude-fable-5-1":{"draws":3,"losses":46,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":20,"wins":9},"claude-opus-4-5":{"draws":28,"losses":19,"wins":23},"claude-opus-4-8":{"draws":15,"losses":20,"wins":5},"claude-opus-5":{"draws":17,"losses":53,"wins":4},"claude-opus-5-5":{"draws":3,"losses":41,"wins":0},"claude-sonnet-5":{"draws":14,"losses":12,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":24,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":14,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":13,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":19,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":19,"losses":23,"wins":14},"google/gemini-3.5-flash-lite":{"draws":38,"losses":15,"wins":29},"google/gemini-3.6-flash":{"draws":30,"losses":32,"wins":14},"google/gemini-3.8-flash":{"draws":14,"losses":24,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":3,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":12},"gpt-5.4":{"draws":16,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":18,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":18},"gpt-5.5":{"draws":19,"losses":14,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":24,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":14},"gpt-6-astra":{"draws":3,"losses":37,"wins":4},"gpt-6-luna":{"draws":8,"losses":8,"wins":12},"gpt-6-sol":{"draws":8,"losses":28,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":17,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":11},"meta/muse-spark-1.3":{"draws":9,"losses":30,"wins":5},"meta/muse-wonder":{"draws":15,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":14},"o3":{"draws":13,"losses":20,"wins":25},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":14},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":40,"losses":71,"wins":39},"stealth/space-bunny-alpha":{"draws":15,"losses":5,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":9},"thinkingmachines/inkling":{"draws":18,"losses":12,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":12,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":10},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":9},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":34,"losses":6,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":4,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":23,"wins":33},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":9}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":8,"losses":20,"wins":20},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":9,"losses":12,"wins":21},"claude-opus-4-5":{"draws":15,"losses":11,"wins":52},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":7,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":15,"wins":35},"google/gemini-3.5-flash-lite":{"draws":12,"losses":8,"wins":64},"google/gemini-3.6-flash":{"draws":14,"losses":25,"wins":45},"google/gemini-3.8-flash":{"draws":9,"losses":20,"wins":19},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":21},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":5,"losses":9,"wins":30},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":29},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":6,"wins":31},"gpt-6-sol":{"draws":5,"losses":21,"wins":6},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":9,"wins":27},"meta/muse-wonder":{"draws":12,"losses":21,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":36},"o3":{"draws":4,"losses":4,"wins":56},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":10,"losses":3,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":24},"stealth/ox-alpha":{"draws":25,"losses":33,"wins":98},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":42},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":12,"wins":22},"x-ai/grok-4.6":{"draws":12,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":23,"losses":12,"wins":61},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":21,"wins":20}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":32},"claude-fable-5":{"draws":4,"losses":18,"wins":26},"claude-fable-5-1":{"draws":4,"losses":35,"wins":15},"claude-haiku-5-5":{"draws":8,"losses":4,"wins":34},"claude-opus-4-5":{"draws":18,"losses":9,"wins":51},"claude-opus-4-8":{"draws":4,"losses":9,"wins":31},"claude-opus-5":{"draws":14,"losses":36,"wins":32},"claude-opus-5-5":{"draws":10,"losses":25,"wins":17},"claude-sonnet-5":{"draws":5,"losses":7,"wins":36},"claude-sonnet-5-5":{"draws":2,"losses":17,"wins":29},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":61},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":3,"wins":35},"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":29},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":64},"google/gemini-3.8-flash":{"draws":14,"losses":8,"wins":26},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":4,"losses":10,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":8,"losses":9,"wins":31},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":5,"losses":35,"wins":8},"gpt-6-luna":{"draws":10,"losses":4,"wins":32},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":44},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":7,"losses":7,"wins":30},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":31},"meta/muse-wonder":{"draws":8,"losses":13,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":32},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"o3":{"draws":2,"losses":7,"wins":57},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":37},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":31},"qwen/qwen3.8-27b":{"draws":7,"losses":1,"wins":26},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":23},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":38},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":29},"stealth/ox-alpha":{"draws":26,"losses":18,"wins":112},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":30},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":30},"x-ai/grok-4.6":{"draws":11,"losses":5,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":5,"wins":73},"z-ai/glm-5.3":{"draws":8,"losses":12,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":13,"losses":8,"wins":27}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":17,"wins":19},"claude-fable-5":{"draws":15,"losses":22,"wins":7},"claude-fable-5-1":{"draws":5,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":27,"losses":28,"wins":9},"claude-opus-4-8":{"draws":11,"losses":7,"wins":8},"claude-opus-5":{"draws":13,"losses":35,"wins":2},"claude-opus-5-5":{"draws":4,"losses":26,"wins":0},"claude-sonnet-5":{"draws":23,"losses":19,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":27,"losses":24,"wins":17},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":25,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":12,"wins":3},"fireworks/ember-1":{"draws":13,"losses":12,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":8,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":20,"losses":23,"wins":13},"google/gemini-3.5-flash-lite":{"draws":37,"losses":27,"wins":40},"google/gemini-3.6-flash":{"draws":26,"losses":41,"wins":15},"google/gemini-3.8-flash":{"draws":21,"losses":25,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":7},"gpt-5.4":{"draws":26,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":9},"gpt-5.5":{"draws":13,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":28,"losses":19,"wins":11},"gpt-5.6-sol":{"draws":14,"losses":35,"wins":1},"gpt-5.6-terra":{"draws":24,"losses":18,"wins":10},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":4},"gpt-6-sol":{"draws":7,"losses":22,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":8},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":18,"losses":14,"wins":16},"meta/muse-glimmer-30b":{"draws":23,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":18,"losses":17,"wins":9},"meta/muse-spark-1.3":{"draws":12,"losses":25,"wins":7},"meta/muse-wonder":{"draws":10,"losses":17,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":6,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":24,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":8},"o3":{"draws":9,"losses":27,"wins":14},"openai/gpt-oss-120b":{"draws":21,"losses":11,"wins":18},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":29,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":16,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":8},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":2},"stealth/ox-alpha":{"draws":63,"losses":88,"wins":36},"stealth/space-bunny-alpha":{"draws":8,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":25,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":21,"losses":7,"wins":20},"thinkingmachines/inkling-small":{"draws":29,"losses":11,"wins":20},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":19,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":19,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":41,"losses":32,"wins":15},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":5},"z-ai/glm-5.3-flash":{"draws":17,"losses":23,"wins":8},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":28,"wins":10},"claude-fable-5":{"draws":14,"losses":47,"wins":3},"claude-fable-5-1":{"draws":5,"losses":63,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":33,"wins":4},"claude-opus-4-5":{"draws":57,"losses":67,"wins":12},"claude-opus-4-8":{"draws":39,"losses":55,"wins":0},"claude-opus-5":{"draws":31,"losses":111,"wins":8},"claude-opus-5-5":{"draws":4,"losses":70,"wins":0},"claude-sonnet-5":{"draws":26,"losses":37,"wins":7},"claude-sonnet-5-5":{"draws":16,"losses":43,"wins":3},"cohere/north-mini-code":{"draws":20,"losses":9,"wins":9},"deepseek/deepseek-v4-flash":{"draws":67,"losses":48,"wins":27},"deepseek/deepseek-v4-pro":{"draws":25,"losses":25,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":27,"wins":6},"fireworks/ember-1":{"draws":29,"losses":31,"wins":0},"gemini-3.1-pro-preview":{"draws":25,"losses":32,"wins":5},"google/gemini-3.1-flash-lite":{"draws":30,"losses":30,"wins":16},"google/gemini-3.5-flash":{"draws":32,"losses":49,"wins":5},"google/gemini-3.5-flash-lite":{"draws":87,"losses":65,"wins":18},"google/gemini-3.6-flash":{"draws":90,"losses":80,"wins":16},"google/gemini-3.8-flash":{"draws":21,"losses":41,"wins":0},"google/gemma-4-31b-it":{"draws":17,"losses":8,"wins":5},"gpt-4.1":{"draws":22,"losses":27,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":31,"losses":23,"wins":34},"gpt-5.4":{"draws":20,"losses":32,"wins":6},"gpt-5.4-mini":{"draws":49,"losses":29,"wins":12},"gpt-5.4-nano":{"draws":50,"losses":53,"wins":21},"gpt-5.5":{"draws":67,"losses":39,"wins":6},"gpt-5.6-luna":{"draws":33,"losses":24,"wins":7},"gpt-5.6-sol":{"draws":9,"losses":58,"wins":1},"gpt-5.6-terra":{"draws":25,"losses":40,"wins":3},"gpt-6-astra":{"draws":3,"losses":58,"wins":1},"gpt-6-luna":{"draws":24,"losses":31,"wins":7},"gpt-6-sol":{"draws":10,"losses":46,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":61,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":32,"losses":24,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":79,"losses":51,"wins":24},"meta/muse-glimmer-30b":{"draws":33,"losses":17,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":37,"wins":5},"meta/muse-spark-1.3":{"draws":15,"losses":42,"wins":5},"meta/muse-wonder":{"draws":9,"losses":48,"wins":5},"minimax/minimax-m3":{"draws":36,"losses":35,"wins":9},"mistralai/mistral-large-4-0":{"draws":15,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":15,"losses":22,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":4},"moonshotai/kimi-k3":{"draws":40,"losses":34,"wins":6},"nex-agi/nex-n2-pro":{"draws":44,"losses":24,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":29,"wins":17},"o3":{"draws":31,"losses":49,"wins":6},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":2},"poolside/laguna-s-2.1":{"draws":77,"losses":43,"wins":20},"qwen/qwen3.7-max":{"draws":43,"losses":18,"wins":11},"qwen/qwen3.7-plus":{"draws":31,"losses":19,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":41,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":29,"wins":9},"qwen/qwen3.8-flash":{"draws":22,"losses":26,"wins":2},"qwen/qwen3.8-max":{"draws":28,"losses":35,"wins":7},"qwen/qwen3.8-max-0902":{"draws":25,"losses":32,"wins":3},"stealth/ox-alpha":{"draws":72,"losses":143,"wins":9},"stealth/space-bunny-alpha":{"draws":24,"losses":16,"wins":6},"stepfun/step-3.7-flash":{"draws":23,"losses":20,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":25,"losses":33,"wins":8},"tencent/hy4-preview":{"draws":26,"losses":34,"wins":2},"thinkingmachines/inkling":{"draws":51,"losses":48,"wins":35},"thinkingmachines/inkling-small":{"draws":33,"losses":20,"wins":11},"unbiased/pareto-26.10-preview":{"draws":2,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":29,"losses":76,"wins":9},"x-ai/grok-4.6":{"draws":24,"losses":37,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":47,"wins":3},"x-ai/grok-build-0.1":{"draws":19,"losses":23,"wins":0},"xiaomi/mimo-v2.5":{"draws":85,"losses":64,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":29,"losses":28,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":32,"wins":3},"z-ai/glm-5.2":{"draws":111,"losses":51,"wins":16},"z-ai/glm-5.3":{"draws":19,"losses":38,"wins":3},"z-ai/glm-5.3-flash":{"draws":24,"losses":32,"wins":6},"z-ai/glm-5.3-flashx":{"draws":21,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":0,"wins":0},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":0,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":0},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":3,"losses":0,"wins":1},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":3,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":6,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":4,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":0,"losses":2,"wins":0},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":1},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":0,"wins":0}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":33,"wins":22},"claude-fable-5":{"draws":12,"losses":64,"wins":10},"claude-fable-5-1":{"draws":0,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":48,"wins":10},"claude-opus-4-5":{"draws":65,"losses":110,"wins":33},"claude-opus-4-8":{"draws":22,"losses":68,"wins":18},"claude-opus-5":{"draws":23,"losses":174,"wins":18},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":30,"losses":41,"wins":17},"claude-sonnet-5-5":{"draws":12,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":13,"losses":7,"wins":24},"deepseek/deepseek-v4-flash":{"draws":54,"losses":66,"wins":60},"deepseek/deepseek-v4-pro":{"draws":21,"losses":47,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":44,"wins":20},"fireworks/ember-1":{"draws":32,"losses":47,"wins":5},"gemini-3.1-pro-preview":{"draws":24,"losses":39,"wins":21},"google/gemini-3.1-flash-lite":{"draws":25,"losses":33,"wins":58},"google/gemini-3.5-flash":{"draws":28,"losses":68,"wins":20},"google/gemini-3.5-flash-lite":{"draws":73,"losses":93,"wins":40},"google/gemini-3.6-flash":{"draws":67,"losses":118,"wins":43},"google/gemini-3.8-flash":{"draws":15,"losses":67,"wins":4},"google/gemma-4-31b-it":{"draws":16,"losses":11,"wins":17},"gpt-4.1":{"draws":16,"losses":32,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":42,"losses":58,"wins":36},"gpt-5.4":{"draws":26,"losses":52,"wins":8},"gpt-5.4-mini":{"draws":50,"losses":35,"wins":25},"gpt-5.4-nano":{"draws":38,"losses":86,"wins":56},"gpt-5.5":{"draws":65,"losses":42,"wins":27},"gpt-5.6-luna":{"draws":27,"losses":36,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":75,"wins":5},"gpt-5.6-terra":{"draws":31,"losses":44,"wins":17},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":22,"losses":44,"wins":16},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":76,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":16,"wins":19},"inclusionai/ling-3.0-flash":{"draws":70,"losses":36,"wins":50},"meituan/longcat-2.0":{"draws":38,"losses":37,"wins":32},"meta/muse-glimmer-30b":{"draws":35,"losses":24,"wins":17},"meta/muse-spark-1.2":{"draws":18,"losses":51,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":60,"wins":12},"meta/muse-wonder":{"draws":18,"losses":50,"wins":10},"minimax/minimax-m3":{"draws":22,"losses":30,"wins":32},"mistralai/mistral-large-4-0":{"draws":15,"losses":24,"wins":7},"mistralai/mistral-medium-3-5":{"draws":22,"losses":18,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":23,"wins":4},"moonshotai/kimi-k3":{"draws":42,"losses":41,"wins":21