{"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":"2026-08-07T12:33:34Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:f42601f844754f74","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.138875},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125000000001},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.07445}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":73.70625692665044,"highest":80.80364109715514,"medium":74.90272134044969,"none":69.63250431033174},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.1875,"model_code_failures":3}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:16Z","match_totals_all":{"draws":541,"losses":636,"wins":2420},"match_totals_tracks":{"highest":{"draws":63,"losses":157,"wins":674},"medium":{"draws":176,"losses":233,"wins":905},"none":{"draws":302,"losses":246,"wins":841}},"model_slug":"claude-opus-5","overall":{"max":100.0,"mean":72.16867361924449,"min":43.10391328842407},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.096152664379886,"GB2-02":71.99902750726241,"GB2-03":98.38502694069997,"GB2-04":79.47342462976314,"GB2-05":85.20269021147601,"GB2-07":100.0,"GB2-08":67.46916572650451},"per_game_all":{"GB2-01":67.64128620520997,"GB2-02":67.29591060419256,"GB2-03":82.74116288274756,"GB2-04":55.853507681253575,"GB2-05":84.60600044621033,"GB2-07":88.17038286729267,"GB2-08":69.63554779964636},"per_game_match_totals_all":{"GB2-01":{"draws":121,"losses":128,"wins":310},"GB2-02":{"draws":171,"losses":50,"wins":215},"GB2-03":{"draws":42,"losses":78,"wins":322},"GB2-04":{"draws":189,"losses":130,"wins":237},"GB2-05":{"draws":0,"losses":74,"wins":514},"GB2-06":{"draws":11,"losses":5,"wins":84},"GB2-07":{"draws":0,"losses":56,"wins":306},"GB2-08":{"draws":7,"losses":115,"wins":432}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":46,"wins":77},"GB2-02":{"draws":37,"losses":21,"wins":56},"GB2-03":{"draws":0,"losses":9,"wins":103},"GB2-04":{"draws":25,"losses":19,"wins":116},"GB2-05":{"draws":0,"losses":22,"wins":114},"GB2-07":{"draws":0,"losses":1,"wins":77},"GB2-08":{"draws":0,"losses":39,"wins":131}},"medium":{"GB2-01":{"draws":19,"losses":59,"wins":124},"GB2-02":{"draws":64,"losses":15,"wins":65},"GB2-03":{"draws":8,"losses":15,"wins":135},"GB2-04":{"draws":85,"losses":55,"wins":58},"GB2-05":{"draws":0,"losses":28,"wins":194},"GB2-07":{"draws":0,"losses":33,"wins":155},"GB2-08":{"draws":0,"losses":28,"wins":174}},"none":{"GB2-01":{"draws":101,"losses":23,"wins":109},"GB2-02":{"draws":70,"losses":14,"wins":94},"GB2-03":{"draws":34,"losses":54,"wins":84},"GB2-04":{"draws":79,"losses":56,"wins":63},"GB2-05":{"draws":0,"losses":24,"wins":206},"GB2-06":{"draws":11,"losses":5,"wins":84},"GB2-07":{"draws":0,"losses":22,"wins":74},"GB2-08":{"draws":7,"losses":48,"wins":127}}},"per_game_raw_elo_all":{"GB2-01":1700.936252843705,"GB2-02":1667.5243923953606,"GB2-03":1777.911838535716,"GB2-04":1624.121377647322,"GB2-05":1948.5386140340622,"GB2-07":1927.1769578368612,"GB2-08":1792.9782208479019},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1666.7809463961355,"GB2-02":1693.539453456156,"GB2-03":1886.5839666583847,"GB2-04":1757.096473051806,"GB2-05":1961.9846191205747,"GB2-07":2048.6955646228785,"GB2-08":1776.0794210582203},"medium":{"GB2-01":1716.7127113138886,"GB2-02":1651.5328918965038,"GB2-03":1861.0033303173484,"GB2-04":1562.8056788345384,"GB2-05":1918.5280885728605,"GB2-07":1897.5748924741924,"GB2-08":1902.1030786263232},"none":{"GB2-01":1719.3151008210912,"GB2-02":1657.5008318334221,"GB2-03":1586.1482186314154,"GB2-04":1552.461981055621,"GB2-05":1965.1031344087517,"GB2-06":1924.0542264240664,"GB2-07":1835.2604164135125,"GB2-08":1700.752162859162}},"per_game_tracks":{"highest":{"GB2-01":63.096152664379886,"GB2-02":71.99902750726241,"GB2-03":98.38502694069997,"GB2-04":79.47342462976314,"GB2-05":85.20269021147601,"GB2-07":100.0,"GB2-08":67.46916572650451},"medium":{"GB2-01":69.6194323591836,"GB2-02":63.73552101088833,"GB2-03":95.74255598925224,"GB2-04":44.983185125573506,"GB2-05":82.07879945591797,"GB2-07":85.32857790093769,"GB2-08":82.83097754139442},"none":{"GB2-01":70.20827359206642,"GB2-02":66.15318329442692,"GB2-03":54.09590571829045,"GB2-04":43.10391328842407,"GB2-05":86.53651167123698,"GB2-06":99.17317608622864,"GB2-07":79.18257070094032,"GB2-08":58.60650013104014}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":76.71614536377726,"medium":72.44353093299611,"none":67.34634456096008},"reasoning_agg":{"highest":{"max":100.0,"mean":76.71614536377726,"min":63.096152664379886},"medium":{"max":95.74255598925224,"mean":72.44353093299611,"min":44.983185125573506},"none":{"max":99.17317608622864,"mean":67.34634456096008,"min":43.10391328842407}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":86.13671171032217,"reasoning_variance":9.369800802817181,"reliability_score":89.64113280154912,"uncertainty_avg":10.358867198450882,"uncertainty_penalty":13.968038091077688},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":79.53629857129359,"reliability_score":83.60262408125878,"uncertainty_avg":16.397375918741215,"uncertainty_penalty":2.820153207516327},"medium":{"ceiling_score":95.74255598925224,"expected_score":91.47441802395666,"reliability_score":91.97535585326195,"uncertainty_avg":8.024644146738058,"uncertainty_penalty":19.030887090960547},"none":{"ceiling_score":99.17317608622864,"expected_score":88.9744912187518,"reliability_score":93.42700872254836,"uncertainty_avg":6.57299127745163,"uncertainty_penalty":21.628146657791717}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:e2f72ed41374a73b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":2.642580625,"median":2.681945,"min":1.562975,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":21.140645},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.712055,"mean":0.49864374999999994,"median":0.5065824999999999,"min":0.29423750000000004,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":3.98915},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.15985749999999999,"mean":0.09356500000000001,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7485200000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.712055,"mean":0.49864374999999994,"median":0.5065824999999999,"min":0.29423750000000004,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":3.98915},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.15985749999999999,"mean":0.09356500000000001,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":8,"token_priced_attempt_count":10,"total":0.74852},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":2.642580625,"median":2.681945,"min":1.562975,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":21.140645}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":1.0782631249999999,"median":0.5065824999999999,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":28},"run_count":24,"token_priced_attempt_count":28,"total":25.878315},"codegen_latency_ms":{"attempt_count":28,"max_ms":1461887,"mean_ms":367273.6666666667,"min_ms":21601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1461887,"mean_ms":911419.875,"min_ms":461183,"run_count":8},"medium":{"attempt_count":9,"max_ms":292880,"mean_ms":161490.125,"min_ms":88006,"run_count":8},"none":{"attempt_count":10,"max_ms":50293,"mean_ms":28911.0,"min_ms":21601,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":218271,"output_mean":69498.70833333333,"output_min":3346,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":218271,"output_mean":172117.75,"output_min":103016,"run_count":8},"medium":{"attempt_count":9,"output_max":45034,"output_mean":31797.75,"output_min":18396,"run_count":8},"none":{"attempt_count":10,"output_max":7647,"output_mean":4580.625,"output_min":3346,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":56.905591925345966,"highest":72.00166756452465,"medium":47.969059392457204,"none":50.74604881905604},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":1667969},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"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,"repaired_admitted":1,"repaired_rate":0.125}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:12Z","match_totals_all":{"draws":633,"losses":473,"wins":1038},"match_totals_tracks":{"highest":{"draws":136,"losses":119,"wins":441},"medium":{"draws":235,"losses":200,"wins":305},"none":{"draws":262,"losses":154,"wins":292}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":56.905591925345966,"min":22.571342246704436},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":100.0,"GB2-02":57.21854400867016,"GB2-03":31.89608232157542,"GB2-04":58.01517252922639,"GB2-05":92.49362898125582,"GB2-06":100.0,"GB2-07":89.10077480456111,"GB2-08":47.28913787090833},"per_game_all":{"GB2-01":89.11434761895505,"GB2-02":34.358405890480526,"GB2-03":39.869509151229046,"GB2-04":41.52199157669525,"GB2-05":67.06867696350535,"GB2-06":89.30059012106234,"GB2-07":58.35412163308243,"GB2-08":35.65709244775774},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":27,"wins":220},"GB2-02":{"draws":196,"losses":21,"wins":27},"GB2-03":{"draws":85,"losses":65,"wins":66},"GB2-04":{"draws":168,"losses":45,"wins":69},"GB2-05":{"draws":0,"losses":101,"wins":199},"GB2-06":{"draws":27,"losses":34,"wins":185},"GB2-07":{"draws":0,"losses":98,"wins":186},"GB2-08":{"draws":136,"losses":82,"wins":86}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":5,"wins":89},"GB2-02":{"draws":49,"losses":9,"wins":22},"GB2-03":{"draws":17,"losses":24,"wins":17},"GB2-04":{"draws":34,"losses":24,"wins":36},"GB2-05":{"draws":0,"losses":8,"wins":84},"GB2-06":{"draws":10,"losses":7,"wins":65},"GB2-07":{"draws":0,"losses":11,"wins":85},"GB2-08":{"draws":26,"losses":31,"wins":43}},"medium":{"GB2-01":{"draws":19,"losses":16,"wins":47},"GB2-02":{"draws":68,"losses":8,"wins":4},"GB2-03":{"draws":36,"losses":24,"wins":18},"GB2-04":{"draws":65,"losses":13,"wins":22},"GB2-05":{"draws":0,"losses":68,"wins":50},"GB2-06":{"draws":9,"losses":5,"wins":68},"GB2-07":{"draws":0,"losses":35,"wins":65},"GB2-08":{"draws":38,"losses":31,"wins":31}},"none":{"GB2-01":{"draws":2,"losses":6,"wins":84},"GB2-02":{"draws":79,"losses":4,"wins":1},"GB2-03":{"draws":32,"losses":17,"wins":31},"GB2-04":{"draws":69,"losses":8,"wins":11},"GB2-05":{"draws":0,"losses":25,"wins":65},"GB2-06":{"draws":8,"losses":22,"wins":52},"GB2-07":{"draws":0,"losses":52,"wins":36},"GB2-08":{"draws":72,"losses":20,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1900.534571624891,"GB2-02":1519.7792866351062,"GB2-03":1497.1653291858238,"GB2-04":1544.8336065864278,"GB2-05":1761.7137618642585,"GB2-06":1835.3570790361016,"GB2-07":1626.4288486490325,"GB2-08":1504.2079181121728},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2000.7576930253301,"GB2-02":1620.5373124406053,"GB2-03":1449.7947632570085,"GB2-04":1635.5726584504935,"GB2-05":2032.5608459804337,"GB2-06":1935.9305085166034,"GB2-07":1934.857523033671,"GB2-08":1602.560257343934},"medium":{"GB2-01":1700.0514577525005,"GB2-02":1471.4974252789027,"GB2-03":1439.39286064408,"GB2-04":1509.4148214952497,"GB2-05":1475.0224962569089,"GB2-06":1892.891192538813,"GB2-07":1645.147005295843,"GB2-08":1459.2219261759235},"none":{"GB2-01":2000.7945640968424,"GB2-02":1467.3031221858107,"GB2-03":1602.3083636563829,"GB2-04":1489.5133398135404,"GB2-05":1777.5579433554326,"GB2-06":1677.2495360528883,"GB2-07":1299.2820176175837,"GB2-08":1450.841570816661}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-02":57.21854400867016,"GB2-03":31.89608232157542,"GB2-04":58.01517252922639,"GB2-05":92.49362898125582,"GB2-06":100.0,"GB2-07":89.10077480456111,"GB2-08":47.28913787090833},"medium":{"GB2-01":67.38623768514597,"GB2-02":23.285331416066995,"GB2-03":31.388151856713836,"GB2-04":35.31932420897261,"GB2-05":40.32822843528254,"GB2-06":95.42130277416098,"GB2-07":60.331355683982295,"GB2-08":30.292543079332418},"none":{"GB2-01":99.95680517171921,"GB2-02":22.571342246704436,"GB2-03":56.324293275397885,"GB2-04":31.231477991886752,"GB2-05":68.38417347397768,"GB2-06":72.48046758902608,"GB2-07":25.63023441070387,"GB2-08":29.38959639303247}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.00166756452465,"medium":47.969059392457204,"none":50.74604881905605},"reasoning_agg":{"highest":{"max":100.0,"mean":72.00166756452465,"min":31.89608232157542},"medium":{"max":95.42130277416098,"mean":47.969059392457204,"min":23.285331416066995},"none":{"max":99.95680517171921,"mean":50.74604881905605,"min":22.571342246704436}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"expected_score":57.51529215909712,"reasoning_variance":24.032608172067448,"reliability_score":90.7963182936154,"uncertainty_avg":9.2036817063846,"uncertainty_penalty":0.6097002337511555},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":68.11794011352328,"reliability_score":89.93790890587128,"uncertainty_avg":10.062091094128718,"uncertainty_penalty":-3.883727451001377},"medium":{"ceiling_score":95.42130277416098,"expected_score":48.06605122457438,"reliability_score":91.666910753193,"uncertainty_avg":8.333089246807006,"uncertainty_penalty":0.0969918321171761},"none":{"ceiling_score":99.95680517171921,"expected_score":56.36188513919368,"reliability_score":90.78413522178192,"uncertainty_avg":9.215864778218078,"uncertainty_penalty":5.615836320137632}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:2c7771c40a0c79dd","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":12.915325,"mean":10.059243749999998,"median":10.0094025,"min":8.401555,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":80.47395},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6689649999999999,"mean":0.46799875,"median":0.4352825,"min":0.36661499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":4.1199200000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.147405,"mean":0.12146437500000001,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6689649999999999,"mean":0.46799875,"median":0.4352825,"min":0.36661499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":4.11992},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.147405,"mean":0.12146437500000001,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":12.915325,"mean":10.059243749999998,"median":10.0094025,"min":8.401555,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":80.47395}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":12.915325,"mean":3.549568958333333,"median":0.4352825,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":27},"run_count":26,"token_priced_attempt_count":27,"total":85.663355},"codegen_latency_ms":{"attempt_count":27,"max_ms":422464,"mean_ms":160017.42307692306,"min_ms":18406,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":422464,"mean_ms":390133.625,"min_ms":351613,"run_count":8},"medium":{"attempt_count":10,"max_ms":132971,"mean_ms":90177.0,"min_ms":75382,"run_count":9},"none":{"attempt_count":9,"max_ms":34692,"mean_ms":25310.11111111111,"min_ms":18406,"run_count":9}},"codegen_output_tokens":{"attempt_count":27,"output_max":428840,"output_mean":108480.34615384616,"output_min":1810,"run_count":26},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":428840,"output_mean":334016.875,"output_min":278832,"run_count":8},"medium":{"attempt_count":10,"output_max":20628,"output_mean":13803.555555555555,"output_min":9542,"run_count":9},"none":{"attempt_count":9,"output_max":3573,"output_mean":2680.222222222222,"output_min":1810,"run_count":9}},"display_name":"GPT-5.6 Sol","economics":{"all":56.33535128463828,"highest":66.2642269283388,"medium":58.665774525975536,"none":44.076052399600464},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":51,"output_token_observations":27,"total_output_tokens":2820489},"generation_policy":{"generation_policy":"quality_generation_policy","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-5.6-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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.1111111111111111},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-08-05T05:17:02Z","match_totals_all":{"draws":422,"losses":616,"wins":1072},"match_totals_tracks":{"highest":{"draws":79,"losses":201,"wins":420},"medium":{"draws":154,"losses":180,"wins":380},"none":{"draws":189,"losses":235,"wins":272}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":55.341616697809656,"min":20.34202322749009},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":83.08829242248612,"GB2-02":100.0,"GB2-03":57.90485555225239,"GB2-04":61.74991968984401,"GB2-05":63.86653414034944,"GB2-06":84.20334702445369,"GB2-07":58.95884336983468,"GB2-08":20.34202322749009},"per_game_all":{"GB2-01":66.31637810152806,"GB2-02":58.74600353894508,"GB2-03":45.86736705635483,"GB2-04":45.19852810427412,"GB2-05":60.05622432277934,"GB2-06":71.4974757293251,"GB2-07":60.41936086156523,"GB2-08":42.58147256233439},"per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":88,"wins":184},"GB2-02":{"draws":109,"losses":31,"wins":92},"GB2-03":{"draws":61,"losses":66,"wins":79},"GB2-04":{"draws":190,"losses":18,"wins":74},"GB2-05":{"draws":0,"losses":109,"wins":179},"GB2-06":{"draws":18,"losses":96,"wins":160},"GB2-07":{"draws":0,"losses":105,"wins":175},"GB2-08":{"draws":32,"losses":103,"wins":129}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":23,"wins":77},"GB2-02":{"draws":15,"losses":11,"wins":60},"GB2-03":{"draws":7,"losses":26,"wins":35},"GB2-04":{"draws":42,"losses":6,"wins":46},"GB2-05":{"draws":0,"losses":33,"wins":59},"GB2-06":{"draws":3,"losses":23,"wins":58},"GB2-07":{"draws":0,"losses":29,"wins":63},"GB2-08":{"draws":12,"losses":50,"wins":22}},"medium":{"GB2-01":{"draws":1,"losses":37,"wins":60},"GB2-02":{"draws":38,"losses":11,"wins":27},"GB2-03":{"draws":13,"losses":16,"wins":29},"GB2-04":{"draws":85,"losses":6,"wins":15},"GB2-05":{"draws":0,"losses":37,"wins":61},"GB2-06":{"draws":12,"losses":16,"wins":64},"GB2-07":{"draws":0,"losses":38,"wins":60},"GB2-08":{"draws":5,"losses":19,"wins":64}},"none":{"GB2-01":{"draws":11,"losses":28,"wins":47},"GB2-02":{"draws":56,"losses":9,"wins":5},"GB2-03":{"draws":41,"losses":24,"wins":15},"GB2-04":{"draws":63,"losses":6,"wins":13},"GB2-05":{"draws":0,"losses":39,"wins":59},"GB2-06":{"draws":3,"losses":57,"wins":38},"GB2-07":{"draws":0,"losses":38,"wins":52},"GB2-08":{"draws":15,"losses":34,"wins":43}}},"per_game_raw_elo_all":{"GB2-01":1687.1498731720624,"GB2-02":1628.115037878468,"GB2-03":1537.5359326503592,"GB2-04":1565.19421362646,"GB2-05":1688.0132438554726,"GB2-06":1665.7923599185342,"GB2-07":1647.4329103362172,"GB2-08":1565.4787114124958},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1842.1038472104176,"GB2-02":1806.880102034298,"GB2-03":1616.3799977137346,"GB2-04":1656.1290756470048,"GB2-05":1729.2371283141379,"GB2-06":1786.9238690390182,"GB2-07":1633.041024252725,"GB2-08":1378.8902558829477},"medium":{"GB2-01":1664.1747525619378,"GB2-02":1582.2391207094831,"GB2-03":1545.0279839646837,"GB2-04":1530.4112566798308,"GB2-05":1672.1305254535307,"GB2-06":1792.977450720159,"GB2-07":1641.3171931289405,"GB2-08":1778.443049602078},"none":{"GB2-01":1555.171019743832,"GB2-02":1495.2258908916226,"GB2-03":1451.199816272659,"GB2-04":1509.0423085525442,"GB2-05":1662.6720777987493,"GB2-06":1417.4757599964255,"GB2-07":1667.940513626986,"GB2-08":1539.1028287524625}},"per_game_tracks":{"highest":{"GB2-01":83.08829242248612,"GB2-02":100.0,"GB2-03":57.90485555225239,"GB2-04":61.74991968984401,"GB2-05":63.86653414034944,"GB2-06":84.20334702445369,"GB2-07":58.95884336983468,"GB2-08":20.34202322749009},"medium":{"GB2-01":63.92984534569066,"GB2-02":48.239355196944736,"GB2-03":46.42280040640819,"GB2-04":39.33968507396859,"GB2-05":58.59740424093167,"GB2-06":85.05033494665588,"GB2-07":59.9101347289806,"GB2-08":67.83663626822397},"none":{"GB2-01":51.9309965364074,"GB2-02":27.998655419890518,"GB2-03":33.27444521040391,"GB2-04":34.50597954900976,"GB2-05":57.70473458705692,"GB2-06":45.23874521686571,"GB2-07":62.3891044858804,"GB2-08":39.5657581912891}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.26422692833881,"medium":56.96350162639645,"none":42.79712153869371},"reasoning_agg":{"highest":{"max":100.0,"mean":66.26422692833881,"min":20.34202322749009},"medium":{"max":85.05033494665588,"mean":56.96350162639645,"min":39.33968507396859},"none":{"max":62.3891044858804,"mean":42.79712153869