},"nex-agi/nex-n2-pro":{"draws":23,"losses":23,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":66,"losses":40,"wins":28},"o3":{"draws":31,"losses":77,"wins":34},"openai/gpt-oss-120b":{"draws":26,"losses":23,"wins":25},"poolside/laguna-s-2.1":{"draws":75,"losses":63,"wins":34},"qwen/qwen3.7-max":{"draws":39,"losses":34,"wins":17},"qwen/qwen3.7-plus":{"draws":20,"losses":26,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":51,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":27,"losses":25,"wins":12},"qwen/qwen3.8-max":{"draws":29,"losses":40,"wins":21},"qwen/qwen3.8-max-0902":{"draws":18,"losses":48,"wins":14},"stealth/ox-alpha":{"draws":67,"losses":187,"wins":42},"stealth/space-bunny-alpha":{"draws":22,"losses":33,"wins":11},"stepfun/step-3.7-flash":{"draws":18,"losses":28,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":33,"wins":26},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":12},"thinkingmachines/inkling":{"draws":42,"losses":61,"wins":53},"thinkingmachines/inkling-small":{"draws":34,"losses":26,"wins":26},"unbiased/pareto-26.10-preview":{"draws":1,"losses":22,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":8,"wins":10},"x-ai/grok-4.5":{"draws":30,"losses":91,"wins":25},"x-ai/grok-4.6":{"draws":32,"losses":51,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":17,"losses":15,"wins":18},"xiaomi/mimo-v2.5":{"draws":81,"losses":77,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":49,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":30,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":37,"wins":5},"z-ai/glm-5.2":{"draws":85,"losses":107,"wins":54},"z-ai/glm-5.3":{"draws":12,"losses":63,"wins":5},"z-ai/glm-5.3-flash":{"draws":25,"losses":49,"wins":18},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":26,"wins":11},"claude-fable-5":{"draws":14,"losses":36,"wins":6},"claude-fable-5-1":{"draws":4,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":3},"claude-opus-4-5":{"draws":21,"losses":46,"wins":7},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":18,"losses":37,"wins":7},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":3},"deepseek/deepseek-v4-flash":{"draws":33,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":24,"losses":25,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":2},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":22,"losses":39,"wins":11},"google/gemini-3.5-flash-lite":{"draws":47,"losses":46,"wins":29},"google/gemini-3.6-flash":{"draws":40,"losses":63,"wins":9},"google/gemini-3.8-flash":{"draws":19,"losses":32,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":8},"gpt-5.4":{"draws":21,"losses":31,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":17,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":27,"losses":22,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":40,"wins":2},"gpt-5.6-terra":{"draws":24,"losses":32,"wins":8},"gpt-6-astra":{"draws":1,"losses":45,"wins":0},"gpt-6-luna":{"draws":12,"losses":19,"wins":5},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":20},"meituan/longcat-2.0":{"draws":18,"losses":20,"wins":16},"meta/muse-glimmer-30b":{"draws":21,"losses":20,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":37,"wins":5},"meta/muse-spark-1.3":{"draws":14,"losses":34,"wins":6},"meta/muse-wonder":{"draws":6,"losses":22,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":11,"wins":5},"mistralai/mistral-large-4-0":{"draws":7,"losses":9,"wins":6},"mistralai/mistral-medium-3-5":{"draws":16,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":28,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":9},"o3":{"draws":14,"losses":43,"wins":15},"openai/gpt-oss-120b":{"draws":22,"losses":22,"wins":16},"poolside/laguna-s-2.1":{"draws":23,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":28,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":24,"losses":8,"wins":10},"qwen/qwen3.8-max":{"draws":21,"losses":27,"wins":10},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"stealth/ox-alpha":{"draws":54,"losses":121,"wins":29},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":11},"tencent/hy3-preview":{"draws":7,"losses":12,"wins":1},"tencent/hy4-preview":{"draws":28,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":20,"wins":17},"thinkingmachines/inkling-small":{"draws":31,"losses":15,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":13,"losses":32,"wins":7},"x-ai/grok-4.6":{"draws":25,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":15,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":4},"z-ai/glm-5.2":{"draws":51,"losses":36,"wins":17},"z-ai/glm-5.3":{"draws":6,"losses":34,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":2},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":25,"wins":26},"claude-fable-5":{"draws":13,"losses":53,"wins":10},"claude-fable-5-1":{"draws":7,"losses":81,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":30,"wins":4},"claude-opus-4-5":{"draws":40,"losses":60,"wins":42},"claude-opus-4-8":{"draws":13,"losses":31,"wins":6},"claude-opus-5":{"draws":7,"losses":71,"wins":12},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":43,"losses":53,"wins":40},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":11},"deepseek/deepseek-v4-flash":{"draws":29,"losses":34,"wins":43},"deepseek/deepseek-v4-pro":{"draws":15,"losses":37,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":36,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":26,"wins":11},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":23,"losses":47,"wins":22},"google/gemini-3.5-flash-lite":{"draws":67,"losses":66,"wins":97},"google/gemini-3.6-flash":{"draws":52,"losses":113,"wins":59},"google/gemini-3.8-flash":{"draws":22,"losses":43,"wins":19},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":6},"gpt-4.1":{"draws":4,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":13,"losses":19,"wins":14},"gpt-5.4":{"draws":26,"losses":60,"wins":38},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":15},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":12,"losses":28,"wins":12},"gpt-5.6-luna":{"draws":32,"losses":50,"wins":50},"gpt-5.6-sol":{"draws":17,"losses":96,"wins":17},"gpt-5.6-terra":{"draws":23,"losses":33,"wins":26},"gpt-6-astra":{"draws":2,"losses":72,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":6,"wins":38},"inclusionai/ling-3.0-flash":{"draws":23,"losses":10,"wins":25},"meituan/longcat-2.0":{"draws":24,"losses":39,"wins":39},"meta/muse-glimmer-30b":{"draws":22,"losses":24,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":32,"wins":10},"meta/muse-spark-1.3":{"draws":17,"losses":35,"wins":16},"meta/muse-wonder":{"draws":9,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":18},"mistralai/mistral-large-4-0":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":18,"losses":6,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":50,"wins":31},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":23},"o3":{"draws":12,"losses":87,"wins":39},"openai/gpt-oss-120b":{"draws":22,"losses":12,"wins":42},"poolside/laguna-s-2.1":{"draws":25,"losses":16,"wins":51},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":18},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":44,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":23,"wins":10},"qwen/qwen3.8-flash":{"draws":17,"losses":25,"wins":16},"qwen/qwen3.8-max":{"draws":25,"losses":42,"wins":21},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":10},"stealth/ox-alpha":{"draws":66,"losses":151,"wins":67},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":15,"losses":46,"wins":23},"thinkingmachines/inkling":{"draws":38,"losses":16,"wins":40},"thinkingmachines/inkling-small":{"draws":25,"losses":28,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":26,"losses":64,"wins":16},"x-ai/grok-4.6":{"draws":18,"losses":55,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":19,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":42,"losses":47,"wins":49},"z-ai/glm-5.3":{"draws":12,"losses":38,"wins":14},"z-ai/glm-5.3-flash":{"draws":15,"losses":46,"wins":21},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":18,"wins":31},"claude-fable-5":{"draws":17,"losses":46,"wins":5},"claude-fable-5-1":{"draws":2,"losses":70,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":4},"claude-opus-4-5":{"draws":36,"losses":42,"wins":26},"claude-opus-4-8":{"draws":13,"losses":29,"wins":6},"claude-opus-5":{"draws":12,"losses":65,"wins":7},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":36,"losses":29,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":31,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":36,"losses":30,"wins":46},"deepseek/deepseek-v4-pro":{"draws":21,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"fireworks/ember-1":{"draws":20,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":31,"losses":40,"wins":23},"google/gemini-3.5-flash-lite":{"draws":57,"losses":42,"wins":63},"google/gemini-3.6-flash":{"draws":35,"losses":67,"wins":44},"google/gemini-3.8-flash":{"draws":21,"losses":46,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":19,"wins":11},"gpt-5.4":{"draws":25,"losses":41,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":18},"gpt-5.5":{"draws":16,"losses":20,"wins":8},"gpt-5.6-luna":{"draws":36,"losses":27,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":58,"wins":2},"gpt-5.6-terra":{"draws":20,"losses":35,"wins":19},"gpt-6-astra":{"draws":6,"losses":54,"wins":2},"gpt-6-luna":{"draws":12,"losses":20,"wins":14},"gpt-6-sol":{"draws":8,"losses":39,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":5,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":25},"meituan/longcat-2.0":{"draws":28,"losses":12,"wins":33},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":21},"meta/muse-spark-1.2":{"draws":19,"losses":31,"wins":12},"meta/muse-spark-1.3":{"draws":7,"losses":32,"wins":3},"meta/muse-wonder":{"draws":9,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":20},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":33,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":5,"wins":21},"o3":{"draws":16,"losses":51,"wins":29},"openai/gpt-oss-120b":{"draws":33,"losses":13,"wins":36},"poolside/laguna-s-2.1":{"draws":28,"losses":24,"wins":18},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":34,"wins":19},"qwen/qwen3.8-27b":{"draws":8,"losses":24,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":22,"wins":18},"qwen/qwen3.8-max":{"draws":38,"losses":22,"wins":24},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":75,"losses":139,"wins":56},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":28,"losses":44,"wins":10},"thinkingmachines/inkling":{"draws":23,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":44,"losses":17,"wins":33},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":14,"losses":46,"wins":18},"x-ai/grok-4.6":{"draws":23,"losses":38,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":33,"losses":16,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":13,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":44,"losses":45,"wins":43},"z-ai/glm-5.3":{"draws":17,"losses":43,"wins":6},"z-ai/glm-5.3-flash":{"draws":24,"losses":45,"wins":13},"z-ai/glm-5.3-flashx":{"draws":13,"losses":26,"wins":8}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":4,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":15,"losses":12,"wins":17},"claude-opus-4-5":{"draws":27,"losses":17,"wins":34},"claude-opus-4-8":{"draws":12,"losses":19,"wins":13},"claude-opus-5":{"draws":11,"losses":54,"wins":17},"claude-opus-5-5":{"draws":0,"losses":39,"wins":9},"claude-sonnet-5":{"draws":16,"losses":10,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":12},"fireworks/ember-1":{"draws":16,"losses":10,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":9,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":50},"google/gemini-3.6-flash":{"draws":24,"losses":25,"wins":31},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":14},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":21},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":18,"losses":12,"wins":14},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":8,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":17,"losses":14,"wins":15},"gpt-6-sol":{"draws":6,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":19},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":14},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":13},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":1,"wins":19},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":23},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":0,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":17},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":18},"stealth/ox-alpha":{"draws":43,"losses":58,"wins":55},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":28},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":14,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":7,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":24,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":11,"losses":21,"wins":16},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":14}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":26,"wins":8},"claude-fable-5":{"draws":10,"losses":23,"wins":5},"claude-fable-5-1":{"draws":1,"losses":38,"wins":1},"claude-haiku-5-5":{"draws":2,"losses":20,"wins":8},"claude-opus-4-5":{"draws":26,"losses":58,"wins":16},"claude-opus-4-8":{"draws":8,"losses":42,"wins":14},"claude-opus-5":{"draws":16,"losses":93,"wins":9},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":8,"losses":18,"wins":12},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":10,"wins":12},"deepseek/deepseek-v4-flash":{"draws":17,"losses":22,"wins":33},"deepseek/deepseek-v4-pro":{"draws":5,"losses":21,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":10},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":15},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":21,"wins":35},"google/gemini-3.6-flash":{"draws":13,"losses":52,"wins":19},"google/gemini-3.8-flash":{"draws":4,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":7},"gpt-4.1":{"draws":4,"losses":16,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":10,"losses":24,"wins":18},"gpt-5.4":{"draws":5,"losses":18,"wins":15},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":24},"gpt-5.4-nano":{"draws":19,"losses":20,"wins":35},"gpt-5.5":{"draws":15,"losses":36,"wins":15},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":12},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":20,"wins":12},"gpt-6-astra":{"draws":0,"losses":36,"wins":2},"gpt-6-luna":{"draws":7,"losses":18,"wins":9},"gpt-6-sol":{"draws":2,"losses":29,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":32,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":16,"losses":8,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":15,"wins":27},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":6,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":31,"wins":5},"meta/muse-wonder":{"draws":5,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":8},"mistralai/mistral-large-4-0":{"draws":4,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":5,"losses":7,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":32,"wins":6},"nex-agi/nex-n2-pro":{"draws":11,"losses":8,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":12,"wins":36},"o3":{"draws":7,"losses":35,"wins":18},"openai/gpt-oss-120b":{"draws":9,"losses":14,"wins":15},"poolside/laguna-s-2.1":{"draws":14,"losses":18,"wins":28},"qwen/qwen3.7-max":{"draws":20,"losses":21,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":11,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":24,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":10,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":66,"wins":32},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":20},"tencent/hy4-preview":{"draws":6,"losses":25,"wins":5},"thinkingmachines/inkling":{"draws":16,"losses":17,"wins":31},"thinkingmachines/inkling-small":{"draws":8,"losses":9,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":34,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":30,"losses":25,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":7},"z-ai/glm-5.2":{"draws":25,"losses":28,"wins":37},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":10},"claude-fable-5":{"draws":8,"losses":22,"wins":8},"claude-fable-5-1":{"draws":3,"losses":39,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":7},"claude-opus-4-5":{"draws":23,"losses":28,"wins":13},"claude-opus-4-8":{"draws":9,"losses":13,"wins":10},"claude-opus-5":{"draws":11,"losses":51,"wins":6},"claude-opus-5-5":{"draws":4,"losses":34,"wins":0},"claude-sonnet-5":{"draws":11,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":14,"losses":18,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":20},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":5},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":20,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":21,"losses":35,"wins":8},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":7},"gpt-4.1":{"draws":6,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":15,"losses":10,"wins":9},"gpt-5.4":{"draws":13,"losses":20,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":15},"gpt-5.5":{"draws":19,"losses":15,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":25,"wins":3},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":9},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":13,"losses":15,"wins":12},"gpt-6-sol":{"draws":6,"losses":27,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":33,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":8,"wins":13},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":5},"meta/muse-wonder":{"draws":7,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":4},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":16,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":9},"o3":{"draws":16,"losses":21,"wins":15},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":9},"poolside/laguna-s-2.1":{"draws":18,"losses":9,"wins":13},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":17,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":5},"stealth/ox-alpha":{"draws":41,"losses":60,"wins":27},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":17},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":19,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":24,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":11,"wins":7},"z-ai/glm-5.2":{"draws":38,"losses":17,"wins":21},"z-ai/glm-5.3":{"draws":8,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":13,"losses":18,"wins":7}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":28,"wins":15},"claude-fable-5":{"draws":12,"losses":38,"wins":4},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":25,"wins":2},"claude-opus-4-5":{"draws":26,"losses":57,"wins":3},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":26,"losses":46,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":44,"losses":37,"wins":11},"deepseek/deepseek-v4-pro":{"draws":23,"losses":41,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":36,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":23,"wins":3},"fireworks/ember-1":{"draws":13,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":14,"losses":26,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":12},"google/gemini-3.5-flash":{"draws":21,"losses":43,"wins":10},"google/gemini-3.5-flash-lite":{"draws":46,"losses":69,"wins":27},"google/gemini-3.6-flash":{"draws":48,"losses":62,"wins":10},"google/gemini-3.8-flash":{"draws":15,"losses":40,"wins":1},"google/gemma-4-31b-it":{"draws":11,"losses":11,"wins":2},"gpt-4.1":{"draws":8,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":13,"losses":17,"wins":8},"gpt-5.4":{"draws":22,"losses":26,"wins":12},"gpt-5.4-mini":{"draws":14,"losses":11,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":27,"wins":5},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":30,"losses":34,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":45,"wins":4},"gpt-5.6-terra":{"draws":22,"losses":42,"wins":6},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":2},"gpt-6-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":21,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":14},"meituan/longcat-2.0":{"draws":24,"losses":28,"wins":12},"meta/muse-glimmer-30b":{"draws":34,"losses":28,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":41,"wins":5},"meta/muse-spark-1.3":{"draws":12,"losses":45,"wins":1},"meta/muse-wonder":{"draws":7,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":44,"wins":0},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":15,"wins":4},"o3":{"draws":17,"losses":54,"wins":5},"openai/gpt-oss-120b":{"draws":33,"losses":31,"wins":6},"poolside/laguna-s-2.1":{"draws":31,"losses":26,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":51,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":23,"wins":1},"qwen/qwen3.8-flash":{"draws":18,"losses":29,"wins":5},"qwen/qwen3.8-max":{"draws":21,"losses":45,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":2},"stealth/ox-alpha":{"draws":63,"losses":131,"wins":22},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":19,"losses":45,"wins":4},"thinkingmachines/inkling":{"draws":22,"losses":33,"wins":9},"thinkingmachines/inkling-small":{"draws":41,"losses":25,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":14,"losses":40,"wins":6},"x-ai/grok-4.6":{"draws":22,"losses":34,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":29,"losses":26,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":21,"wins":2},"z-ai/glm-5.2":{"draws":54,"losses":55,"wins":9},"z-ai/glm-5.3":{"draws":12,"losses":42,"wins":2},"z-ai/glm-5.3-flash":{"draws":26,"losses":31,"wins":9},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":16,"wins":41},"claude-fable-5":{"draws":9,"losses":59,"wins":22},"claude-fable-5-1":{"draws":4,"losses":92,"wins":4},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":11},"claude-opus-4-5":{"draws":58,"losses":37,"wins":71},"claude-opus-4-8":{"draws":18,"losses":19,"wins":23},"claude-opus-5":{"draws":18,"losses":78,"wins":28},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":42,"losses":29,"wins":67},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":28,"losses":26,"wins":54},"deepseek/deepseek-v4-pro":{"draws":16,"losses":27,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":32,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":31,"losses":40,"wins":29},"google/gemini-3.5-flash-lite":{"draws":89,"losses":55,"wins":132},"google/gemini-3.6-flash":{"draws":80,"losses":106,"wins":102},"google/gemini-3.8-flash":{"draws":16,"losses":47,"wins":21},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":11},"gpt-4.1":{"draws":5,"losses":3,"wins":14},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":12,"wins":18},"gpt-5.4":{"draws":15,"losses":76,"wins":45},"gpt-5.4-mini":{"draws":21,"losses":13,"wins":20},"gpt-5.4-nano":{"draws":18,"losses":10,"wins":46},"gpt-5.5":{"draws":15,"losses":18,"wins":27},"gpt-5.6-luna":{"draws":36,"losses":27,"wins":69},"gpt-5.6-sol":{"draws":25,"losses":81,"wins":30},"gpt-5.6-terra":{"draws":23,"losses":29,"wins":36},"gpt-6-astra":{"draws":9,"losses":71,"wins":10},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":7,"wins":32},"inclusionai/ling-3.0-flash":{"draws":38,"losses":7,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":40,"losses":27,"wins":63},"meta/muse-glimmer-30b":{"draws":19,"losses":9,"wins":42},"meta/muse-spark-1.2":{"draws":23,"losses":35,"wins":40},"meta/muse-spark-1.3":{"draws":14,"losses":39,"wins":23},"meta/muse-wonder":{"draws":8,"losses":29,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":29},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":9},"mistralai/mistral-medium-3-5":{"draws":11,"losses":5,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":31,"losses":23,"wins":22},"nex-agi/nex-n2-pro":{"draws":8,"losses":9,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":23},"o3":{"draws":21,"losses":71,"wins":62},"openai/gpt-oss-120b":{"draws":19,"losses":14,"wins":39},"poolside/laguna-s-2.1":{"draws":47,"losses":14,"wins":61},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":23},"qwen/qwen3.7-plus":{"draws":16,"losses":8,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":30,"wins":40},"qwen/qwen3.8-27b":{"draws":12,"losses":13,"wins":19},"qwen/qwen3.8-flash":{"draws":17,"losses":28,"wins":15},"qwen/qwen3.8-max":{"draws":18,"losses":36,"wins":39},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":10},"stealth/ox-alpha":{"draws":75,"losses":115,"wins":94},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":23,"losses":33,"wins":30},"thinkingmachines/inkling":{"draws":40,"losses":23,"wins":53},"thinkingmachines/inkling-small":{"draws":27,"losses":20,"wins":46},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":47,"losses":51,"wins":54},"x-ai/grok-4.6":{"draws":12,"losses":49,"wins":27},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":37,"losses":16,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":17,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":55,"losses":27,"wins":54},"z-ai/glm-5.3":{"draws":19,"losses":32,"wins":17},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":25,"wins":10}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":8},"claude-fable-5":{"draws":12,"losses":29,"wins":1},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":7},"claude-opus-4-5":{"draws":33,"losses":47,"wins":22},"claude-opus-4-8":{"draws":33,"losses":37,"wins":10},"claude-opus-5":{"draws":3,"losses":88,"wins":9},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":20,"losses":17,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":17},"deepseek/deepseek-v4-flash":{"draws":34,"losses":37,"wins":19},"deepseek/deepseek-v4-pro":{"draws":19,"losses":15,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":20,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":4},"fireworks/ember-1":{"draws":17,"losses":18,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":6},"google/gemini-3.1-flash-lite":{"draws":18,"losses":9,"wins":21},"google/gemini-3.5-flash":{"draws":23,"losses":20,"wins":13},"google/gemini-3.5-flash-lite":{"draws":47,"losses":21,"wins":26},"google/gemini-3.6-flash":{"draws":38,"losses":47,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":27,"losses":13,"wins":10},"gpt-5.4":{"draws":16,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":32,"losses":15,"wins":11},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":24},"gpt-5.5":{"draws":31,"losses":27,"wins":8},"gpt-5.6-luna":{"draws":16,"losses":21,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":20,"losses":17,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":21,"wins":6},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":43,"losses":11,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":16,"wins":19},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":27,"wins":6},"meta/muse-wonder":{"draws":12,"losses":23,"wins":3},"minimax/minimax-m3":{"draws":23,"losses":16,"wins":11},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":2},"mistralai/mistral-medium-3-5":{"draws":16,"losses":12,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":27,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":20,"wins":15},"o3":{"draws":14,"losses":35,"wins":19},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":12},"poolside/laguna-s-2.1":{"draws":29,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":21,"losses":22,"wins":7},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":20,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":23,"wins":2},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":82,"wins":19},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":33,"losses":7,"wins":14},"tencent/hy4-preview":{"draws":17,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":28,"losses":20,"wins":18},"thinkingmachines/inkling-small":{"draws":20,"losses":12,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":19,"losses":34,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":57,"losses":33,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":62,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":2},"z-ai/glm-5.3-flash":{"draws":16,"losses":23,"wins":3},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":4}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":14},"claude-fable-5":{"draws":8,"losses":28,"wins":8},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":17,"wins":12},"claude-opus-4-5":{"draws":25,"losses":54,"wins":15},"claude-opus-4-8":{"draws":8,"losses":35,"wins":19},"claude-opus-5":{"draws":23,"losses":90,"wins":5},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":13,"losses":20,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":14,"wins":7},"deepseek/deepseek-v4-flash":{"draws":23,"losses":45,"wins":20},"deepseek/deepseek-v4-pro":{"draws":17,"losses":15,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":6},"fireworks/ember-1":{"draws":12,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"google/gemini-3.1-flash-lite":{"draws":14,"losses":23,"wins":19},"google/gemini-3.5-flash":{"draws":15,"losses":30,"wins":13},"google/gemini-3.5-flash-lite":{"draws":32,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":21,"losses":48,"wins":17},"google/gemini-3.8-flash":{"draws":11,"losses":31,"wins":6},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":8},"gpt-4.1":{"draws":8,"losses":16,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":21,"losses":22,"wins":15},"gpt-5.4":{"draws":17,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":22,"losses":14,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":31,"wins":21},"gpt-5.5":{"draws":36,"losses":29,"wins":5},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":23,"wins":7},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":14,"wins":9},"inclusionai/ling-3.0-flash":{"draws":23,"losses":12,"wins":15},"meituan/longcat-2.0":{"draws":24,"losses":29,"wins":13},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":33,"wins":4},"meta/muse-wonder":{"draws":8,"losses":29,"wins":3},"minimax/minimax-m3":{"draws":10,"losses":23,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":25,"wins":9},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":5,"wins":15},"o3":{"draws":21,"losses":31,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":12},"poolside/laguna-s-2.1":{"draws":22,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":18,"losses":21,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":16,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":25,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":86,"wins":28},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":10},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":13},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":36,"wins":3},"x-ai/grok-4.6":{"draws":15,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":16,"losses":12,"wins":4},"xiaomi/mimo-v2.5":{"draws":38,"losses":40,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":3},"z-ai/glm-5.2":{"draws":38,"losses":37,"wins":35},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":7}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":14},"claude-fable-5":{"draws":8,"losses":27,"wins":7},"claude-fable-5-1":{"draws":2,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":19,"wins":9},"claude-opus-4-5":{"draws":15,"losses":31,"wins":22},"claude-opus-4-8":{"draws":14,"losses":18,"wins":8},"claude-opus-5":{"draws":13,"losses":59,"wins":4},"claude-opus-5-5":{"draws":7,"losses":39,"wins":0},"claude-sonnet-5":{"draws":13,"losses":19,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":13,"wins":33},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":22,"wins":13},"fireworks/ember-1":{"draws":16,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":9,"losses":17,"wins":16},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":16,"losses":25,"wins":15},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":15,"losses":36,"wins":23},"google/gemini-3.8-flash":{"draws":13,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":11,"wins":13},"gpt-5.4":{"draws":10,"losses":21,"wins":11},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":15},"gpt-5.5":{"draws":10,"losses":19,"wins":11},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":33,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":11,"wins":15},"gpt-6-astra":{"draws":2,"losses":42,"wins":0},"gpt-6-luna":{"draws":11,"losses":20,"wins":13},"gpt-6-sol":{"draws":2,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":8,"wins":25},"meta/muse-glimmer-30b":{"draws":9,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":6},"meta/muse-spark-1.3":{"draws":10,"losses":29,"wins":7},"meta/muse-wonder":{"draws":7,"losses":36,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":17,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":16},"o3":{"draws":7,"losses":19,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":24,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":13,"losses":23,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"stealth/ox-alpha":{"draws":41,"losses":75,"wins":32},"stealth/space-bunny-alpha":{"draws":11,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":18,"wins":14},"thinkingmachines/inkling":{"draws":14,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":23,"wins":11},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":20,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":25,"wins":1},"z-ai/glm-5.2":{"draws":30,"losses":25,"wins":33},"z-ai/glm-5.3":{"draws":7,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":25,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":28,"wins":7}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":26,"wins":16},"claude-fable-5":{"draws":10,"losses":37,"wins":5},"claude-fable-5-1":{"draws":0,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":21,"wins":5},"claude-opus-4-5":{"draws":26,"losses":49,"wins":7},"claude-opus-4-8":{"draws":9,"losses":22,"wins":1},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":24,"losses":36,"wins":8},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":3},"deepseek/deepseek-v4-flash":{"draws":35,"losses":24,"wins":29},"deepseek/deepseek-v4-pro":{"draws":18,"losses":30,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":14,"losses":20,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":21,"losses":38,"wins":13},"google/gemini-3.5-flash-lite":{"draws":42,"losses":41,"wins":35},"google/gemini-3.6-flash":{"draws":37,"losses":52,"wins":13},"google/gemini-3.8-flash":{"draws":18,"losses":34,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":9},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":16,"wins":7},"gpt-5.4":{"draws":18,"losses":29,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":15},"gpt-5.5":{"draws":13,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":30,"losses":26,"wins":14},"gpt-5.6-sol":{"draws":4,"losses":46,"wins":0},"gpt-5.6-terra":{"draws":19,"losses":39,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":10,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":14,"wins":14},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"meituan/longcat-2.0":{"draws":20,"losses":17,"wins":11},"meta/muse-glimmer-30b":{"draws":30,"losses":16,"wins":22},"meta/muse-spark-1.2":{"draws":13,"losses":38,"wins":1},"meta/muse-spark-1.3":{"draws":16,"losses":26,"wins":8},"meta/muse-wonder":{"draws":4,"losses":22,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":16,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":28,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":9},"o3":{"draws":11,"losses":49,"wins":12},"openai/gpt-oss-120b":{"draws":17,"losses":15,"wins":12},"poolside/laguna-s-2.1":{"draws":26,"losses":24,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":28,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":20,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":16,"wins":8},"qwen/qwen3.8-max":{"draws":23,"losses":27,"wins":6},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":4},"stealth/ox-alpha":{"draws":59,"losses":122,"wins":18},"stealth/space-bunny-alpha":{"draws":6,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":13,"losses":24,"wins":17},"thinkingmachines/inkling-small":{"draws":28,"losses":12,"wins":32},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":26,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":33,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":18,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":47,"losses":37,"wins":20},"z-ai/glm-5.3":{"draws":16,"losses":30,"wins":0},"z-ai/glm-5.3-flash":{"draws":22,"losses":27,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":22,"wins":27},"claude-fable-5":{"draws":12,"losses":49,"wins":17},"claude-fable-5-1":{"draws":2,"losses":85,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":28,"wins":23},"claude-opus-4-5":{"draws":60,"losses":82,"wins":36},"claude-opus-4-8":{"draws":27,"losses":66,"wins":19},"claude-opus-5":{"draws":16,"losses":193,"wins":17},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":24,"losses":42,"wins":20},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":15},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":15},"deepseek/deepseek-v4-flash":{"draws":55,"losses":41,"wins":62},"deepseek/deepseek-v4-pro":{"draws":18,"losses":32,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":34,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":14},"fireworks/ember-1":{"draws":23,"losses":36,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"google/gemini-3.1-flash-lite":{"draws":18,"losses":22,"wins":40},"google/gemini-3.5-flash":{"draws":24,"losses":54,"wins":26},"google/gemini-3.5-flash-lite":{"draws":49,"losses":55,"wins":88},"google/gemini-3.6-flash":{"draws":56,"losses":97,"wins":59},"google/gemini-3.8-flash":{"draws":15,"losses":54,"wins":15},"google/gemma-4-31b-it":{"draws":9,"losses":10,"wins":17},"gpt-4.1":{"draws":11,"losses":24,"wins":13},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":33,"losses":32,"wins":47},"gpt-5.4":{"draws":29,"losses":46,"wins":11},"gpt-5.4-mini":{"draws":37,"losses":25,"wins":24},"gpt-5.4-nano":{"draws":42,"losses":45,"wins":57},"gpt-5.5":{"draws":49,"losses":47,"wins":28},"gpt-5.6-luna":{"draws":29,"losses":27,"wins":32},"gpt-5.6-sol":{"draws":13,"losses":67,"wins":8},"gpt-5.6-terra":{"draws":28,"losses":36,"wins":14},"gpt-6-astra":{"draws":5,"losses":73,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":27},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":14,"wins":20},"inclusionai/ling-3.0-flash":{"draws":48,"losses":18,"wins":46},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":56,"losses":34,"wins":52},"meta/muse-glimmer-30b":{"draws":27,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":15,"losses":47,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":45,"wins":22},"meta/muse-wonder":{"draws":10,"losses":57,"wins":5},"minimax/minimax-m3":{"draws":24,"losses":26,"wins":32},"mistralai/mistral-large-4-0":{"draws":11,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":13,"losses":12,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":23},"moonshotai/kimi-k3":{"draws":29,"losses":38,"wins":29},"nex-agi/nex-n2-pro":{"draws":26,"losses":9,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":24,"wins":39},"o3":{"draws":18,"losses":63,"wins":37},"openai/gpt-oss-120b":{"draws":23,"losses":13,"wins":38},"poolside/laguna-s-2.1":{"draws":47,"losses":32,"wins":41},"qwen/qwen3.7-max":{"draws":25,"losses":28,"wins":21},"qwen/qwen3.7-plus":{"draws":21,"losses":9,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":47,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":25,"wins":16},"qwen/qwen3.8-flash":{"draws":20,"losses":21,"wins":17},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":25},"qwen/qwen3.8-max-0902":{"draws":18,"losses":34,"wins":18},"stealth/ox-alpha":{"draws":67,"losses":152,"wins":70},"stealth/space-bunny-alpha":{"draws":13,"losses":22,"wins":21},"stepfun/step-3.7-flash":{"draws":13,"losses":20,"wins":25},"tencent/hy3-preview":{"draws":18,"losses":26,"wins":24},"tencent/hy4-preview":{"draws":25,"losses":43,"wins":18},"thinkingmachines/inkling":{"draws":33,"losses":37,"wins":66},"thinkingmachines/inkling-small":{"draws":30,"losses":10,"wins":40},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":27,"losses":88,"wins":29},"x-ai/grok-4.6":{"draws":23,"losses":44,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":12,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":54,"losses":53,"wins":81},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":32,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":31,"wins":13},"z-ai/glm-5.2":{"draws":87,"losses":73,"wins":66},"z-ai/glm-5.3":{"draws":9,"losses":51,"wins":10},"z-ai/glm-5.3-flash":{"draws":21,"losses":42,"wins":15},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":20,"wins":11},"claude-fable-5":{"draws":8,"losses":30,"wins":6},"claude-fable-5-1":{"draws":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":8},"claude-opus-4-5":{"draws":33,"losses":57,"wins":20},"claude-opus-4-8":{"draws":21,"losses":33,"wins":16},"claude-opus-5":{"draws":18,"losses":102,"wins":4},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":16,"losses":23,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4-flash":{"draws":36,"losses":21,"wins":35},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":13,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":13},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":32},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":18,"losses":26,"wins":34},"google/gemini-3.6-flash":{"draws":24,"losses":54,"wins":18},"google/gemini-3.8-flash":{"draws":16,"losses":19,"wins":13},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":8,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":24,"losses":22,"wins":12},"gpt-5.4":{"draws":11,"losses":20,"wins":11},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":25},"gpt-5.4-nano":{"draws":26,"losses":27,"wins":31},"gpt-5.5":{"draws":27,"losses":23,"wins":14},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":24,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":9,"losses":16,"wins":15},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":11,"wins":13},"inclusionai/ling-3.0-flash":{"draws":28,"losses":7,"wins":23},"meituan/longcat-2.0":{"draws":24,"losses":15,"wins":27},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":27,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":9},"meta/muse-wonder":{"draws":5,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":22,"losses":5,"wins":23},"mistralai/mistral-large-4-0":{"draws":10,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":12,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":14,"wins":25},"o3":{"draws":13,"losses":41,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":24,"losses":24,"wins":22},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":7},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.8-max":{"draws":22,"losses":17,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":9},"stealth/ox-alpha":{"draws":33,"losses":87,"wins":30},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":10,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":25,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":28,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.5":{"draws":47,"losses":28,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":11,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":42,"losses":39,"wins":33},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":7},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":15,"wins":7},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":5,"losses":35,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":52,"losses":39,"wins":11},"claude-opus-4-8":{"draws":16,"losses":39,"wins":9},"claude-opus-5":{"draws":8,"losses":58,"wins":14},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":11,"losses":25,"wins":6},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":11,"wins":7},"deepseek/deepseek-v4-flash":{"draws":24,"losses":34,"wins":24},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":2},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":19,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":24,"losses":37,"wins":13},"google/gemini-3.6-flash":{"draws":34,"losses":48,"wins":6},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":6},"gpt-4.1":{"draws":8,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":20,"wins":2},"gpt-5.4":{"draws":6,"losses":27,"wins":1},"gpt-5.4-mini":{"draws":16,"losses":20,"wins":12},"gpt-5.4-nano":{"draws":18,"losses":40,"wins":18},"gpt-5.5":{"draws":22,"losses":34,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":17,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":28,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":23,"wins":2},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":14,"losses":20,"wins":2},"gpt-6-sol":{"draws":7,"losses":28,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":23,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":29,"wins":7},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":32,"wins":5},"meta/muse-wonder":{"draws":4,"losses":30,"wins":2},"minimax/minimax-m3":{"draws":13,"losses":21,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":9,"losses":9,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":7},"nex-agi/nex-n2-pro":{"draws":12,"losses":17,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":24,"wins":15},"o3":{"draws":8,"losses":43,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":19,"wins":4},"poolside/laguna-s-2.1":{"draws":14,"losses":29,"wins":5},"qwen/qwen3.7-max":{"draws":16,"losses":22,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":12,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":21,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":2},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":2},"stealth/ox-alpha":{"draws":25,"losses":76,"wins":7},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"wins":3},"stepfun/step-3.7-flash":{"draws":5,"losses":17,"wins":10},"tencent/hy3-preview":{"draws":16,"losses":23,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":35,"wins":17},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":28,"wins":0},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":46,"losses":60,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":30,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":58,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":27,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":23,"wins":31},"claude-fable-5":{"draws":21,"losses":48,"wins":15},"claude-fable-5-1":{"draws":4,"losses":88,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":12},"claude-opus-4-5":{"draws":34,"losses":34,"wins":36},"claude-opus-4-8":{"draws":17,"losses":21,"wins":14},"claude-opus-5":{"draws":7,"losses":67,"wins":14},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":30,"losses":18,"wins":40},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":35,"losses":18,"wins":57},"deepseek/deepseek-v4-pro":{"draws":24,"losses":23,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":28,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"wins":16},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":28,"losses":34,"wins":36},"google/gemini-3.5-flash-lite":{"draws":54,"losses":32,"wins":64},"google/gemini-3.6-flash":{"draws":34,"losses":71,"wins":45},"google/gemini-3.8-flash":{"draws":17,"losses":45,"wins":24},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":14},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":21},"gpt-5.4":{"draws":18,"losses":28,"wins":32},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":27},"gpt-5.5":{"draws":12,"losses":20,"wins":14},"gpt-5.6-luna":{"draws":34,"losses":19,"wins":31},"gpt-5.6-sol":{"draws":16,"losses":54,"wins":12},"gpt-5.6-terra":{"draws":24,"losses":19,"wins":39},"gpt-6-astra":{"draws":7,"losses":70,"wins":1},"gpt-6-luna":{"draws":10,"losses":22,"wins":14},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":6,"wins":28},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":43},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":26},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":37},"meta/muse-spark-1.3":{"draws":20,"losses":27,"wins":25},"meta/muse-wonder":{"draws":10,"losses":24,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":17,"losses":27,"wins":30},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":24},"o3":{"draws":16,"losses":27,"wins":49},"openai/gpt-oss-120b":{"draws":27,"losses":8,"wins":35},"poolside/laguna-s-2.1":{"draws":25,"losses":11,"wins":32},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":22,"wins":13},"qwen/qwen3.8-27b":{"draws":14,"losses":14,"wins":14},"qwen/qwen3.8-flash":{"draws":12,"losses":22,"wins":26},"qwen/qwen3.8-max":{"draws":22,"losses":42,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":64,"losses":115,"wins":92},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":25,"losses":37,"wins":18},"thinkingmachines/inkling":{"draws":20,"losses":14,"wins":36},"thinkingmachines/inkling-small":{"draws":25,"losses":11,"wins":56},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":31,"wins":25},"x-ai/grok-4.6":{"draws":20,"losses":37,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":43,"losses":38,"wins":55},"z-