371,"min":27.998655419890518}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"expected_score":58.32489453344921,"reasoning_variance":23.467105389645106,"reliability_score":90.36781452997255,"uncertainty_avg":9.632185470027448,"uncertainty_penalty":2.983277835639555},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":59.77419533052139,"reliability_score":90.37378390226223,"uncertainty_avg":9.626216097737764,"uncertainty_penalty":-6.490031597817428},"medium":{"ceiling_score":85.05033494665588,"expected_score":65.1846183328719,"reliability_score":90.4981601002206,"uncertainty_avg":9.501839899779393,"uncertainty_penalty":8.221116706475456},"none":{"ceiling_score":62.3891044858804,"expected_score":50.015869936954374,"reliability_score":90.23149958743481,"uncertainty_avg":9.768500412565187,"uncertainty_penalty":7.218748398260665}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:164e2eeded186d37","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449889999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628250000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"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-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449889999999999}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":25},"run_count":24,"token_priced_attempt_count":25,"total":10.456240000000001},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":52.85661491834983,"highest":67.09931744185045,"medium":43.39147302621686,"none":46.49013596853745},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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},"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},"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,"repaired_admitted":1,"repaired_rate":0.125}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-08-05T03:49:27Z","match_totals_all":{"draws":537,"losses":571,"wins":916},"match_totals_tracks":{"highest":{"draws":83,"losses":181,"wins":394},"medium":{"draws":297,"losses":203,"wins":258},"none":{"draws":157,"losses":187,"wins":264}},"model_slug":"claude-opus-4-8","overall":{"max":85.7032381321606,"mean":51.0838604570741,"min":20.525841154304743},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.63498693048245,"GB2-02":82.05347374902418,"GB2-04":55.68784123456057,"GB2-05":45.72757509137996,"GB2-06":85.7032381321606,"GB2-07":75.86448374979243,"GB2-08":67.02362320555288},"per_game_all":{"GB2-01":52.2119157493421,"GB2-02":41.780349291005216,"GB2-04":39.131772098892746,"GB2-05":42.58767454918476,"GB2-06":77.12791046317784,"GB2-07":63.915450657404186,"GB2-08":53.24123161944198},"per_game_match_totals_all":{"GB2-01":{"draws":51,"losses":99,"wins":130},"GB2-02":{"draws":172,"losses":15,"wins":49},"GB2-03":{"draws":38,"losses":15,"wins":11},"GB2-04":{"draws":182,"losses":44,"wins":54},"GB2-05":{"draws":0,"losses":172,"wins":160},"GB2-06":{"draws":12,"losses":67,"wins":179},"GB2-07":{"draws":0,"losses":90,"wins":192},"GB2-08":{"draws":82,"losses":69,"wins":141}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":14,"losses":36,"wins":52},"GB2-02":{"draws":32,"losses":5,"wins":45},"GB2-04":{"draws":35,"losses":17,"wins":40},"GB2-05":{"draws":0,"losses":63,"wins":53},"GB2-06":{"draws":2,"losses":16,"wins":62},"GB2-07":{"draws":0,"losses":21,"wins":69},"GB2-08":{"draws":0,"losses":23,"wins":73}},"medium":{"GB2-01":{"draws":17,"losses":39,"wins":38},"GB2-02":{"draws":72,"losses":5,"wins":1},"GB2-03":{"draws":38,"losses":15,"wins":11},"GB2-04":{"draws":87,"losses":12,"wins":5},"GB2-05":{"draws":0,"losses":55,"wins":65},"GB2-06":{"draws":1,"losses":22,"wins":67},"GB2-07":{"draws":0,"losses":34,"wins":66},"GB2-08":{"draws":82,"losses":21,"wins":5}},"none":{"GB2-01":{"draws":20,"losses":24,"wins":40},"GB2-02":{"draws":68,"losses":5,"wins":3},"GB2-04":{"draws":60,"losses":15,"wins":9},"GB2-05":{"draws":0,"losses":54,"wins":42},"GB2-06":{"draws":9,"losses":29,"wins":50},"GB2-07":{"draws":0,"losses":35,"wins":57},"GB2-08":{"draws":0,"losses":25,"wins":63}}},"per_game_raw_elo_all":{"GB2-01":1556.1808136161505,"GB2-02":1553.117093277622,"GB2-04":1531.8974776610646,"GB2-05":1500.2807707103377,"GB2-06":1719.954601591389,"GB2-07":1682.4067740169578,"GB2-08":1653.3971651091153},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.793115128391,"GB2-02":1729.077401945733,"GB2-04":1623.201730875163,"GB2-05":1532.5443530487862,"GB2-06":1802.081054869981,"GB2-07":1803.2582355928973,"GB2-08":1769.8005525842925},"medium":{"GB2-01":1492.718192054946,"GB2-02":1459.9363913520322,"GB2-03":1449.778133454939,"GB2-04":1481.537434054386,"GB2-05":1542.2837822150532,"GB2-06":1774.7289447776332,"GB2-07":1667.8017327798075,"GB2-08":1422.9709089457906},"none":{"GB2-01":1571.0311336651146,"GB2-02":1470.3374865351009,"GB2-04":1490.9532680536443,"GB2-05":1426.0141768671742,"GB2-06":1583.0538051265532,"GB2-07":1576.1603536781683,"GB2-08":1767.4200337972638}},"per_game_tracks":{"highest":{"GB2-01":57.63498693048245,"GB2-02":82.05347374902418,"GB2-04":55.68784123456057,"GB2-05":45.72757509137996,"GB2-06":85.7032381321606,"GB2-07":75.86448374979243,"GB2-08":67.02362320555288},"medium":{"GB2-01":45.419750227325316,"GB2-02":20.525841154304743,"GB2-03":32.26904479710366,"GB2-04":30.39355816481966,"GB2-05":46.70493564691155,"GB2-06":83.06075814643916,"GB2-07":62.58738719657233,"GB2-08":26.170508876258452},"none":{"GB2-01":53.58101009021854,"GB2-02":22.761732969686722,"GB2-04":31.313916897298004,"GB2-05":35.33051290926278,"GB2-06":62.619735110933746,"GB2-07":53.294481025847816,"GB2-08":66.52956277651462}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":64.89632675143649,"medium":43.39147302621685,"none":44.96378159356898},"reasoning_agg":{"highest":{"max":85.7032381321606,"mean":64.89632675143649,"min":45.72757509137996},"medium":{"max":83.06075814643916,"mean":43.39147302621685,"min":20.525841154304743},"none":{"max":66.52956277651462,"mean":44.96378159356898,"min":22.761732969686722}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":85.7032381321606,"expected_score":52.727459663640374,"reasoning_variance":21.50485372521964,"reliability_score":91.99386780318166,"uncertainty_avg":8.006132196818344,"uncertainty_penalty":1.6435992065662717},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.7032381321606,"expected_score":60.461828103919075,"reliability_score":92.18452847999772,"uncertainty_avg":7.8154715200022755,"uncertainty_penalty":-4.434498647517415},"medium":{"ceiling_score":83.06075814643916,"expected_score":40.48199653511266,"reliability_score":92.01529441815147,"uncertainty_avg":7.984705581848527,"uncertainty_penalty":-2.9094764911041935},"none":{"ceiling_score":66.52956277651462,"expected_score":53.01480435577711,"reliability_score":90.31282883814497,"uncertainty_avg":9.687171161855039,"uncertainty_penalty":8.051022762208127}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:b8f6c70d3173c941","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428549999999994},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"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-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885474999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566349999999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":50.91270382636398,"highest":67.14610422168701,"medium":50.61580565140894,"none":37.374699430120664},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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},"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}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:23:57Z","match_totals_all":{"draws":721,"losses":545,"wins":822},"match_totals_tracks":{"highest":{"draws":124,"losses":144,"wins":368},"medium":{"draws":253,"losses":222,"wins":299},"none":{"draws":344,"losses":179,"wins":155}},"model_slug":"gpt-5-5","overall":{"max":94.05837364506577,"mean":50.568334747025915,"min":15.142060466906322},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.2539994315327,"GB2-03":45.35305938673562,"GB2-04":15.142060466906322,"GB2-05":81.36228215819001,"GB2-06":94.05837364506577,"GB2-07":92.05790847852163,"GB2-08":68.79504598485697},"per_game_all":{"GB2-01":60.54152698073648,"GB2-03":36.785819230698856,"GB2-04":26.00400279583101,"GB2-05":64.32554767139082,"GB2-07":69.56328799174737,"GB2-08":48.25603828777935},"per_game_match_totals_all":{"GB2-01":{"draws":180,"losses":49,"wins":91},"GB2-02":{"draws":116,"losses":18,"wins":20},"GB2-03":{"draws":101,"losses":79,"wins":54},"GB2-04":{"draws":172,"losses":68,"wins":40},"GB2-05":{"draws":0,"losses":88,"wins":194},"GB2-06":{"draws":5,"losses":88,"wins":109},"GB2-07":{"draws":0,"losses":88,"wins":210},"GB2-08":{"draws":147,"losses":67,"wins":104}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":16,"wins":51},"GB2-03":{"draws":30,"losses":29,"wins":21},"GB2-04":{"draws":45,"losses":33,"wins":6},"GB2-05":{"draws":0,"losses":20,"wins":76},"GB2-06":{"draws":4,"losses":16,"wins":62},"GB2-07":{"draws":0,"losses":6,"wins":90},"GB2-08":{"draws":16,"losses":24,"wins":62}},"medium":{"GB2-01":{"draws":61,"losses":14,"wins":29},"GB2-02":{"draws":43,"losses":9,"wins":20},"GB2-03":{"draws":35,"losses":24,"wins":15},"GB2-04":{"draws":63,"losses":17,"wins":22},"GB2-05":{"draws":0,"losses":30,"wins":66},"GB2-06":{"draws":1,"losses":72,"wins":47},"GB2-07":{"draws":0,"losses":32,"wins":62},"GB2-08":{"draws":50,"losses":24,"wins":38}},"none":{"GB2-01":{"draws":90,"losses":19,"wins":11},"GB2-02":{"draws":73,"losses":9,"wins":0},"GB2-03":{"draws":36,"losses":26,"wins":18},"GB2-04":{"draws":64,"losses":18,"wins":12},"GB2-05":{"draws":0,"losses":38,"wins":52},"GB2-07":{"draws":0,"losses":50,"wins":58},"GB2-08":{"draws":81,"losses":19,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1631.105528815463,"GB2-03":1474.8006236042627,"GB2-04":1459.620350486796,"GB2-05":1733.6756528173428,"GB2-07":1738.0398640192154,"GB2-08":1609.6056545618994},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.3774293727092,"GB2-03":1530.3839322567405,"GB2-04":1401.941773211182,"GB2-05":1913.7523653539108,"GB2-06":1880.0797890873182,"GB2-07":1964.5526124609985,"GB2-08":1783.5389156654253},"medium":{"GB2-01":1626.375137598157,"GB2-02":1580.4346988559294,"GB2-03":1440.3708349548044,"GB2-04":1486.0440995567778,"GB2-05":1733.9891021907006,"GB2-06":1493.0993164354797,"GB2-07":1732.0611905000076,"GB2-08":1605.807541988619},"none":{"GB2-01":1515.5640194755229,"GB2-02":1477.8084557546495,"GB2-03":1453.647103601243,"GB2-04":1490.875178692428,"GB2-05":1553.2854909074172,"GB2-07":1517.5057890966405,"GB2-08":1439.4705060316537}},"per_game_tracks":{"highest":{"GB2-01":73.2539994315327,"GB2-03":45.35305938673562,"GB2-04":15.142060466906322,"GB2-05":81.36228215819001,"GB2-06":94.05837364506577,"GB2-07":92.05790847852163,"GB2-08":68.79504598485697},"medium":{"GB2-01":59.9941304808233,"GB2-02":47.54797454033727,"GB2-03":31.35664793074286,"GB2-04":31.14381674077765,"GB2-05":64.39657956468047,"GB2-06":53.69217513632242,"GB2-07":68.86330432028504,"GB2-08":47.93181649730258},"none":{"GB2-01":48.376451029853435,"GB2-02":24.844878577648164,"GB2-03":33.64775037461809,"GB2-04":31.726131179809055,"GB2-05":47.21778129130201,"GB2-07":47.768651176435434,"GB2-08":28.041252381178502}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":64.94157743754894,"medium":50.615805651408955,"none":36.147621152119854},"reasoning_agg":{"highest":{"max":94.05837364506577,"mean":64.94157743754894,"min":15.142060466906322},"medium":{"max":68.86330432028504,"mean":50.615805651408955,"min":31.14381674077765},"none":{"max":48.376451029853435,"mean":36.147621152119854,"min":24.844878577648164}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":94.05837364506577,"expected_score":51.464882779197104,"reasoning_variance":28.79395628542909,"reliability_score":92.76861662210342,"uncertainty_avg":7.231383377896577,"uncertainty_penalty":0.8965480321711894},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":94.05837364506577,"expected_score":62.11039821935536,"reliability_score":91.43018733095396,"uncertainty_avg":8.56981266904604,"uncertainty_penalty":-2.831179218193583},"medium":{"ceiling_score":68.86330432028504,"expected_score":51.58622956746797,"reliability_score":92.64076464908335,"uncertainty_avg":7.359235350916645,"uncertainty_penalty":0.970423916059012},"none":{"ceiling_score":48.376451029853435,"expected_score":40.11088132112258,"reliability_score":92.851184520888,"uncertainty_avg":7.148815479112007,"uncertainty_penalty":3.963260169002723}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:eac4d255581f5932","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947035999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998543999999995},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":46.63852829188297,"highest":47.00578335780231,"medium":53.491845423282335,"none":39.417956094564275},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"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,"repaired_admitted":2,"repaired_rate":0.25}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:42:30Z","match_totals_all":{"draws":497,"losses":594,"wins":911},"match_totals_tracks":{"highest":{"draws":123,"losses":183,"wins":296},"medium":{"draws":192,"losses":247,"wins":395},"none":{"draws":182,"losses":164,"wins":220}},"model_slug":"x-ai-grok-4-5","overall":{"max":80.48164573606203,"mean":46.63852829188297,"min":6.748867164434723},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":66.90936602956313,"GB2-02":36.83057284966336,"GB2-03":29.960074596473827,"GB2-04":17.698293904601133,"GB2-05":49.08738584494886,"GB2-06":54.40923463191768,"GB2-07":54.20659865554057,"GB2-08":66.94474034970983},"per_game_all":{"GB2-01":64.96054400856177,"GB2-02":26.941540913371494,"GB2-03":25.990328321186805,"GB2-04":25.04322717312451,"GB2-05":49.05925698469563,"GB2-06":52.64619222265302,"GB2-07":58.35995128865022,"GB2-08":70.10718542282028},"per_game_match_totals_all":{"GB2-01":{"draws":101,"losses":45,"wins":150},"GB2-02":{"draws":138,"losses":40,"wins":36},"GB2-03":{"draws":76,"losses":101,"wins":43},"GB2-04":{"draws":157,"losses":50,"wins":31},"GB2-05":{"draws":0,"losses":101,"wins":133},"GB2-06":{"draws":23,"losses":124,"wins":133},"GB2-07":{"draws":0,"losses":90,"wins":154},"GB2-08":{"draws":2,"losses":43,"wins":231}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":14,"losses":10,"wins":56},"GB2-02":{"draws":34,"losses":19,"wins":21},"GB2-03":{"draws":31,"losses":23,"wins":14},"GB2-04":{"draws":37,"losses":27,"wins":12},"GB2-05":{"draws":0,"losses":20,"wins":30},"GB2-06":{"draws":6,"losses":39,"wins":45},"GB2-07":{"draws":0,"losses":31,"wins":45},"GB2-08":{"draws":1,"losses":14,"wins":73}},"medium":{"GB2-01":{"draws":8,"losses":21,"wins":73},"GB2-02":{"draws":67,"losses":16,"wins":13},"GB2-03":{"draws":28,"losses":26,"wins":24},"GB2-04":{"draws":80,"losses":16,"wins":12},"GB2-05":{"draws":0,"losses":46,"wins":70},"GB2-06":{"draws":8,"losses":61,"wins":51},"GB2-07":{"draws":0,"losses":47,"wins":65},"GB2-08":{"draws":1,"losses":14,"wins":87}},"none":{"GB2-01":{"draws":79,"losses":14,"wins":21},"GB2-02":{"draws":37,"losses":5,"wins":2},"GB2-03":{"draws":17,"losses":52,"wins":5},"GB2-04":{"draws":40,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":35,"wins":33},"GB2-06":{"draws":9,"losses":24,"wins":37},"GB2-07":{"draws":0,"losses":12,"wins":44},"GB2-08":{"draws":0,"losses":15,"wins":71}}},"per_game_raw_elo_all":{"GB2-01":1685.3528989351114,"GB2-02":1514.2941541882064,"GB2-03":1418.221604992548,"GB2-04":1472.404909929919,"GB2-05":1594.7019012480387,"GB2-06":1501.2334260849987,"GB2-07":1645.1429664094296,"GB2-08":1808.6906949557285},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1714.4010124412612,"GB2-02":1551.8610091385813,"GB2-03":1452.6395980970199,"GB2-04":1436.7399927678175,"GB2-05":1613.477136059127,"GB2-06":1522.4632087444165,"GB2-07":1608.4714041645075,"GB2-08":1788.3276397387067},"medium":{"GB2-01":1799.055667309865,"GB2-02":1499.1232344259092,"GB2-03":1504.1234121905509,"GB2-04":1488.922495957919,"GB2-05":1662.7933410041032,"GB2-06":1442.0865376108627,"GB2-07":1630.4735516007104,"GB2-08":1882.0961693922998},"none":{"GB2-01":1542.6020170542076,"GB2-02":1491.8982190001293,"GB2-03":1297.9018046900726,"GB2-04":1491.55224106402,"GB2-05":1507.8352266808859,"GB2-06":1539.1505318997167,"GB2-07":1696.4839434630712,"GB2-08":1755.6482757361791}},"per_game_tracks":{"highest":{"GB2-01":66.90936602956313,"GB2-02":36.83057284966336,"GB2-03":29.960074596473827,"GB2-04":17.698293904601133,"GB2-05":49.08738584494886,"GB2-06":54.40923463191768,"GB2-07":54.20659865554057,"GB2-08":66.94474034970983},"medium":{"GB2-01":78.50521178364832,"GB2-02":30.44728628591251,"GB2-03":41.26204320265185,"GB2-04":31.866644636143132,"GB2-05":58.02021794771947,"GB2-06":48.2652285508529,"GB2-07":59.08648524326837,"GB2-08":80.48164573606203},"none":{"GB2-01":49.46705421247383,"GB2-02":13.54676360453859,"GB2-03":6.748867164434723,"GB2-04":25.564742978629265,"GB2-05":40.07016716141857,"GB2-06":55.264113485188496,"GB2-07":61.78676996714175,"GB2-08":62.895170182688986}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.0057833578023,"medium":53.49184542328232,"none":39.417956094564275},"reasoning_agg":{"highest":{"max":66.94474034970983,"mean":47.0057833578023,"min":17.698293904601133},"medium":{"max":80.48164573606203,"mean":53.49184542328232,"min":30.44728628591251},"none":{"max":62.895170182688986,"mean":39.417956094564275,"min":6.748867164434723}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":80.48164573606203,"expected_score":47.74609342919673,"reasoning_variance":14.073889328718046,"reliability_score":70.8175441254784,"uncertainty_avg":29.1824558745216,"uncertainty_penalty":1.1075651373137632},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.94474034970983,"expected_score":39.461260482920665,"reliability_score":61.64489723873858,"uncertainty_avg":38.35510276126142,"uncertainty_penalty":-7.544522874881636},"medium":{"ceiling_score":80.48164573606203,"expected_score":54.40092627555066,"reliability_score":94.7298061742129,"uncertainty_avg":5.270193825787098,"uncertainty_penalty":0.9090808522683389},"none":{"ceiling_score":62.895170182688986,"expected_score":49.37609352911886,"reliability_score":56.077928963483714,"uncertainty_avg":43.922071036516286,"uncertainty_penalty":9.958137434554587}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:3e7c051458a7cbef","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":12.137519999999999,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":65.32801249999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.24673750000000003,"mean":0.16744,"median":0.15809499999999999,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":1.3395199999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063375}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.24673750000000003,"mean":0.16744,"median":0.15809499999999999,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":1.3395199999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063374999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":12.137519999999999,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":65.3280125}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":32},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":12.137519999999999,"mean":2.8005991666666663,"median":0.15809499999999999,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":32},"run_count":25,"token_priced_attempt_count":32,"total":67.27386999999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":309143,"mean_ms":97936.92,"min_ms":13711,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":309143,"mean_ms":245541.25,"min_ms":194014,"run_count":8},"medium":{"attempt_count":11,"max_ms":70195,"mean_ms":41737.375,"min_ms":27719,"run_count":8},"none":{"attempt_count":10,"max_ms":27196,"mean_ms":16688.222222222223,"min_ms":13711,"run_count":9}},"codegen_output_tokens":{"attempt_count":32,"output_max":806490,"output_mean":177703.68,"output_min":2382,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":806490,"output_mean":542498.625,"output_min":312998,"run_count":8},"medium":{"attempt_count":11,"output_max":13756,"output_mean":9389.25,"output_min":6044,"run_count":8},"none":{"attempt_count":10,"output_max":5458,"output_mean":3054.3333333333335,"output_min":2382,"run_count":9}},"display_name":"GPT-5.6 Terra","economics":{"all":45.64716886591871,"highest":55.51299956858801,"medium":40.62132498586859,"none":40.807182043299505},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":32,"total_output_tokens":4442592},"generation_policy":{"generation_policy":"quality_generation_policy","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-5.6-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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.1111111111111111},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-08-05T05:18:32Z","match_totals_all":{"draws":737,"losses":721,"wins":784},"match_totals_tracks":{"highest":{"draws":152,"losses":231,"wins":325},"medium":{"draws":287,"losses":250,"wins":247},"none":{"draws":298,"losses":240,"wins":212}},"model_slug":"gpt-5-6-terra","overall":{"max":78.97727049438612,"mean":45.25247559054204,"min":24.606530359301495},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.88844588724325,"GB2-02":48.40569833085461,"GB2-03":52.47594525860797,"GB2-04":44.4786439895316,"GB2-05":56.425112707893895,"GB2-06":78.97727049438612,"GB2-07":71.72102167529864,"GB2-08":48.731858204888034},"per_game_all":{"GB2-01":47.38322276425541,"GB2-02":35.4618809395776,"GB2-03":45.08991001504496,"GB2-04":39.249391937557824,"GB2-05":52.7765721451986,"GB2-06":60.034099744815386,"GB2-07":49.53866811603564,"GB2-08":35.64360526486425},"per_game_match_totals_all":{"GB2-01":{"draws":95,"losses":104,"wins":91},"GB2-02":{"draws":212,"losses":38,"wins":20},"GB2-03":{"draws":89,"losses":64,"wins":61},"GB2-04":{"draws":187,"losses":33,"wins":52},"GB2-05":{"draws":0,"losses":121,"wins":169},"GB2-06":{"draws":14,"losses":126,"wins":150},"GB2-07":{"draws":0,"losses":146,"wins":166},"GB2-08":{"draws":140,"losses":89,"wins":75}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":31,"losses":40,"wins":29},"GB2-02":{"draws":50,"losses":20,"wins":16},"GB2-03":{"draws":15,"losses":16,"wins":27},"GB2-04":{"draws":41,"losses":18,"wins":31},"GB2-05":{"draws":0,"losses":42,"wins":52},"GB2-06":{"draws":0,"losses":34,"wins":56},"GB2-07":{"draws":0,"losses":29,"wins":63},"GB2-08":{"draws":15,"losses":32,"wins":51}},"medium":{"GB2-01":{"draws":34,"losses":29,"wins":33},"GB2-02":{"draws":75,"losses":9,"wins":0},"GB2-03":{"draws":39,"losses":25,"wins":14},"GB2-04":{"draws":74,"losses":9,"wins":13},"GB2-05":{"draws":0,"losses":44,"wins":64},"GB2-06":{"draws":12,"losses":41,"wins":47},"GB2-07":{"draws":0,"losses":59,"wins":55},"GB2-08":{"draws":53,"losses":34,"wins":21}},"none":{"GB2-01":{"draws":30,"losses":35,"wins":29},"GB2-02":{"draws":87,"losses":9,"wins":4},"GB2-03":{"draws":35,"losses":23,"wins":20},"GB2-04":{"draws":72,"losses":6,"wins":8},"GB2-05":{"draws":0,"losses":35,"wins":53},"GB2-06":{"draws":2,"losses":51,"wins":47},"GB2-07":{"draws":0,"losses":58,"wins":48},"GB2-08":{"draws":72,"losses":23,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1510.4401182404865,"GB2-02":1522.55828542164,"GB2-03":1531.575217448187,"GB2-04":1533.0547286008903,"GB2-05":1610.837335302126,"GB2-06":1556.8606210252492,"GB2-07":1536.1162201771901,"GB2-08":1504.1198753984509},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1467.9188616540573,"GB2-02":1580.2699961396245,"GB2-03":1584.7107585816805,"GB2-04":1561.9585279553617,"GB2-05":1649.9512272105483,"GB2-06":1736.344551427424,"GB2-07":1761.1968899835726,"GB2-08":1615.127256233949},"medium":{"GB2-01":1507.6320452094085,"GB2-02":1484.6607459565766,"GB2-03":1484.2886571135925,"GB2-04":1514.0428742199645,"GB2-05":1604.4100113362138,"GB2-06":1507.497978964082,"GB2-07":1401.2822756940366,"GB2-08":1485.5625871021477},"none":{"GB2-01":1555.7694478579945,"GB2-02":1502.7441141687189,"GB2-03":1525.7262366492885,"GB2-04":1523.1627836273447,"GB2-05":1578.1507673596157,"GB2-06":1426.7393326842414,"GB2-07":1445.8694948539608,"GB2-08":1411.6697828592557}},"per_game_tracks":{"highest":{"GB2-01":42.88844588724325,"GB2-02":48.40569833085461,"GB2-03":52.47594525860797,"GB2-04":44.4786439895316,"GB2-05":56.425112707893895,"GB2-06":78.97727049438612,"GB2-07":71.72102167529864,"GB2-08":48.731858204888034},"medium":{"GB2-01":47.06768139295753,"GB2-02":26.523304025075756,"GB2-03":38.23648244618929,"GB2-04":36.01257007858806,"GB2-05":52.384304794269354,"GB2-06":54.85823075496087,"GB2-07":36.2955991645047,"GB2-08":33.5924272304032},"none":{"GB2-01":52.193541012565454,"GB2-02":31.456640462802426,"GB2-03":44.55730234033761,"GB2-04":37.25696174455382,"GB2-05":49.52029893343254,"GB2-06":46.266797985099174,"GB2-07":40.59938350830355,"GB2-08":24.606530359301495}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.51299956858802,"medium":40.6213249858686,"none":39.6231022171695},"reasoning_agg":{"highest":{"max":78.97727049438612,"mean":55.51299956858802,"min":42.88844588724325},"medium":{"max":54.85823075496087,"mean":40.6213249858686,"min":26.523304025075756},"none":{"max":52.193541012565454,"mean":39.6231022171695,"min":24.606530359301495}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":78.97727049438612,"expected_score":43.90605035880376,"reasoning_variance":15.889897351418519,"reliability_score":91.95368997472086,"uncertainty_avg":8.046310025279139,"uncertainty_penalty":-1.34642523173828},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.97727049438612,"expected_score":46.86128736570228,"reliability_score":90.41514768515843,"uncertainty_avg":9.584852314841568,"uncertainty_penalty":-8.65171220288574},"medium":{"ceiling_score":54.85823075496087,"expected_score":39.12329531467304,"reliability_score":93.22733069263032,"uncertainty_avg":6.772669307369679,"uncertainty_penalty":-1.4980296711955603},"none":{"ceiling_score":52.193541012565454,"expected_score":45.73356839603595,"reliability_score":92.21859154637383,"uncertainty_avg":7.78140845362617,"uncertainty_penalty":6.110466178866446}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:c02c4e37bd6ab352","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.6379623500000005},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.169687700000001},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000001},"historical-provider-setting-intensive-variant-1":{"admitted_cell_count":4,"cell_count":3,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.729738,"mean":0.551419875,"median":0.531673125,"min":0.39284850000000004,"recorded_attempt_count":16,"run_count":4,"total":2.18593275},"historical-provider-setting-intensive-variant-2":{"admitted_cell_count":8,"cell_count":7,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.6549207,"mean":0.4590043071428571,"median":0.4757886,"min":0.31911,"recorded_attempt_count":37,"run_count":12,"total":5.4520296}},"codegen_cost_usd":{"admitted_cell_count":42,"cell_count":24,"cost_basis_counts":{"provider_reported":126},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.531673125,"mean":0.264606278125,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":126,"run_count":48,"total":12.701101349999997},"codegen_latency_ms":{"attempt_count":122,"max_ms":348942,"mean_ms":136127.20833333334,"min_ms":17298,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":49,"max_ms":348942,"mean_ms":238985.4375,"min_ms":149523,"run_count":16},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":126,"output_max":100087,"output_mean":32301.520833333332,"output_min":2060,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":100087,"output_mean":61701.5625,"output_min":36597,"run_count":16},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":47.73845222346885,"highest":47.06945590526891,"medium":53.090232750620466,"none":36.12279181493238},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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},"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,"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":12,"failed_game_aliases":["GB2-02","GB2-03","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.3333333333333333,"model_code_failure_rate":0.3333333333333333,"model_code_failures":4,"repaired_admitted":4,"repaired_rate":0.3333333333333333}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:12Z","match_totals_all":{"draws":925,"losses":800,"wins":1237},"match_totals_tracks":{"highest":{"draws":146,"losses":224,"wins":385},"medium":{"draws":306,"losses":232,"wins":516},"none":{"draws":473,"losses":344,"wins":336}},"model_slug":"google-gemini-3-6-flash","overall":{"max":91.70201059215609,"mean":43.3340106215883,"min":18.71384108753165},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.77809618811668,"GB2-03":44.72105372304396,"GB2-04":35.0157186034202,"GB2-05":51.59820019792202,"GB2-06":74.49579059518622,"GB2-07":46.508716072525516,"GB2-08":34.36861595666778},"per_game_all":{"GB2-01":50.41443060165969,"GB2-03":40.96701089870093,"GB2-04":30.46535134203296,"GB2-05":56.53501278089997,"GB2-06":69.29535948025757,"GB2-07":49.273072645932565,"GB2-08":37.218927814798285},"per_game_match_totals_all":{"GB2-01":{"draws":144,"losses":134,"wins":202},"GB2-02":{"draws":195,"losses":10,"wins":1},"GB2-03":{"draws":83,"losses":83,"wins":105},"GB2-04":{"draws":279,"losses":77,"wins":91},"GB2-05":{"draws":0,"losses":124,"wins":268},"GB2-06":{"draws":37,"losses":115,"wins":267},"GB2-07":{"draws":0,"losses":175,"wins":220},"GB2-08":{"draws":187,"losses":82,"wins":83}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":49,"losses":49,"wins":48},"GB2-03":{"draws":4,"losses":9,"wins":21},"GB2-04":{"draws":40,"losses":46,"wins":56},"GB2-05":{"draws":0,"losses":25,"wins":71},"GB2-06":{"draws":8,"losses":25,"wins":103},"GB2-07":{"draws":0,"losses":32,"wins":37},"GB2-08":{"draws":45,"losses":38,"wins":49}},"medium":{"GB2-01":{"draws":43,"losses":20,"wins":101},"GB2-02":{"draws":80,"losses":5,"wins":1},"GB2-03":{"draws":27,"losses":36,"wins":32},"GB2-04":{"draws":137,"losses":19,"wins":25},"GB2-05":{"draws":0,"losses":39,"wins":105},"GB2-06":{"draws":10,"losses":11,"wins":111},"GB2-07":{"draws":0,"losses":85,"wins":111},"GB2-08":{"draws":9,"losses":17,"wins":30}},"none":{"GB2-01":{"draws":52,"losses":65,"wins":53},"GB2-02":{"draws":115,"losses":5,"wins":0},"GB2-03":{"draws":52,"losses":38,"wins":52},"GB2-04":{"draws":102,"losses":12,"wins":10},"GB2-05":{"draws":0,"losses":60,"wins":92},"GB2-06":{"draws":19,"losses":79,"wins":53},"GB2-07":{"draws":0,"losses":58,"wins":72},"GB2-08":{"draws":133,"losses":27,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1557.2446183467816,"GB2-03":1533.488931725624,"GB2-04":1504.118587585807,"GB2-05":1675.55609189145,"GB2-06":1664.6832262267283,"GB2-07":1555.687691768527,"GB2-08":1541.279390802539},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1499.2480909757069,"GB2-03":1586.952914842092,"GB2-04":1535.1898264095873,"GB2-05":1640.777615993166,"GB2-06":1721.3048744665289,"GB2-07":1537.1110560655984,"GB2-08":1529.3131028207222},"medium":{"GB2-01":1748.1942513938784,"GB2-02":1464.156172217111,"GB2-03":1474.4996298826736,"GB2-04":1482.8442918018895,"GB2-05":1798.5063962519441,"GB2-06":1862.8922755189858,"GB2-07":1564.44883752229,"GB2-08":1654.1866708150255},"none":{"GB2-01":1424.2915126707596,"GB2-02":1478.9288912413258,"GB2-03":1539.0142504521068,"GB2-04":1494.3216445459439,"GB2-05":1587.384263429241,"GB2-06":1409.8525286946704,"GB2-07":1565.5031817176923,"GB2-08":1440.3383987718696}},"per_game_tracks":{"highest":{"GB2-01":42.77809618811668,"GB2-03":44.72105372304396,"GB2-04":35.0157186034202,"GB2-05":51.59820019792202,"GB2-06":74.49579059518622,"GB2-07":46.508716072525516,"GB2-08":34.36861595666778},"medium":{"GB2-01":72.5069715162629,"GB2-02":21.969050080927598,"GB2-03":34.83800371361828,"GB2-04":29.85012509642266,"GB2-05":69.90020433563501,"GB2-06":91.70201059215609,"GB2-07":52.107484759458345,"GB2-08":51.848011910482846},"none":{"GB2-01":35.95822410059949,"GB2-02":18.71384108753165,"GB2-03":43.34197525944053,"GB2-04":26.53021032625603,"GB2-05":48.10663380914288,"GB2-06":41.68827725343043,"GB2-07":49.20301710581384,"GB2-08":25.440155577244205}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.53205466482623,"medium":51.347185385006284,"none":36.12279181493238},"reasoning_agg":{"highest":{"max":74.49579059518622,"mean":42.53205466482623,"min":34.36861595666778},"medium":{"max":91.70201059215609,"mean":51.347185385006284,"min":21.969050080927598},"none":{"max":49.20301710581384,"mean":36.12279181493238,"min":18.71384108753165}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":91.70201059215609,"expected_score":50.27290419452631,"reasoning_variance":15.224393570073907,"reliability_score":64.26128339074869,"uncertainty_avg":35.73871660925131,"uncertainty_penalty":6.938893572938014},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.49579059518622,"expected_score":41.5887160478382,"reliability_score":48.48023013122151,"uncertainty_avg":51.51976986877849,"uncertainty_penalty":-0.9433386169880293},"medium":{"ceiling_score":91.70201059215609,"expected_score":54.36795200008303,"reliability_score":84.61745659176809,"uncertainty_avg":15.382543408231916,"uncertainty_penalty":3.020766615076745},"none":{"ceiling_score":49.20301710581384,"expected_score":43.69587721160113,"reliability_score":59.64210153474375,"uncertainty_avg":40.35789846525625,"uncertainty_penalty":7.573085396668752}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:a93d7b20a8cd643a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.43048093750000005,"median":0.4308725,"min":0.32672249999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-07-30":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887694999999999},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"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-2026-07-30":8},"run_count":16,"token_priced_attempt_count":16,"total":3.34216},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"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":1.4245200000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709265},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":17},"run_count":16,"token_priced_attempt_count":17,"total":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"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-2026-07-30":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785},"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":42.03361346295354,"highest":33.234360450130474,"medium":45.72055502526362,"none":47.14592491346651},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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},"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},"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}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:15Z","match_totals_all":{"draws":615,"losses":685,"wins":775},"match_totals_tracks":{"highest":{"draws":153,"losses":249,"wins":198},"medium":{"draws":195,"losses":223,"wins":295},"none":{"draws":267,"losses":213,"wins":282}},"model_slug":"claude-opus-4-5","overall":{"max":69.00313139343699,"mean":42.03361346295353,"min":7.670088947709001},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":53.00989881361929,"GB2-02":11.233180622648142,"GB2-03":26.677879816109012,"GB2-04":7.670088947709001,"GB2-05":42.773354886116735,"GB2-06":55.38133319989706,"GB2-07":44.28793172321607,"GB2-08":24.841215591728457},"per_game_all":{"GB2-01":52.345875375333755,"GB2-02":22.758176673826465,"GB2-03":33.798817819279265,"GB2-04":26.862226711825667,"GB2-05":45.189341785339,"GB2-06":55.3216014247912,"GB2-07":45.99168444177662,"GB2-08":54.00118347145631},"per_game_match_totals_all":{"GB2-01":{"draws":106,"losses":59,"wins":93},"GB2-02":{"draws":171,"losses":31,"wins":8},"GB2-03":{"draws":108,"losses":64,"wins":38},"GB2-04":{"draws":153,"losses":67,"wins":31},"GB2-05":{"draws":0,"losses":132,"wins":182},"GB2-06":{"draws":22,"losses":119,"wins":137},"GB2-07":{"draws":0,"losses":142,"wins":146},"GB2-08":{"draws":55,"losses":71,"wins":140}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":13,"wins":36},"GB2-02":{"draws":43,"losses":16,"wins":1},"GB2-03":{"draws":14,"losses":27,"wins":13},"GB2-04":{"draws":29,"losses":37,"wins":6},"GB2-05":{"draws":0,"losses":48,"wins":56},"GB2-06":{"draws":8,"losses":37,"wins":37},"GB2-07":{"draws":0,"losses":36,"wins":40},"GB2-08":{"draws":50,"losses":35,"wins":9}},"medium":{"GB2-01":{"draws":21,"losses":21,"wins":42},"GB2-02":{"draws":54,"losses":4,"wins":2},"GB2-03":{"draws":34,"losses":22,"wins":12},"GB2-04":{"draws":76,"losses":16,"wins":11},"GB2-05":{"draws":0,"losses":46,"wins":60},"GB2-06":{"draws":9,"losses":42,"wins":53},"GB2-07":{"draws":0,"losses":55,"wins":49},"GB2-08":{"draws":1,"losses":17,"wins":66}},"none":{"GB2-01":{"draws":76,"losses":25,"wins":15},"GB2-02":{"draws":74,"losses":11,"wins":5},"GB2-03":{"draws":60,"losses":15,"wins":13},"GB2-04":{"draws":48,"losses":14,"wins":14},"GB2-05":{"draws":0,"losses":38,"wins":66},"GB2-06":{"draws":5,"losses":40,"wins":47},"GB2-07":{"draws":0,"losses":51,"wins":57},"GB2-08":{"draws":4,"losses":19,"wins":65}}},"per_game_raw_elo_all":{"GB2-01":1569.2725748386256,"GB2-02":1479.7337249039385,"GB2-03":1465.6847885990117,"GB2-04":1473.3505478097702,"GB2-05":1534.0877415665946,"GB2-06":1520.2591756117872,"GB2-07":1509.2969309514374,"GB2-08":1667.2324544403489},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1601.3359090209483,"GB2-02":1445.9602022628883,"GB2-03":1439.4311400458312,"GB2-04":1383.47949608107,"GB2-05":1519.235945481571,"GB2-06":1536.720666438107,"GB2-07":1510.7354986238543,"GB2-08":1431.2672956941567},"medium":{"GB2-01":1645.6640036153567,"GB2-02":1499.262611968492,"GB2-03":1438.7975158584218,"GB2-04":1483.6856058732603,"GB2-05":1490.8078638278364,"GB2-06":1549.8531936911686,"GB2-07":1484.9594600967189,"GB2-08":1789.2666943887314},"none":{"GB2-01":1460.8178118795715,"GB2-02":1493.9783604804352,"GB2-03":1518.8257098927816,"GB2-04":1552.8865414749796,"GB2-05":1592.219415390376,"GB2-06":1474.2036667060856,"GB2-07":1532.1958341337388,"GB2-08":1781.1633732381583}},"per_game_tracks":{"highest":{"GB2-01":53.00989881361929,"GB2-02":11.233180622648142,"GB2-03":26.677879816109012,"GB2-04":7.670088947709001,"GB2-05":42.773354886116735,"GB2-06":55.38133319989706,"GB2-07":44.28793172321607,"GB2-08":24.841215591728457},"medium":{"GB2-01":61.59904938707476,"GB2-02":28.065418891234213,"GB2-03":30.81671727920589,"GB2-04":30.749828609175978,"GB2-05":41.629120841132384,"GB2-06":59.445585881637015,"GB2-07":44.455587919211716,"GB2-08":69.00313139343699},"none":{"GB2-01":42.428677925307234,"GB2-02":28.975930507597035,"GB2-03":43.90185636252289,"GB2-04":42.16676257859201,"GB2-05":51.16554962876789,"GB2-06":51.13788519283952,"GB2-07":49.231533682902075,"GB2-08":68.15920342920347}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.23436045013047,"medium":45.72055502526362,"none":47.145924913466516},"reasoning_agg":{"highest":{"max":55.38133319989706,"mean":33.23436045013047,"min":7.670088947709001},"medium":{"max":69.00313139343699,"mean":45.72055502526362,"min":28.065418891234213},"none":{"max":68.15920342920347,"mean":47.145924913466516,"min":28.975930507597035}},"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":69.00313139343699,"expected_score":42.276662749429526,"reasoning_variance":13.911564463336049,"reliability_score":80.91432387551889,"uncertainty_avg":19.085676124481115,"uncertainty_penalty":0.2430492864759941},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.38133319989706,"expected_score":23.35095780345705,"reliability_score":59.9661838783069,"uncertainty_avg":40.0338161216931,"uncertainty_penalty":-9.883402646673417},"medium":{"ceiling_score":69.00313139343699,"expected_score":44.861411678455504,"reliability_score":90.2959423812071,"uncertainty_avg":9.704057618792902,"uncertainty_penalty":-0.8591433468081178},"none":{"ceiling_score":68.15920342920347,"expected_score":58.61761876637604,"reliability_score":92.48084536704265,"uncertainty_avg":7.519154632957353,"uncertainty_penalty":11.471693852909524}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:7e275ce6898630a0","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.526117125,"median":0.5491332,"min":0.330054,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":15},"recorded_attempt_count":15,"run_count":8,"total":4.208937},