ai/glm-5.3":{"draws":14,"losses":43,"wins":9},"z-ai/glm-5.3-flash":{"draws":22,"losses":31,"wins":27},"z-ai/glm-5.3-flashx":{"draws":12,"losses":25,"wins":11}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":8},"claude-fable-5":{"draws":5,"losses":17,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":19,"wins":2},"claude-opus-4-8":{"draws":5,"losses":12,"wins":3},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":6,"losses":13,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":2},"fireworks/ember-1":{"draws":12,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":20,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":12,"losses":22,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":17,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":5},"gpt-5.4":{"draws":7,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":4},"gpt-5.5":{"draws":8,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":9,"losses":11,"wins":4},"gpt-6-sol":{"draws":7,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":8},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":15,"wins":1},"meta/muse-wonder":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":3},"o3":{"draws":4,"losses":19,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":18,"losses":53,"wins":15},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":11,"wins":3},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":15,"losses":14,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":20,"losses":22,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":28,"wins":25},"claude-fable-5":{"draws":17,"losses":53,"wins":2},"claude-fable-5-1":{"draws":7,"losses":67,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":31,"wins":2},"claude-opus-4-5":{"draws":40,"losses":53,"wins":11},"claude-opus-4-8":{"draws":13,"losses":30,"wins":3},"claude-opus-5":{"draws":14,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":34,"losses":42,"wins":12},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":37,"losses":38,"wins":35},"deepseek/deepseek-v4-pro":{"draws":28,"losses":37,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":34,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":4},"fireworks/ember-1":{"draws":17,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"google/gemini-3.1-flash-lite":{"draws":14,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":28,"losses":56,"wins":12},"google/gemini-3.5-flash-lite":{"draws":60,"losses":41,"wins":55},"google/gemini-3.6-flash":{"draws":65,"losses":69,"wins":12},"google/gemini-3.8-flash":{"draws":17,"losses":60,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":24,"wins":9},"gpt-5.4":{"draws":22,"losses":35,"wins":15},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":21,"wins":19},"gpt-5.5":{"draws":21,"losses":22,"wins":5},"gpt-5.6-luna":{"draws":32,"losses":39,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":53,"wins":11},"gpt-5.6-terra":{"draws":19,"losses":37,"wins":16},"gpt-6-astra":{"draws":9,"losses":59,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"wins":9},"gpt-6-sol":{"draws":2,"losses":41,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":12,"wins":24},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":20,"wins":25},"meta/muse-glimmer-30b":{"draws":42,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":21,"losses":35,"wins":12},"meta/muse-spark-1.3":{"draws":17,"losses":45,"wins":10},"meta/muse-wonder":{"draws":11,"losses":33,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":16,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":29,"losses":40,"wins":7},"nex-agi/nex-n2-pro":{"draws":18,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":14},"o3":{"draws":25,"losses":49,"wins":20},"openai/gpt-oss-120b":{"draws":28,"losses":28,"wins":24},"poolside/laguna-s-2.1":{"draws":29,"losses":24,"wins":17},"qwen/qwen3.7-max":{"draws":16,"losses":22,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":16,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":13},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":0},"qwen/qwen3.8-max":{"draws":34,"losses":32,"wins":12},"qwen/qwen3.8-max-0902":{"draws":15,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":75,"losses":139,"wins":48},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":14},"tencent/hy3-preview":{"draws":17,"losses":11,"wins":6},"tencent/hy4-preview":{"draws":19,"losses":49,"wins":10},"thinkingmachines/inkling":{"draws":24,"losses":19,"wins":29},"thinkingmachines/inkling-small":{"draws":42,"losses":23,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":13},"x-ai/grok-4.6":{"draws":30,"losses":40,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":12,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":31,"losses":26,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":53,"losses":56,"wins":23},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":5},"z-ai/glm-5.3-flash":{"draws":34,"losses":34,"wins":8},"z-ai/glm-5.3-flashx":{"draws":19,"losses":26,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":27,"wins":21},"claude-fable-5":{"draws":17,"losses":27,"wins":30},"claude-fable-5-1":{"draws":2,"losses":66,"wins":6},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":15},"claude-opus-4-5":{"draws":35,"losses":38,"wins":31},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":15,"losses":61,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":36,"losses":32,"wins":23},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":53,"losses":17,"wins":38},"deepseek/deepseek-v4-pro":{"draws":25,"losses":23,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":24,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":35,"losses":21,"wins":30},"google/gemini-3.5-flash-lite":{"draws":62,"losses":42,"wins":45},"google/gemini-3.6-flash":{"draws":46,"losses":49,"wins":49},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":33},"google/gemma-4-31b-it":{"draws":13,"losses":4,"wins":9},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":28,"losses":24,"wins":30},"gpt-5.4-mini":{"draws":18,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":38,"losses":20,"wins":33},"gpt-5.6-sol":{"draws":16,"losses":44,"wins":19},"gpt-5.6-terra":{"draws":34,"losses":20,"wins":30},"gpt-6-astra":{"draws":2,"losses":62,"wins":2},"gpt-6-luna":{"draws":12,"losses":19,"wins":15},"gpt-6-sol":{"draws":5,"losses":29,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":25},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":37,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":26,"losses":16,"wins":34},"meta/muse-spark-1.2":{"draws":18,"losses":23,"wins":27},"meta/muse-spark-1.3":{"draws":17,"losses":27,"wins":20},"meta/muse-wonder":{"draws":9,"losses":24,"wins":11},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":17,"losses":10,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":18,"losses":27,"wins":23},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":17},"o3":{"draws":23,"losses":33,"wins":40},"openai/gpt-oss-120b":{"draws":34,"losses":7,"wins":31},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":32,"wins":22},"qwen/qwen3.8-27b":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-flash":{"draws":18,"losses":15,"wins":17},"qwen/qwen3.8-max":{"draws":28,"losses":40,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":14},"stealth/ox-alpha":{"draws":83,"losses":102,"wins":77},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":35,"wins":22},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":27},"thinkingmachines/inkling-small":{"draws":53,"losses":36,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":26,"losses":31,"wins":25},"x-ai/grok-4.6":{"draws":24,"losses":39,"wins":19},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":51,"losses":30,"wins":51},"z-ai/glm-5.3":{"draws":17,"losses":32,"wins":17},"z-ai/glm-5.3-flash":{"draws":19,"losses":32,"wins":25},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":5,"wins":19},"claude-fable-5":{"draws":12,"losses":29,"wins":7},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":29,"losses":26,"wins":23},"claude-opus-4-8":{"draws":17,"losses":13,"wins":14},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":14,"wins":17},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":36},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":18,"losses":13,"wins":17},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":23,"losses":13,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":10,"wins":40},"google/gemini-3.6-flash":{"draws":33,"losses":28,"wins":23},"google/gemini-3.8-flash":{"draws":16,"losses":22,"wins":10},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":11,"wins":16},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":22,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":12},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":18,"losses":14,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":15,"losses":8,"wins":29},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":12},"meta/muse-wonder":{"draws":11,"losses":25,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":9,"wins":19},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":2,"wins":16},"o3":{"draws":16,"losses":22,"wins":28},"openai/gpt-oss-120b":{"draws":18,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":6,"losses":15,"wins":9},"stealth/ox-alpha":{"draws":44,"losses":59,"wins":53},"stealth/space-bunny-alpha":{"draws":13,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":17},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":18,"losses":6,"wins":30},"thinkingmachines/inkling-small":{"draws":21,"losses":2,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":33,"losses":9,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":16,"wins":36},"z-ai/glm-5.3":{"draws":16,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":101,"losses":62,"wins":119},"claude-fable-5":{"draws":69,"losses":171,"wins":42},"claude-fable-5-1":{"draws":15,"losses":292,"wins":3},"claude-haiku-5-5":{"draws":48,"losses":71,"wins":33},"claude-opus-4-5":{"draws":142,"losses":124,"wins":98},"claude-opus-4-8":{"draws":42,"losses":74,"wins":36},"claude-opus-5":{"draws":43,"losses":243,"wins":26},"claude-opus-5-5":{"draws":17,"losses":158,"wins":1},"claude-sonnet-5":{"draws":104,"losses":100,"wins":98},"claude-sonnet-5-5":{"draws":37,"losses":90,"wins":41},"cohere/north-mini-code":{"draws":19,"losses":10,"wins":33},"deepseek/deepseek-v4-flash":{"draws":167,"losses":91,"wins":120},"deepseek/deepseek-v4-pro":{"draws":121,"losses":92,"wins":77},"deepseek/deepseek-v4-pro-0813":{"draws":106,"losses":113,"wins":65},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":77,"wins":39},"fireworks/ember-1":{"draws":62,"losses":75,"wins":31},"gemini-3.1-pro-preview":{"draws":55,"losses":59,"wins":54},"google/gemini-3.1-flash-lite":{"draws":28,"losses":9,"wins":61},"google/gemini-3.5-flash":{"draws":99,"losses":152,"wins":79},"google/gemini-3.5-flash-lite":{"draws":196,"losses":149,"wins":195},"google/gemini-3.6-flash":{"draws":143,"losses":225,"wins":142},"google/gemini-3.8-flash":{"draws":90,"losses":152,"wins":48},"google/gemma-4-31b-it":{"draws":29,"losses":15,"wins":40},"gpt-4.1":{"draws":27,"losses":18,"wins":15},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":61,"losses":53,"wins":44},"gpt-5.4":{"draws":124,"losses":124,"wins":42},"gpt-5.4-mini":{"draws":49,"losses":34,"wins":33},"gpt-5.4-nano":{"draws":48,"losses":47,"wins":65},"gpt-5.5":{"draws":65,"losses":61,"wins":36},"gpt-5.6-luna":{"draws":141,"losses":89,"wins":88},"gpt-5.6-sol":{"draws":56,"losses":178,"wins":42},"gpt-5.6-terra":{"draws":126,"losses":86,"wins":68},"gpt-6-astra":{"draws":23,"losses":240,"wins":1},"gpt-6-luna":{"draws":50,"losses":69,"wins":45},"gpt-6-sol":{"draws":20,"losses":133,"wins":15},"gpt-6.1-sol":{"draws":11,"losses":151,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":91,"losses":20,"wins":89},"inclusionai/ling-3.0-flash":{"draws":71,"losses":20,"wins":57},"meituan/longcat-2.0":{"draws":94,"losses":37,"wins":111},"meta/muse-glimmer-30b":{"draws":124,"losses":52,"wins":108},"meta/muse-spark-1.2":{"draws":82,"losses":82,"wins":74},"meta/muse-spark-1.3":{"draws":67,"losses":133,"wins":50},"meta/muse-wonder":{"draws":43,"losses":96,"wins":23},"minimax/minimax-m3":{"draws":33,"losses":18,"wins":43},"mistralai/mistral-large-4-0":{"draws":44,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":81,"losses":27,"wins":82},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":12},"moonshotai/kimi-k3":{"draws":83,"losses":87,"wins":74},"nex-agi/nex-n2-pro":{"draws":35,"losses":12,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":24,"wins":55},"o3":{"draws":73,"losses":141,"wins":92},"openai/gpt-oss-120b":{"draws":125,"losses":48,"wins":102},"poolside/laguna-s-2.1":{"draws":114,"losses":55,"wins":83},"qwen/qwen3.7-max":{"draws":40,"losses":27,"wins":33},"qwen/qwen3.7-plus":{"draws":26,"losses":13,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":102,"losses":109,"wins":73},"qwen/qwen3.8-27b":{"draws":47,"losses":60,"wins":41},"qwen/qwen3.8-flash":{"draws":87,"losses":67,"wins":36},"qwen/qwen3.8-max":{"draws":100,"losses":128,"wins":68},"qwen/qwen3.8-max-0902":{"draws":53,"losses":71,"wins":40},"stealth/ox-alpha":{"draws":291,"losses":535,"wins":299},"stealth/space-bunny-alpha":{"draws":55,"losses":37,"wins":38},"stepfun/step-3.7-flash":{"draws":37,"losses":23,"wins":60},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":23,"wins":29},"tencent/hy4-preview":{"draws":101,"losses":130,"wins":55},"thinkingmachines/inkling":{"draws":104,"losses":45,"wins":113},"thinkingmachines/inkling-small":{"draws":147,"losses":50,"wins":123},"unbiased/pareto-26.10-preview":{"draws":0,"losses":56,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":6,"wins":23},"x-ai/grok-4.5":{"draws":83,"losses":106,"wins":69},"x-ai/grok-4.6":{"draws":123,"losses":117,"wins":54},"x-ai/grok-4.7":{"draws":19,"losses":106,"wins":15},"x-ai/grok-build-0.1":{"draws":24,"losses":13,"wins":25},"xiaomi/mimo-v2.5":{"draws":93,"losses":50,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":36,"losses":30,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":52,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":62,"wins":22},"z-ai/glm-5.2":{"draws":207,"losses":126,"wins":159},"z-ai/glm-5.3":{"draws":60,"losses":142,"wins":32},"z-ai/glm-5.3-flash":{"draws":87,"losses":140,"wins":67},"z-ai/glm-5.3-flashx":{"draws":43,"losses":94,"wins":31}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":13,"losses":19,"wins":4},"claude-fable-5-1":{"draws":2,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":16,"wins":4},"claude-opus-4-5":{"draws":19,"losses":29,"wins":10},"claude-opus-4-8":{"draws":11,"losses":15,"wins":6},"claude-opus-5":{"draws":10,"losses":55,"wins":3},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":14},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":7},"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":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":8},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":20},"google/gemini-3.6-flash":{"draws":20,"losses":35,"wins":5},"google/gemini-3.8-flash":{"draws":11,"losses":19,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":5},"gpt-4.1":{"draws":5,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":12,"wins":7},"gpt-5.4":{"draws":17,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":12},"gpt-5.5":{"draws":20,"losses":13,"wins":1},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":9},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":6},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":2},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":14},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":2},"meta/muse-wonder":{"draws":8,"losses":20,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":1,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":0,"wins":12},"o3":{"draws":12,"losses":23,"wins":7},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":11},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":2},"stealth/ox-alpha":{"draws":46,"losses":65,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":10,"wins":13},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":8},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":25,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":6}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":11,"losses":24,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":4},"claude-opus-4-5":{"draws":18,"losses":25,"wins":15},"claude-opus-4-8":{"draws":11,"losses":18,"wins":3},"claude-opus-5":{"draws":11,"losses":43,"wins":4},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":14,"losses":9,"wins":13},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":12,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"fireworks/ember-1":{"draws":14,"losses":15,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":21,"losses":33,"wins":8},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":8},"gpt-4.1":{"draws":6,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":11,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":9},"gpt-5.5":{"draws":14,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":8},"gpt-6-astra":{"draws":6,"losses":30,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":7},"gpt-6-sol":{"draws":9,"losses":24,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":17},"meta/muse-glimmer-30b":{"draws":13,"losses":11,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":10,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":4},"meta/muse-wonder":{"draws":10,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":8,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":13},"o3":{"draws":11,"losses":20,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":9},"stealth/ox-alpha":{"draws":32,"losses":66,"wins":24},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":18,"losses":3,"wins":19},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":19,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":21,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":12,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":23,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":10},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.8-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":2,"wins":0},"meta/muse-wonder":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"o3":{"draws":6,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max-0902":{"draws":3,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":2,"losses":2,"wins":0},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":0,"wins":0},"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":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":0}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":9},"claude-fable-5":{"draws":9,"losses":23,"wins":6},"claude-fable-5-1":{"draws":5,"losses":32,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":7},"claude-opus-4-5":{"draws":32,"losses":33,"wins":15},"claude-opus-4-8":{"draws":26,"losses":27,"wins":11},"claude-opus-5":{"draws":28,"losses":71,"wins":15},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":20,"losses":13,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":12,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":15,"wins":4},"fireworks/ember-1":{"draws":15,"losses":15,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":11},"google/gemini-3.5-flash":{"draws":16,"losses":20,"wins":12},"google/gemini-3.5-flash-lite":{"draws":42,"losses":9,"wins":27},"google/gemini-3.6-flash":{"draws":33,"losses":31,"wins":20},"google/gemini-3.8-flash":{"draws":22,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":4},"gpt-4.1":{"draws":14,"losses":6,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":22,"losses":12,"wins":12},"gpt-5.4":{"draws":19,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":23,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":24,"losses":11,"wins":29},"gpt-5.5":{"draws":30,"losses":22,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":13,"wins":4},"gpt-6-astra":{"draws":7,"losses":29,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":8},"gpt-6-sol":{"draws":10,"losses":24,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":23,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":18,"losses":6,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":6},"meta/muse-wonder":{"draws":8,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":22,"losses":12,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":21,"wins":7},"nex-agi/nex-n2-pro":{"draws":21,"losses":10,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":10,"wins":10},"o3":{"draws":17,"losses":22,"wins":13},"openai/gpt-oss-120b":{"draws":18,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":22,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":23,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":20,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":15,"wins":6},"qwen/qwen3.8-flash":{"draws":15,"losses":11,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":5},"stealth/ox-alpha":{"draws":43,"losses":63,"wins":26},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":9},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":15,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":21,"losses":22,"wins":19},"thinkingmachines/inkling-small":{"draws":19,"losses":5,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":24,"wins":8},"x-ai/grok-4.6":{"draws":22,"losses":21,"wins":3},"x-ai/grok-4.7":{"draws":9,"losses":23,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":52,"losses":24,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":6,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":51,"losses":32,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":15,"wins":40},"claude-fable-5":{"draws":15,"losses":54,"wins":3},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":15},"claude-opus-4-5":{"draws":39,"losses":45,"wins":22},"claude-opus-4-8":{"draws":12,"losses":21,"wins":17},"claude-opus-5":{"draws":13,"losses":64,"wins":9},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":31,"losses":33,"wins":28},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":37,"losses":30,"wins":41},"deepseek/deepseek-v4-pro":{"draws":31,"losses":29,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":27,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":15},"fireworks/ember-1":{"draws":20,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":25},"google/gemini-3.5-flash":{"draws":28,"losses":39,"wins":31},"google/gemini-3.5-flash-lite":{"draws":58,"losses":39,"wins":59},"google/gemini-3.6-flash":{"draws":48,"losses":56,"wins":42},"google/gemini-3.8-flash":{"draws":21,"losses":39,"wins":18},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":15,"wins":15},"gpt-5.4":{"draws":29,"losses":37,"wins":12},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":23},"gpt-5.5":{"draws":22,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":35,"losses":18,"wins":35},"gpt-5.6-sol":{"draws":13,"losses":60,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":32,"wins":23},"gpt-6-astra":{"draws":4,"losses":70,"wins":0},"gpt-6-luna":{"draws":18,"losses":17,"wins":13},"gpt-6-sol":{"draws":9,"losses":36,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":30},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":28},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":9,"wins":36},"meta/muse-glimmer-30b":{"draws":38,"losses":12,"wins":30},"meta/muse-spark-1.2":{"draws":18,"losses":32,"wins":20},"meta/muse-spark-1.3":{"draws":20,"losses":32,"wins":18},"meta/muse-wonder":{"draws":11,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":26,"losses":6,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":32,"losses":26,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":7,"wins":16},"o3":{"draws":19,"losses":50,"wins":31},"openai/gpt-oss-120b":{"draws":30,"losses":17,"wins":29},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":30},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":30,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":16,"wins":13},"qwen/qwen3.8-flash":{"draws":20,"losses":18,"wins":20},"qwen/qwen3.8-max":{"draws":29,"losses":25,"wins":30},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":67,"losses":125,"wins":78},"stealth/space-bunny-alpha":{"draws":14,"losses":14,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":25,"wins":9},"thinkingmachines/inkling":{"draws":25,"losses":15,"wins":36},"thinkingmachines/inkling-small":{"draws":39,"losses":15,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":24,"losses":37,"wins":11},"x-ai/grok-4.6":{"draws":26,"losses":34,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":43,"losses":35,"wins":48},"z-ai/glm-5.3":{"draws":17,"losses":41,"wins":10},"z-ai/glm-5.3-flash":{"draws":25,"losses":35,"wins":20},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":20},"claude-fable-5":{"draws":17,"losses":49,"wins":6},"claude-fable-5-1":{"draws":5,"losses":77,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":41,"wins":11},"claude-opus-4-5":{"draws":74,"losses":84,"wins":38},"claude-opus-4-8":{"draws":28,"losses":61,"wins":19},"claude-opus-5":{"draws":27,"losses":155,"wins":26},"claude-opus-5-5":{"draws":6,"losses":70,"wins":0},"claude-sonnet-5":{"draws":24,"losses":38,"wins":14},"claude-sonnet-5-5":{"draws":15,"losses":42,"wins":15},"cohere/north-mini-code":{"draws":8,"losses":15,"wins":11},"deepseek/deepseek-v4-flash":{"draws":50,"losses":44,"wins":50},"deepseek/deepseek-v4-pro":{"draws":19,"losses":38,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":27,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":31,"wins":15},"fireworks/ember-1":{"draws":24,"losses":35,"wins":13},"gemini-3.1-pro-preview":{"draws":21,"losses":30,"wins":21},"google/gemini-3.1-flash-lite":{"draws":29,"losses":28,"wins":37},"google/gemini-3.5-flash":{"draws":22,"losses":56,"wins":20},"google/gemini-3.5-flash-lite":{"draws":50,"losses":76,"wins":54},"google/gemini-3.6-flash":{"draws":65,"losses":100,"wins":31},"google/gemini-3.8-flash":{"draws":12,"losses":50,"wins":10},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":8},"gpt-4.1":{"draws":12,"losses":16,"wins":22},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":34,"losses":47,"wins":19},"gpt-5.4":{"draws":23,"losses":40,"wins":13},"gpt-5.4-mini":{"draws":40,"losses":27,"wins":25},"gpt-5.4-nano":{"draws":18,"losses":48,"wins":40},"gpt-5.5":{"draws":32,"losses":62,"wins":26},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":17},"gpt-5.6-sol":{"draws":13,"losses":54,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":32,"wins":16},"gpt-6-astra":{"draws":3,"losses":70,"wins":1},"gpt-6-luna":{"draws":23,"losses":31,"wins":18},"gpt-6-sol":{"draws":13,"losses":56,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":65,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":14,"wins":15},"inclusionai/ling-3.0-flash":{"draws":40,"losses":33,"wins":47},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":36,"losses":42,"wins":50},"meta/muse-glimmer-30b":{"draws":27,"losses":20,"wins":23},"meta/muse-spark-1.2":{"draws":22,"losses":32,"wins":22},"meta/muse-spark-1.3":{"draws":15,"losses":51,"wins":10},"meta/muse-wonder":{"draws":12,"losses":47,"wins":11},"minimax/minimax-m3":{"draws":19,"losses":29,"wins":28},"mistralai/mistral-large-4-0":{"draws":16,"losses":20,"wins":6},"mistralai/mistral-medium-3-5":{"draws":16,"losses":11,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":16,"wins":14},"moonshotai/kimi-k3":{"draws":27,"losses":43,"wins":18},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":37,"wins":40},"o3":{"draws":16,"losses":74,"wins":26},"openai/gpt-oss-120b":{"draws":16,"losses":23,"wins":23},"poolside/laguna-s-2.1":{"draws":38,"losses":53,"wins":43},"qwen/qwen3.7-max":{"draws":34,"losses":36,"wins":12},"qwen/qwen3.7-plus":{"draws":21,"losses":26,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":36,"wins":18},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":14},"qwen/qwen3.8-flash":{"draws":14,"losses":26,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":31,"wins":16},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"stealth/ox-alpha":{"draws":60,"losses":149,"wins":53},"stealth/space-bunny-alpha":{"draws":19,"losses":23,"wins":16},"stepfun/step-3.7-flash":{"draws":13,"losses":39,"wins":10},"tencent/hy3-preview":{"draws":26,"losses":23,"wins":23},"tencent/hy4-preview":{"draws":28,"losses":38,"wins":10},"thinkingmachines/inkling":{"draws":41,"losses":23,"wins":30},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":37,"losses":64,"wins":23},"x-ai/grok-4.6":{"draws":27,"losses":34,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":50,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":17,"wins":12},"xiaomi/mimo-v2.5":{"draws":74,"losses":91,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":38,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":27,"wins":5},"z-ai/glm-5.2":{"draws":70,"losses":82,"wins":50},"z-ai/glm-5.3":{"draws":15,"losses":44,"wins":11},"z-ai/glm-5.3-flash":{"draws":20,"losses":41,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":44,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":36,"wins":13},"claude-fable-5":{"draws":15,"losses":44,"wins":9},"claude-fable-5-1":{"draws":4,"losses":65,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":27,"wins":5},"claude-opus-4-5":{"draws":34,"losses":60,"wins":8},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":31,"losses":47,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":57,"losses":42,"wins":13},"deepseek/deepseek-v4-pro":{"draws":39,"losses":34,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":26,"wins":8},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":26,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.5-flash":{"draws":32,"losses":45,"wins":9},"google/gemini-3.5-flash-lite":{"draws":58,"losses":62,"wins":42},"google/gemini-3.6-flash":{"draws":43,"losses":68,"wins":26},"google/gemini-3.8-flash":{"draws":27,"losses":38,"wins":7},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":21,"losses":17,"wins":4},"gpt-5.4":{"draws":37,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":18,"losses":18,"wins":12},"gpt-5.5":{"draws":16,"losses":25,"wins":3},"gpt-5.6-luna":{"draws":44,"losses":35,"wins":15},"gpt-5.6-sol":{"draws":15,"losses":54,"wins":3},"gpt-5.6-terra":{"draws":32,"losses":46,"wins":4},"gpt-6-astra":{"draws":2,"losses":56,"wins":0},"gpt-6-luna":{"draws":11,"losses":25,"wins":10},"gpt-6-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":16,"wins":17},"inclusionai/ling-3.0-flash":{"draws":20,"losses":12,"wins":12},"meituan/longcat-2.0":{"draws":23,"losses":33,"wins":14},"meta/muse-glimmer-30b":{"draws":42,"losses":28,"wins":12},"meta/muse-spark-1.2":{"draws":22,"losses":32,"wins":10},"meta/muse-spark-1.3":{"draws":25,"losses":38,"wins":5},"meta/muse-wonder":{"draws":12,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":10,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":32,"losses":12,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":27,"losses":36,"wins":9},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":8},"o3":{"draws":23,"losses":53,"wins":19},"openai/gpt-oss-120b":{"draws":37,"losses":29,"wins":16},"poolside/laguna-s-2.1":{"draws":39,"losses":26,"wins":5},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":48,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.8-flash":{"draws":26,"losses":24,"wins":6},"qwen/qwen3.8-max":{"draws":47,"losses":46,"wins":34},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"stealth/ox-alpha":{"draws":87,"losses":135,"wins":36},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":12},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":9},"thinkingmachines/inkling":{"draws":33,"losses":29,"wins":10},"thinkingmachines/inkling-small":{"draws":41,"losses":36,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":24,"losses":40,"wins":5},"x-ai/grok-4.6":{"draws":24,"losses":42,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":26,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":19,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":54,"losses":59,"wins":21},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":2},"z-ai/glm-5.3-flash":{"draws":25,"losses":43,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":29,"wins":6}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":41},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":20,"wins":27},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":74},"claude-opus-4-8":{"draws":2,"losses":1,"wins":39},"claude-opus-5":{"draws":3,"losses":29,"wins":46},"claude-opus-5-5":{"draws":1,"losses":24,"wins":21},"claude-sonnet-5":{"draws":0,"losses":0,"wins":42},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"fireworks/ember-1":{"draws":1,"losses":1,"wins":44},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":44},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":47},