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.526117125,"median":0.5491332,"min":0.330054,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":15},"recorded_attempt_count":15,"run_count":8,"total":4.208937}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.2975122,"median":0.2990655,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":40},"recorded_attempt_count":40,"run_count":24,"total":7.1402928},"codegen_latency_ms":{"attempt_count":40,"max_ms":1201344,"mean_ms":515468.5833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":1201344,"mean_ms":973286.5,"min_ms":605299,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":40000,"output_mean":17970.666666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":40000,"output_mean":33312.25,"output_min":20000,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":37.84494979904803,"highest":41.34245113044163,"medium":37.05266115739552,"none":47.116500014100644},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":40,"finish_reasons":["length","stop"],"indexed_attempts":41,"output_token_observations":40,"reasoning_token_observations":40,"total_output_tokens":431296,"total_reasoning_output_tokens":338477,"total_visible_output_tokens":92819,"visible_token_observations":40},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":5,"evaluated_cells":7,"failed_game_aliases":["GB2-05","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.2857142857142857,"model_code_failures":2,"repaired_admitted":4,"repaired_rate":0.5714285714285714}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:02Z","match_totals_all":{"draws":494,"losses":455,"wins":641},"match_totals_tracks":{"highest":{"draws":101,"losses":102,"wins":145},"medium":{"draws":172,"losses":182,"wins":188},"none":{"draws":221,"losses":171,"wins":308}},"model_slug":"moonshotai-kimi-k3","overall":{"max":68.5646741796879,"mean":40.72540519959575,"min":16.21094587734794},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.61062123130229,"GB2-02":20.67238336600834,"GB2-03":28.936698930432165,"GB2-04":51.71458862728154,"GB2-07":52.77796349718378},"per_game_all":{"GB2-01":47.598111826843535,"GB2-02":19.02126430304863,"GB2-03":43.353118445542314,"GB2-04":39.08035915303598,"GB2-07":40.17189526676969},"per_game_match_totals_all":{"GB2-01":{"draws":98,"losses":67,"wins":79},"GB2-02":{"draws":151,"losses":20,"wins":9},"GB2-03":{"draws":44,"losses":35,"wins":69},"GB2-04":{"draws":105,"losses":32,"wins":67},"GB2-05":{"draws":0,"losses":65,"wins":115},"GB2-06":{"draws":18,"losses":73,"wins":99},"GB2-07":{"draws":0,"losses":138,"wins":114},"GB2-08":{"draws":78,"losses":25,"wins":89}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":33,"wins":44},"GB2-02":{"draws":55,"losses":8,"wins":3},"GB2-03":{"draws":14,"losses":11,"wins":7},"GB2-04":{"draws":23,"losses":13,"wins":38},"GB2-07":{"draws":0,"losses":37,"wins":53}},"medium":{"GB2-01":{"draws":7,"losses":22,"wins":19},"GB2-02":{"draws":22,"losses":6,"wins":4},"GB2-03":{"draws":18,"losses":9,"wins":19},"GB2-04":{"draws":39,"losses":8,"wins":9},"GB2-05":{"draws":0,"losses":32,"wins":54},"GB2-06":{"draws":8,"losses":40,"wins":52},"GB2-07":{"draws":0,"losses":46,"wins":26},"GB2-08":{"draws":78,"losses":19,"wins":5}},"none":{"GB2-01":{"draws":82,"losses":12,"wins":16},"GB2-02":{"draws":74,"losses":6,"wins":2},"GB2-03":{"draws":12,"losses":15,"wins":43},"GB2-04":{"draws":43,"losses":11,"wins":20},"GB2-05":{"draws":0,"losses":33,"wins":61},"GB2-06":{"draws":10,"losses":33,"wins":47},"GB2-07":{"draws":0,"losses":55,"wins":35},"GB2-08":{"draws":0,"losses":6,"wins":84}}},"per_game_raw_elo_all":{"GB2-01":1536.8738363010934,"GB2-02":1487.8850561930176,"GB2-03":1562.8951726259038,"GB2-04":1561.3777874324821,"GB2-07":1464.7479941538177},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1578.92650016324,"GB2-02":1484.198212620904,"GB2-03":1492.401197179736,"GB2-04":1625.589788462788,"GB2-07":1588.9932384807714},"medium":{"GB2-01":1500.986338566357,"GB2-02":1502.647858481688,"GB2-03":1565.527697651422,"GB2-04":1511.8183597556254,"GB2-05":1574.497314720862,"GB2-06":1560.1002332195922,"GB2-07":1410.472304078443,"GB2-08":1440.7671715437525},"none":{"GB2-01":1530.7086701736835,"GB2-02":1476.8090974764614,"GB2-03":1630.7566230465538,"GB2-04":1546.7252140790329,"GB2-05":1631.606346995783,"GB2-06":1564.000524633293,"GB2-07":1394.7784399022385,"GB2-08":1801.6806806916547}},"per_game_tracks":{"highest":{"GB2-01":52.61062123130229,"GB2-02":20.67238336600834,"GB2-03":28.936698930432165,"GB2-04":51.71458862728154,"GB2-07":52.77796349718378},"medium":{"GB2-01":42.10161283911572,"GB2-02":16.21094587734794,"GB2-03":43.87527093406364,"GB2-04":28.063919114389087,"GB2-05":47.28681973887564,"GB2-06":58.49270207782266,"GB2-07":34.25781838363284,"GB2-08":26.132200293916647},"none":{"GB2-01":48.082101410112614,"GB2-02":20.180463665789603,"GB2-03":57.24738547213113,"GB2-04":37.462569717437304,"GB2-05":53.095684875993925,"GB2-06":58.81921687216023,"GB2-07":33.479903919492436,"GB2-08":68.5646741796879}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.00705442729109,"medium":37.05266115739552,"none":47.11650001410064},"reasoning_agg":{"highest":{"max":52.77796349718378,"mean":38.00705442729109,"min":20.67238336600834},"medium":{"max":58.49270207782266,"mean":37.05266115739552,"min":16.21094587734794},"none":{"max":68.5646741796879,"mean":47.11650001410064,"min":20.180463665789603}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":68.5646741796879,"expected_score":43.53011535742036,"reasoning_variance":10.063838856705118,"reliability_score":54.159211809715565,"uncertainty_avg":45.840788190284435,"uncertainty_penalty":2.8047101578246085},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.77796349718378,"expected_score":35.73829393845668,"reliability_score":56.210320812779784,"uncertainty_avg":43.789679187220216,"uncertainty_penalty":-2.2687604888344097},"medium":{"ceiling_score":58.49270207782266,"expected_score":41.66015353811072,"reliability_score":51.070931181384125,"uncertainty_avg":48.929068818615875,"uncertainty_penalty":4.6074923807152},"none":{"ceiling_score":68.5646741796879,"expected_score":62.71750844375377,"reliability_score":67.90475552201852,"uncertainty_avg":32.09524447798149,"uncertainty_penalty":15.601008429653135}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:6e5fee7bd6a04cc5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.987857,"mean":3.1645696249999995,"median":3.0710854999999997,"min":1.985613,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":28.806540999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.046574000000000004,"mean":0.036155625000000004,"median":0.035338,"min":0.025803,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":9,"token_priced_attempt_count":9,"total":0.31504800000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.038815,"mean":0.02196775,"median":0.0196975,"min":0.016152,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":0.175742}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.046574000000000004,"mean":0.036155625000000004,"median":0.035338,"min":0.025803,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":9,"token_priced_attempt_count":9,"total":0.315048},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.038815,"mean":0.02196775,"median":0.0196975,"min":0.016152,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":0.175742},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.987857,"mean":3.1645696249999995,"median":3.0710854999999997,"min":1.985613,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":28.806541}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.987857,"mean":1.074231,"median":0.038529,"min":0.016152,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":28},"run_count":26,"token_priced_attempt_count":28,"total":29.297331},"codegen_latency_ms":{"attempt_count":28,"max_ms":220389,"mean_ms":65068.846153846156,"min_ms":7259,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":220389,"mean_ms":159594.88888888888,"min_ms":125171,"run_count":9},"medium":{"attempt_count":9,"max_ms":22604,"mean_ms":17903.777777777777,"min_ms":13783,"run_count":9},"none":{"attempt_count":9,"max_ms":28315,"mean_ms":11787.75,"min_ms":7259,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":830024,"output_mean":186407.65384615384,"output_min":1487,"run_count":26},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":830024,"output_mean":531970.4444444445,"output_min":329738,"run_count":9},"medium":{"attempt_count":9,"output_max":6580,"output_mean":4552.555555555556,"output_min":2724,"run_count":9},"none":{"attempt_count":9,"output_max":4181,"output_mean":2236.5,"output_min":1487,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":38.66435199573877,"highest":51.77671506081652,"medium":44.28791315320452,"none":19.928427773195267},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":52,"output_token_observations":28,"total_output_tokens":4846599},"generation_policy":{"generation_policy":"quality_generation_policy","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-5.6-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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.1111111111111111}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:40Z","match_totals_all":{"draws":753,"losses":798,"wins":630},"match_totals_tracks":{"highest":{"draws":156,"losses":234,"wins":308},"medium":{"draws":295,"losses":229,"wins":246},"none":{"draws":302,"losses":335,"wins":76}},"model_slug":"gpt-5-6-luna","overall":{"max":81.11440057033718,"mean":37.73520029108536,"min":0.5457336893360095},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.69363121403609,"GB2-02":22.96981343482104,"GB2-03":15.787023585925473,"GB2-04":31.466665424316382,"GB2-05":53.65215492250481,"GB2-06":81.11440057033718,"GB2-07":76.38776402098694,"GB2-08":52.14226731360425},"per_game_all":{"GB2-01":56.30560968737632,"GB2-02":23.478073872361094,"GB2-03":28.441397213857755,"GB2-04":32.12606776179985,"GB2-05":35.39997451583346,"GB2-06":52.123171042936036,"GB2-07":45.85096889422504,"GB2-08":35.58955297752059},"per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":115,"wins":127},"GB2-02":{