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":75},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":66},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":40},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":38},"gpt-5.4":{"draws":2,"losses":6,"wins":34},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":41},"gpt-5.5":{"draws":1,"losses":4,"wins":33},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":39},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":35},"gpt-6-astra":{"draws":6,"losses":21,"wins":19},"gpt-6-luna":{"draws":2,"losses":1,"wins":41},"gpt-6-sol":{"draws":5,"losses":7,"wins":32},"gpt-6.1-sol":{"draws":2,"losses":17,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":30},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":42},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":38},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":40},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":38},"meta/muse-wonder":{"draws":4,"losses":9,"wins":33},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":33},"o3":{"draws":0,"losses":3,"wins":59},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":37},"stealth/ox-alpha":{"draws":9,"losses":6,"wins":131},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":20},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":53},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":38},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":38},"x-ai/grok-4.7":{"draws":3,"losses":6,"wins":29},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":80},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":37},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":38}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":8,"losses":1,"wins":1},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":7,"losses":5,"wins":0},"claude-opus-5-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":1,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":5,"losses":1,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.5":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":0},"gpt-6-astra":{"draws":2,"losses":4,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":3},"meta/muse-wonder":{"draws":3,"losses":3,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":1},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":10,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":0,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":0},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":0}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":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-haiku-5-5":{"draws":11,"losses":18,"wins":13},"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},"claude-sonnet-5-5":{"draws":15,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"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},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"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":6,"wins":14},"gpt-4.1":{"draws":8,"losses":6,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"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":18,"losses":15,"wins":13},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":28},"inclusionai/ling-3.0-flash":{"draws":32,"losses":9,"wins":39},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"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":31,"losses":33,"wins":36},"meta/muse-spark-1.3":{"draws":10,"losses":40,"wins":20},"meta/muse-wonder":{"draws":9,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":8},"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":45,"losses":52,"wins":27},"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":7,"losses":72,"wins":75},"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":11,"losses":16,"wins":15},"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":13,"losses":21,"wins":14},"stealth/ox-alpha":{"draws":67,"losses":113,"wins":84},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":20},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":44,"wins":20},"thinkingmachines/inkling":{"draws":34,"losses":16,"wins":64},"thinkingmachines/inkling-small":{"draws":34,"losses":11,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":27,"losses":41,"wins":12},"x-ai/grok-4.6":{"draws":32,"losses":37,"wins":17},"x-ai/grok-4.7":{"draws":5,"losses":30,"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":6,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":41,"losses":36,"wins":51},"z-ai/glm-5.3":{"draws":16,"losses":41,"wins":11},"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":37,"losses":14,"wins":31},"claude-fable-5":{"draws":26,"losses":50,"wins":10},"claude-fable-5-1":{"draws":3,"losses":86,"wins":3},"claude-haiku-5-5":{"draws":16,"losses":15,"wins":13},"claude-opus-4-5":{"draws":37,"losses":32,"wins":37},"claude-opus-4-8":{"draws":16,"losses":20,"wins":12},"claude-opus-5":{"draws":17,"losses":68,"wins":7},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":37,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":13,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":45,"losses":22,"wins":47},"deepseek/deepseek-v4-pro":{"draws":32,"losses":21,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":28,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":20,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":20,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":18},"google/gemini-3.5-flash":{"draws":37,"losses":29,"wins":30},"google/gemini-3.5-flash-lite":{"draws":67,"losses":31,"wins":56},"google/gemini-3.6-flash":{"draws":52,"losses":55,"wins":37},"google/gemini-3.8-flash":{"draws":30,"losses":39,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":17,"losses":13,"wins":18},"gpt-5.4":{"draws":32,"losses":44,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":22,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":38,"losses":21,"wins":33},"gpt-5.6-sol":{"draws":19,"losses":53,"wins":16},"gpt-5.6-terra":{"draws":43,"losses":21,"wins":22},"gpt-6-astra":{"draws":9,"losses":73,"wins":0},"gpt-6-luna":{"draws":19,"losses":11,"wins":16},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":7,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":24},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":22},"meta/muse-glimmer-30b":{"draws":42,"losses":6,"wins":28},"meta/muse-spark-1.2":{"draws":25,"losses":17,"wins":28},"meta/muse-spark-1.3":{"draws":21,"losses":28,"wins":21},"meta/muse-wonder":{"draws":18,"losses":24,"wins":2},"minimax/minimax-m3":{"draws":12,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":7,"wins":10},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":27,"losses":18,"wins":27},"nex-agi/nex-n2-pro":{"draws":12,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":14},"o3":{"draws":19,"losses":42,"wins":41},"openai/gpt-oss-120b":{"draws":40,"losses":12,"wins":26},"poolside/laguna-s-2.1":{"draws":38,"losses":15,"wins":21},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":36,"wins":20},"qwen/qwen3.8-27b":{"draws":15,"losses":22,"wins":9},"qwen/qwen3.8-flash":{"draws":24,"losses":16,"wins":14},"qwen/qwen3.8-max":{"draws":42,"losses":34,"wins":18},"qwen/qwen3.8-max-0902":{"draws":19,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":105,"losses":128,"wins":45},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":33,"losses":33,"wins":18},"thinkingmachines/inkling":{"draws":26,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":39,"losses":20,"wins":33},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":25,"losses":42,"wins":13},"x-ai/grok-4.6":{"draws":23,"losses":30,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":36,"losses":13,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":54,"losses":34,"wins":52},"z-ai/glm-5.3":{"draws":17,"losses":39,"wins":12},"z-ai/glm-5.3-flash":{"draws":23,"losses":40,"wins":21},"z-ai/glm-5.3-flashx":{"draws":14,"losses":29,"wins":5}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":15,"wins":18},"claude-fable-5":{"draws":5,"losses":26,"wins":11},"claude-fable-5-1":{"draws":3,"losses":37,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":15},"claude-opus-4-5":{"draws":13,"losses":26,"wins":31},"claude-opus-4-8":{"draws":11,"losses":17,"wins":14},"claude-opus-5":{"draws":10,"losses":43,"wins":17},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":9,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":17},"fireworks/ember-1":{"draws":6,"losses":14,"wins":22},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":17,"wins":26},"google/gemini-3.5-flash-lite":{"draws":13,"losses":21,"wins":40},"google/gemini-3.6-flash":{"draws":5,"losses":35,"wins":34},"google/gemini-3.8-flash":{"draws":10,"losses":17,"wins":15},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":14},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":15,"wins":15},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":8,"wins":27},"gpt-5.5":{"draws":8,"losses":19,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":28,"wins":9},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":17},"gpt-6-astra":{"draws":3,"losses":34,"wins":5},"gpt-6-luna":{"draws":7,"losses":13,"wins":20},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":4,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":15},"meta/muse-wonder":{"draws":10,"losses":18,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":28},"o3":{"draws":7,"losses":24,"wins":29},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":19},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":16,"wins":14},"stealth/ox-alpha":{"draws":28,"losses":44,"wins":46},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":22},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":31},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":22,"losses":21,"wins":41},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":13},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":18,"wins":17}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":39,"wins":33},"claude-fable-5":{"draws":14,"losses":86,"wins":2},"claude-fable-5-1":{"draws":5,"losses":105,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":59,"wins":20},"claude-opus-4-5":{"draws":84,"losses":133,"wins":59},"claude-opus-4-8":{"draws":42,"losses":118,"wins":22},"claude-opus-5":{"draws":35,"losses":193,"wins":10},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":28,"losses":61,"wins":19},"claude-sonnet-5-5":{"draws":15,"losses":74,"wins":13},"cohere/north-mini-code":{"draws":18,"losses":13,"wins":23},"deepseek/deepseek-v4-flash":{"draws":62,"losses":76,"wins":80},"deepseek/deepseek-v4-pro":{"draws":28,"losses":48,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":53,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":57,"wins":17},"fireworks/ember-1":{"draws":32,"losses":54,"wins":16},"gemini-3.1-pro-preview":{"draws":24,"losses":52,"wins":26},"google/gemini-3.1-flash-lite":{"draws":38,"losses":43,"wins":63},"google/gemini-3.5-flash":{"draws":31,"losses":80,"wins":31},"google/gemini-3.5-flash-lite":{"draws":49,"losses":93,"wins":64},"google/gemini-3.6-flash":{"draws":59,"losses":129,"wins":40},"google/gemini-3.8-flash":{"draws":26,"losses":66,"wins":12},"google/gemma-4-31b-it":{"draws":16,"losses":15,"wins":25},"gpt-4.1":{"draws":22,"losses":29,"wins":17},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":43,"losses":60,"wins":27},"gpt-5.4":{"draws":22,"losses":74,"wins":6},"gpt-5.4-mini":{"draws":46,"losses":37,"wins":47},"gpt-5.4-nano":{"draws":38,"losses":101,"wins":85},"gpt-5.5":{"draws":67,"losses":70,"wins":19},"gpt-5.6-luna":{"draws":34,"losses":42,"wins":26},"gpt-5.6-sol":{"draws":13,"losses":81,"wins":10},"gpt-5.6-terra":{"draws":29,"losses":65,"wins":8},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":24,"losses":59,"wins":15},"gpt-6-sol":{"draws":14,"losses":78,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":90,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":13,"wins":35},"inclusionai/ling-3.0-flash":{"draws":42,"losses":26,"wins":52},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":71,"wins":58},"meta/muse-glimmer-30b":{"draws":30,"losses":34,"wins":26},"meta/muse-spark-1.2":{"draws":24,"losses":60,"wins":16},"meta/muse-spark-1.3":{"draws":18,"losses":75,"wins":13},"meta/muse-wonder":{"draws":9,"losses":78,"wins":9},"minimax/minimax-m3":{"draws":28,"losses":39,"wins":45},"mistralai/mistral-large-4-0":{"draws":15,"losses":27,"wins":12},"mistralai/mistral-medium-3-5":{"draws":18,"losses":17,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":22,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":75,"wins":23},"nex-agi/nex-n2-pro":{"draws":27,"losses":26,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":55,"wins":64},"o3":{"draws":26,"losses":108,"wins":40},"openai/gpt-oss-120b":{"draws":26,"losses":34,"wins":28},"poolside/laguna-s-2.1":{"draws":37,"losses":65,"wins":42},"qwen/qwen3.7-max":{"draws":36,"losses":46,"wins":30},"qwen/qwen3.7-plus":{"draws":19,"losses":35,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":58,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":47,"wins":19},"qwen/qwen3.8-flash":{"draws":22,"losses":31,"wins":17},"qwen/qwen3.8-max":{"draws":27,"losses":55,"wins":26},"qwen/qwen3.8-max-0902":{"draws":32,"losses":57,"wins":11},"stealth/ox-alpha":{"draws":61,"losses":213,"wins":52},"stealth/space-bunny-alpha":{"draws":26,"losses":33,"wins":23},"stepfun/step-3.7-flash":{"draws":18,"losses":33,"wins":43},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":47,"wins":31},"tencent/hy4-preview":{"draws":28,"losses":77,"wins":9},"thinkingmachines/inkling":{"draws":32,"losses":48,"wins":84},"thinkingmachines/inkling-small":{"draws":34,"losses":28,"wins":42},"unbiased/pareto-26.10-preview":{"draws":2,"losses":30,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":17,"wins":10},"x-ai/grok-4.5":{"draws":28,"losses":81,"wins":15},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":10},"x-ai/grok-4.7":{"draws":7,"losses":74,"wins":9},"x-ai/grok-build-0.1":{"draws":16,"losses":29,"wins":19},"xiaomi/mimo-v2.5":{"draws":93,"losses":81,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":57,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":44,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":95,"losses":124,"wins":71},"z-ai/glm-5.3":{"draws":13,"losses":80,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":61,"wins":20},"z-ai/glm-5.3-flashx":{"draws":22,"losses":70,"wins":10}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":15,"wins":8},"claude-fable-5":{"draws":6,"losses":34,"wins":2},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":20,"wins":8},"claude-opus-4-5":{"draws":26,"losses":47,"wins":27},"claude-opus-4-8":{"draws":19,"losses":29,"wins":14},"claude-opus-5":{"draws":8,"losses":99,"wins":3},"claude-opus-5-5":{"draws":1,"losses":44,"wins":1},"claude-sonnet-5":{"draws":10,"losses":28,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":35,"losses":35,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":23,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":5},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":21,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":34},"google/gemini-3.5-flash":{"draws":16,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":40,"wins":23},"google/gemini-3.6-flash":{"draws":22,"losses":52,"wins":12},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":10},"gpt-4.1":{"draws":8,"losses":16,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":21,"wins":14},"gpt-5.4":{"draws":10,"losses":25,"wins":5},"gpt-5.4-mini":{"draws":15,"losses":22,"wins":11},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":32},"gpt-5.5":{"draws":26,"losses":25,"wins":13},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":28,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":11,"losses":23,"wins":6},"gpt-6-sol":{"draws":1,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":24,"losses":15,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":26,"wins":29},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":40,"wins":3},"meta/muse-wonder":{"draws":4,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":13},"nex-agi/nex-n2-pro":{"draws":16,"losses":11,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":14,"wins":22},"o3":{"draws":14,"losses":40,"wins":14},"openai/gpt-oss-120b":{"draws":16,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":22,"losses":26,"wins":22},"qwen/qwen3.7-max":{"draws":17,"losses":24,"wins":11},"qwen/qwen3.7-plus":{"draws":20,"losses":8,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":20,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":20,"wins":4},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":9},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":87,"wins":22},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":19,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":16,"losses":17,"wins":35},"thinkingmachines/inkling-small":{"draws":20,"losses":9,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":42,"wins":9},"x-ai/grok-4.6":{"draws":12,"losses":33,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":1},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":38,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":8,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":5},"z-ai/glm-5.2":{"draws":48,"losses":48,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":4},"z-ai/glm-5.3-flashx":{"draws":12,"losses":27,"wins":3}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":17},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":1,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":15,"wins":10},"claude-opus-4-5":{"draws":22,"losses":27,"wins":19},"claude-opus-4-8":{"draws":10,"losses":16,"wins":12},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":11},"fireworks/ember-1":{"draws":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":21,"wins":19},"google/gemini-3.5-flash-lite":{"draws":14,"losses":15,"wins":43},"google/gemini-3.6-flash":{"draws":15,"losses":33,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":1},"gpt-5":{"draws":12,"losses":18,"wins":8},"gpt-5.4":{"draws":16,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":9},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":21},"gpt-5.5":{"draws":20,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":12,"losses":20,"wins":8},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":5,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":29,"wins":6},"meta/muse-wonder":{"draws":4,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":17},"o3":{"draws":8,"losses":20,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":19},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":17,"wins":14},"stealth/ox-alpha":{"draws":35,"losses":70,"wins":33},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":14,"losses":8,"wins":24},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":20,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":5,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":24,"wins":6},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":10}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":6,"losses":32,"wins":10},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":10},"claude-opus-4-5":{"draws":28,"losses":25,"wins":25},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":25,"losses":38,"wins":21},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":13},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":10,"losses":17,"wins":19},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":3,"wins":32},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":14},"meta/muse-wonder":{"draws":8,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":24},"o3":{"draws":10,"losses":18,"wins":36},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":10,"losses":19,"wins":17},"stealth/ox-alpha":{"draws":43,"losses":66,"wins":47},"stealth/space-bunny-alpha":{"draws":15,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":29},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":4,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":11,"wins":2},"z-ai/glm-5.2":{"draws":40,"losses":22,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":10,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":73,"losses":58,"wins":47},"claude-fable-5":{"draws":37,"losses":107,"wins":22},"claude-fable-5-1":{"draws":8,"losses":164,"wins":2},"claude-haiku-5-5":{"draws":24,"losses":79,"wins":23},"claude-opus-4-5":{"draws":116,"losses":165,"wins":91},"claude-opus-4-8":{"draws":58,"losses":108,"wins":40},"claude-opus-5":{"draws":57,"losses":262,"wins":35},"claude-opus-5-5":{"draws":9,"losses":142,"wins":5},"claude-sonnet-5":{"draws":65,"losses":83,"wins":44},"claude-sonnet-5-5":{"draws":28,"losses":90,"wins":26},"cohere/north-mini-code":{"draws":15,"losses":3,"wins":42},"deepseek/deepseek-v4-flash":{"draws":104,"losses":69,"wins":125},"deepseek/deepseek-v4-pro":{"draws":61,"losses":74,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":72,"losses":57,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":50,"losses":66,"wins":28},"fireworks/ember-1":{"draws":48,"losses":69,"wins":27},"gemini-3.1-pro-preview":{"draws":43,"losses":64,"wins":37},"google/gemini-3.1-flash-lite":{"draws":35,"losses":26,"wins":91},"google/gemini-3.5-flash":{"draws":55,"losses":101,"wins":64},"google/gemini-3.5-flash-lite":{"draws":113,"losses":131,"wins":118},"google/gemini-3.6-flash":{"draws":109,"losses":138,"wins":81},"google/gemini-3.8-flash":{"draws":51,"losses":96,"wins":29},"google/gemma-4-31b-it":{"draws":33,"losses":14,"wins":33},"gpt-4.1":{"draws":25,"losses":22,"wins":29},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":58,"losses":74,"wins":58},"gpt-5.4":{"draws":53,"losses":83,"wins":36},"gpt-5.4-mini":{"draws":69,"losses":29,"wins":52},"gpt-5.4-nano":{"draws":58,"losses":80,"wins":90},"gpt-5.5":{"draws":78,"losses":86,"wins":44},"gpt-5.6-luna":{"draws":67,"losses":50,"wins":73},"gpt-5.6-sol":{"draws":21,"losses":130,"wins":19},"gpt-5.6-terra":{"draws":73,"losses":69,"wins":44},"gpt-6-astra":{"draws":7,"losses":142,"wins":3},"gpt-6-luna":{"draws":54,"losses":57,"wins":33},"gpt-6-sol":{"draws":26,"losses":107,"wins":11},"gpt-6.1-sol":{"draws":12,"losses":127,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":60,"losses":13,"wins":65},"inclusionai/ling-3.0-flash":{"draws":67,"losses":26,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":72,"losses":54,"wins":111},"meta/muse-glimmer-30b":{"draws":85,"losses":27,"wins":56},"meta/muse-spark-1.2":{"draws":42,"losses":76,"wins":48},"meta/muse-spark-1.3":{"draws":37,"losses":93,"wins":34},"meta/muse-wonder":{"draws":30,"losses":91,"wins":17},"minimax/minimax-m3":{"draws":40,"losses":26,"wins":44},"mistralai/mistral-large-4-0":{"draws":25,"losses":41,"wins":14},"mistralai/mistral-medium-3-5":{"draws":56,"losses":12,"wins":44},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":26,"wins":19},"moonshotai/kimi-k3":{"draws":53,"losses":73,"wins":42},"nex-agi/nex-n2-pro":{"draws":44,"losses":17,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":81,"losses":42,"wins":55},"o3":{"draws":44,"losses":119,"wins":81},"openai/gpt-oss-120b":{"draws":61,"losses":46,"wins":63},"poolside/laguna-s-2.1":{"draws":86,"losses":70,"wins":56},"qwen/qwen3.7-max":{"draws":43,"losses":50,"wins":45},"qwen/qwen3.7-plus":{"draws":40,"losses":26,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":76,"losses":69,"wins":33},"qwen/qwen3.8-27b":{"draws":37,"losses":45,"wins":28},"qwen/qwen3.8-flash":{"draws":51,"losses":36,"wins":33},"qwen/qwen3.8-max":{"draws":66,"losses":70,"wins":46},"qwen/qwen3.8-max-0902":{"draws":49,"losses":64,"wins":27},"stealth/ox-alpha":{"draws":158,"losses":303,"wins":121},"stealth/space-bunny-alpha":{"draws":40,"losses":37,"wins":37},"stepfun/step-3.7-flash":{"draws":25,"losses":38,"wins":47},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":44,"losses":33,"wins":41},"tencent/hy4-preview":{"draws":48,"losses":93,"wins":31},"thinkingmachines/inkling":{"draws":72,"losses":55,"wins":95},"thinkingmachines/inkling-small":{"draws":77,"losses":50,"wins":69},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":50,"losses":111,"wins":31},"x-ai/grok-4.6":{"draws":50,"losses":107,"wins":23},"x-ai/grok-4.7":{"draws":15,"losses":95,"wins":16},"x-ai/grok-build-0.1":{"draws":23,"losses":16,"wins":27},"xiaomi/mimo-v2.5":{"draws":124,"losses":89,"wins":137},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":47,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":53,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":50,"wins":18},"z-ai/glm-5.2":{"draws":121,"losses":114,"wins":101},"z-ai/glm-5.3":{"draws":42,"losses":99,"wins":13},"z-ai/glm-5.3-flash":{"draws":49,"losses":98,"wins":33},"z-ai/glm-5.3-flashx":{"draws":35,"losses":77,"wins":32}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":19,"wins":34},"claude-fable-5":{"draws":17,"losses":51,"wins":22},"claude-fable-5-1":{"draws":6,"losses":84,"wins":4},"claude-haiku-5-5":{"draws":10,"losses":18,"wins":16},"claude-opus-4-5":{"draws":39,"losses":31,"wins":36},"claude-opus-4-8":{"draws":11,"losses":17,"wins":20},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":31,"losses":17,"wins":38},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":45,"losses":12,"wins":49},"deepseek/deepseek-v4-pro":{"draws":32,"losses":24,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":31,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":18,"losses":14,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":20},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":32,"losses":38,"wins":30},"google/gemini-3.5-flash-lite":{"draws":51,"losses":25,"wins":82},"google/gemini-3.6-flash":{"draws":36,"losses":54,"wins":52},"google/gemini-3.8-flash":{"draws":22,"losses":42,"wins":24},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":11},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":28,"losses":46,"wins":14},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":15,"wins":26},"gpt-5.5":{"draws":15,"losses":11,"wins":20},"gpt-5.6-luna":{"draws":33,"losses":25,"wins":32},"gpt-5.6-sol":{"draws":16,"losses":57,"wins":13},"gpt-5.6-terra":{"draws":30,"losses":24,"wins":30},"gpt-6-astra":{"draws":9,"losses":72,"wins":3},"gpt-6-luna":{"draws":11,"losses":17,"wins":18},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":24},"inclusionai/ling-3.0-flash":{"draws":21,"losses":2,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":11,"wins":37},"meta/muse-glimmer-30b":{"draws":21,"losses":16,"wins":35},"meta/muse-spark-1.2":{"draws":15,"losses":35,"wins":16},"meta/muse-spark-1.3":{"draws":16,"losses":27,"wins":25},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":33,"losses":20,"wins":17},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":13,"wins":17},"o3":{"draws":13,"losses":38,"wins":43},"openai/gpt-oss-120b":{"draws":34,"losses":6,"wins":36},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":30},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":20,"wins":28},"qwen/qwen3.8-27b":{"draws":15,"losses":6,"wins":25},"qwen/qwen3.8-flash":{"draws":27,"losses":17,"wins":12},"qwen/qwen3.8-max":{"draws":29,"losses":34,"wins":23},"qwen/qwen3.8-max-0902":{"draws":16,"losses":18,"wins":12},"stealth/ox-alpha":{"draws":87,"losses":110,"wins":76},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":21},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":13},"tencent/hy4-preview":{"draws":28,"losses":21,"wins":37},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":29,"losses":20,"wins":39},"unbiased/pareto-26.10-preview":{"draws":2,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":24,"losses":22,"wins":30},"x-ai/grok-4.6":{"draws":26,"losses":42,"wins":22},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":30,"losses":3,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":53,"losses":33,"wins":54},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":0},"z-ai/glm-5.3-flash":{"draws":27,"losses":33,"wins":26},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":13}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":10,"wins":38},"claude-fable-5":{"draws":18,"losses":49,"wins":13},"claude-fable-5-1":{"draws":5,"losses":79,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":23,"wins":11},"claude-opus-4-5":{"draws":30,"losses":37,"wins":41},"claude-opus-4-8":{"draws":6,"losses":23,"wins":15},"claude-opus-5":{"draws":16,"losses":65,"wins":13},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":27,"losses":33,"wins":28},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":50,"losses":22,"wins":36},"deepseek/deepseek-v4-pro":{"draws":27,"losses":18,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":28,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":15,"losses":15,"wins":18},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":21},"google/gemini-3.5-flash":{"draws":26,"losses":40,"wins":32},"google/gemini-3.5-flash-lite":{"draws":53,"losses":47,"wins":52},"google/gemini-3.6-flash":{"draws":38,"losses":57,"wins":45},"google/gemini-3.8-flash":{"draws":21,"losses":42,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":13},"gpt-4.1":{"draws":2,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":13,"wins":18},"gpt-5.4":{"draws":18,"losses":39,"wins":25},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":15,"losses":15,"wins":18},"gpt-5.5":{"draws":16,"losses":16,"wins":14},"gpt-5.6-luna":{"draws":37,"losses":23,"wins":26},"gpt-5.6-sol":{"draws":22,"losses":49,"wins":15},"gpt-5.6-terra":{"draws":27,"losses":24,"wins":29},"gpt-6-astra":{"draws":11,"losses":63,"wins":4},"gpt-6-luna":{"draws":14,"losses":12,"wins":20},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":22},"meituan/longcat-2.0":{"draws":21,"losses":22,"wins":35},"meta/muse-glimmer-30b":{"draws":32,"losses":14,"wins":30},"meta/muse-spark-1.2":{"draws":16,"losses":26,"wins":24},"meta/muse-spark-1.3":{"draws":16,"losses":31,"wins":21},"meta/muse-wonder":{"draws":16,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":7,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":18,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":28,"losses":21,"wins":21},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":16,"wins":13},"o3":{"draws":14,"losses":42,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":13,"wins":31},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":21},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":31,"wins":21},"qwen/qwen3.8-27b":{"draws":14,"losses":16,"wins":14},"qwen/qwen3.8-flash":{"draws":23,"losses":19,"wins":12},"qwen/qwen3.8-max":{"draws":29,"losses":30,"wins":19},"qwen/qwen3.8-max-0902":{"draws":14,"losses":23,"wins":11},"stealth/ox-alpha":{"draws":73,"losses":128,"wins":73},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":11,"losses":11,"wins":16},"tencent/hy3-preview":{"draws":6,"losses":11,"wins":11},"tencent/hy4-preview":{"draws":26,"losses":34,"wins":16},"thinkingmachines/inkling":{"draws":27,"losses":17,"wins":28},"thinkingmachines/inkling-small":{"draws":32,"losses":22,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":14,"losses":29,"wins":23},"x-ai/grok-4.6":{"draws":31,"losses":28,"wins":21},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":32,"losses":17,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":56,"losses":31,"wins":49},"z-ai/glm-5.3":{"draws":19,"losses":37,"wins":10},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":10},"z-ai/glm-5.3-flashx":{"draws":15,"losses":23,"wins":10}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":11},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":11,"losses":21,"wins":12},"claude-opus-5":{"draws":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":19,"losses":11,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":16,"wins":24},"google/gemini-3.5-flash-lite":{"draws":32,"losses":13,"wins":39},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":23},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":14},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":10,"wins":15},"gpt-5.4":{"draws":17,"losses":17,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":25},"gpt-5.5":{"draws":19,"losses":16,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":8},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":17},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":18},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":15},"meta/muse-wonder":{"draws":11,"losses":26,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"o3":{"draws":12,"losses":14,"wins":40},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":9,"wins":14},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":17,"wins":15},"stealth/ox-alpha":{"draws":36,"losses":69,"wins":51},"stealth/space-bunny-alpha":{"draws":14,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":5,"wins":34},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":0,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":24,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}