"draws":217,"losses":18,"wins":3},"GB2-03":{"draws":106,"losses":66,"wins":38},"GB2-04":{"draws":193,"losses":42,"wins":29},"GB2-05":{"draws":0,"losses":194,"wins":114},"GB2-06":{"draws":18,"losses":137,"wins":125},"GB2-07":{"draws":0,"losses":159,"wins":131},"GB2-08":{"draws":180,"losses":67,"wins":63}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":32,"wins":62},"GB2-02":{"draws":71,"losses":10,"wins":3},"GB2-03":{"draws":27,"losses":31,"wins":6},"GB2-04":{"draws":42,"losses":24,"wins":16},"GB2-05":{"draws":0,"losses":56,"wins":50},"GB2-06":{"draws":10,"losses":22,"wins":52},"GB2-07":{"draws":0,"losses":28,"wins":64},"GB2-08":{"draws":6,"losses":31,"wins":55}},"medium":{"GB2-01":{"draws":9,"losses":28,"wins":51},"GB2-02":{"draws":64,"losses":6,"wins":0},"GB2-03":{"draws":42,"losses":17,"wins":11},"GB2-04":{"draws":85,"losses":5,"wins":6},"GB2-05":{"draws":0,"losses":59,"wins":57},"GB2-06":{"draws":8,"losses":34,"wins":64},"GB2-07":{"draws":0,"losses":62,"wins":50},"GB2-08":{"draws":87,"losses":18,"wins":7}},"none":{"GB2-01":{"draws":30,"losses":55,"wins":14},"GB2-02":{"draws":82,"losses":2,"wins":0},"GB2-03":{"draws":37,"losses":18,"wins":21},"GB2-04":{"draws":66,"losses":13,"wins":7},"GB2-05":{"draws":0,"losses":79,"wins":7},"GB2-06":{"draws":0,"losses":81,"wins":9},"GB2-07":{"draws":0,"losses":69,"wins":17},"GB2-08":{"draws":87,"losses":18,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1594.1522911888126,"GB2-02":1472.6473518229968,"GB2-03":1422.6276846025958,"GB2-04":1494.505352383562,"GB2-05":1425.647648336505,"GB2-06":1483.3161731982318,"GB2-07":1500.5994633448943,"GB2-08":1503.3507950467235},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1821.051700392042,"GB2-02":1469.0532689115892,"GB2-03":1341.726476188212,"GB2-04":1492.3136234631593,"GB2-05":1618.20016176997,"GB2-06":1757.888067823131,"GB2-07":1808.0596113105762,"GB2-08":1645.1650048305432},"medium":{"GB2-01":1684.1296139952278,"GB2-02":1473.5711246807089,"GB2-03":1449.241069098968,"GB2-04":1508.170150760798,"GB2-05":1599.0265614912312,"GB2-06":1655.1398493340357,"GB2-07":1521.5171741625923,"GB2-08":1429.4023399340574},"none":{"GB2-01":1277.2755591791679,"GB2-02":1475.3176618766922,"GB2-03":1476.915508520607,"GB2-04":1483.0322829267293,"GB2-05":1059.7162217483137,"GB2-06":1036.920602437529,"GB2-07":1172.2216045615141,"GB2-08":1435.4850403755702}},"per_game_tracks":{"highest":{"GB2-01":80.69363121403609,"GB2-02":22.96981343482104,"GB2-03":15.787023585925473,"GB2-04":31.466665424316382,"GB2-05":53.65215492250481,"GB2-06":81.11440057033718,"GB2-07":76.38776402098694,"GB2-08":52.14226731360425},"medium":{"GB2-01":65.83747645882278,"GB2-02":23.068325697614167,"GB2-03":32.513954746621025,"GB2-04":34.94559731506889,"GB2-05":52.00203493565957,"GB2-06":70.68540227201106,"GB2-07":48.23625448361621,"GB2-08":27.014259316222454},"none":{"GB2-01":22.385721389270085,"GB2-02":24.39608248464808,"GB2-03":37.02321330902676,"GB2-04":29.965940546014295,"GB2-05":0.5457336893360095,"GB2-06":4.569710286459858,"GB2-07":12.928888178071984,"GB2-08":27.612132302735073}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.27433825612214,"medium":43.00283484393868,"none":19.928427773195263},"reasoning_agg":{"highest":{"max":81.11440057033718,"mean":50.27433825612214,"min":15.787023585925473},"medium":{"max":70.68540227201106,"mean":43.00283484393868,"min":23.068325697614167},"none":{"max":37.02321330902676,"mean":19.928427773195263,"min":0.5457336893360095}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":81.11440057033718,"expected_score":35.086527745210894,"reasoning_variance":30.34591048292688,"reliability_score":91.14350905641575,"uncertainty_avg":8.856490943584243,"uncertainty_penalty":-2.6486725458744687},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.11440057033718,"expected_score":42.60127283612711,"reliability_score":90.16304528395489,"uncertainty_avg":9.836954716045112,"uncertainty_penalty":-7.673065419995034},"medium":{"ceiling_score":70.68540227201106,"expected_score":43.342659593073776,"reliability_score":92.3650880351088,"uncertainty_avg":7.634911964891199,"uncertainty_penalty":0.3398247491350972},"none":{"ceiling_score":37.02321330902676,"expected_score":19.31565080643182,"reliability_score":90.90239385018359,"uncertainty_avg":9.097606149816416,"uncertainty_penalty":-0.6127769667634446}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:51c4a57bfa7f8191","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093000000001},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000002}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519748999999996},"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":31.90935631875719,"highest":31.00737150112073,"medium":27.596471622289776,"none":37.124225832861065},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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},"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,"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,"repaired_admitted":1,"repaired_rate":0.0625}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:18Z","match_totals_all":{"draws":948,"losses":1072,"wins":724},"match_totals_tracks":{"highest":{"draws":180,"losses":331,"wins":227},"medium":{"draws":378,"losses":411,"wins":198},"none":{"draws":390,"losses":330,"wins":299}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":60.72491770132335,"mean":31.069940185676966,"min":18.932093277185512},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.04185705006656,"GB2-02":20.20823545772604,"GB2-03":35.83416050750126,"GB2-04":21.162958277021243,"GB2-05":25.580760401626307,"GB2-06":47.7133517329692,"GB2-07":40.48268724940904,"GB2-08":22.034961332646205},"per_game_all":{"GB2-01":41.650785782391715,"GB2-02":21.057192942371337,"GB2-03":36.3050802860535,"GB2-04":27.886103210622338,"GB2-05":22.34276078314505,"GB2-06":42.56678341381697,"GB2-07":38.833532270085115,"GB2-08":24.632611861571476},"per_game_match_totals_all":{"GB2-01":{"draws":106,"losses":143,"wins":159},"GB2-02":{"draws":180,"losses":10,"wins":6},"GB2-03":{"draws":97,"losses":94,"wins":85},"GB2-04":{"draws":252,"losses":67,"wins":49},"GB2-05":{"draws":0,"losses":305,"wins":107},"GB2-06":{"draws":11,"losses":217,"wins":144},"GB2-07":{"draws":0,"losses":162,"wins":160},"GB2-08":{"draws":302,"losses":74,"wins":14}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":26,"wins":17},"GB2-02":{"draws":30,"losses":3,"wins":5},"GB2-03":{"draws":21,"losses":33,"wins":34},"GB2-04":{"draws":60,"losses":32,"wins":18},"GB2-05":{"draws":0,"losses":82,"wins":38},"GB2-06":{"draws":8,"losses":55,"wins":51},"GB2-07":{"draws":0,"losses":73,"wins":61},"GB2-08":{"draws":52,"losses":27,"wins":3}},"medium":{"GB2-01":{"draws":47,"losses":61,"wins":76},"GB2-02":{"draws":36,"losses":0,"wins":0},"GB2-03":{"draws":49,"losses":37,"wins":18},"GB2-04":{"draws":128,"losses":19,"wins":14},"GB2-05":{"draws":0,"losses":110,"wins":38},"GB2-06":{"draws":2,"losses":113,"wins":25},"GB2-07":{"draws":0,"losses":48,"wins":22},"GB2-08":{"draws":116,"losses":23,"wins":5}},"none":{"GB2-01":{"draws":50,"losses":56,"wins":66},"GB2-02":{"draws":114,"losses":7,"wins":1},"GB2-03":{"draws":27,"losses":24,"wins":33},"GB2-04":{"draws":64,"losses":16,"wins":17},"GB2-05":{"draws":0,"losses":113,"wins":31},"GB2-06":{"draws":1,"losses":49,"wins":68},"GB2-07":{"draws":0,"losses":41,"wins":77},"GB2-08":{"draws":134,"losses":24,"wins":6}}},"per_game_raw_elo_all":{"GB2-01":1477.3364955430686,"GB2-02":1492.867557270104,"GB2-03":1494.912613467627,"GB2-04":1499.3151773100915,"GB2-05":1310.7611911411639,"GB2-06":1417.31037757821,"GB2-07":1453.7176478403228,"GB2-08":1429.0911555755138},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1432.060421397574,"GB2-02":1503.0646270829602,"GB2-03":1511.6478351806873,"GB2-04":1475.65523885426,"GB2-05":1355.107361683862,"GB2-06":1474.7897534664867,"GB2-07":1475.9736603594838,"GB2-08":1413.1744868927296},"medium":{"GB2-01":1496.5961376388414,"GB2-02":1494.8163977249776,"GB2-03":1434.8740419822784,"GB2-04":1507.413996997494,"GB2-05":1295.8037388255002,"GB2-06":1180.5673528891352,"GB2-07":1257.5590178307139,"GB2-08":1429.7827706058372},"none":{"GB2-01":1503.3529275927908,"GB2-02":1480.721647002374,"GB2-03":1538.2159632399143,"GB2-04":1514.8762960785205,"GB2-05":1281.3724729141295,"GB2-06":1596.5740263790071,"GB2-07":1627.6202653307714,"GB2-08":1444.316209227975}},"per_game_tracks":{"highest":{"GB2-01":35.04185705006656,"GB2-02":20.20823545772604,"GB2-03":35.83416050750126,"GB2-04":21.162958277021243,"GB2-05":25.580760401626307,"GB2-06":47.7133517329692,"GB2-07":40.48268724940904,"GB2-08":22.034961332646205},"medium":{"GB2-01":45.4707813752063,"GB2-02":23.741559061870756,"GB2-03":29.182519323216006,"GB2-04":33.665436329086305,"GB2-05":22.515428670623326,"GB2-06":19.262080807158373,"GB2-07":20.97030061327731,"GB2-08":25.963666797879824},"none":{"GB2-01":44.4397189219023,"GB2-02":19.22178430751722,"GB2-03":43.89856102744325,"GB2-04":28.82991502575947,"GB2-05":18.932093277185512,"GB2-06":60.72491770132335,"GB2-07":55.047608947568996,"GB2-08":25.899207454188396}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.98934399569381,"medium":26.690430064939164,"none":36.53004649639792},"reasoning_agg":{"highest":{"max":47.7133517329692,"mean":29.98934399569381,"min":20.20823545772604},"medium":{"max":45.4707813752063,"mean":26.690430064939164,"min":19.262080807158373},"none":{"max":60.72491770132335,"mean":36.53004649639792,"min":18.932093277185512}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":60.72491770132335,"expected_score":30.518582210048507,"reasoning_variance":9.839616431458758,"reliability_score":61.85947055343441,"uncertainty_avg":38.14052944656559,"uncertainty_penalty":-0.5513579756284592},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":47.7133517329692,"expected_score":21.907476839709183,"reliability_score":47.44038525664332,"uncertainty_avg":52.55961474335668,"uncertainty_penalty":-8.081867155984629},"medium":{"ceiling_score":45.4707813752063,"expected_score":23.934618453030687,"reliability_score":81.23820618266727,"uncertainty_avg":18.761793817332734,"uncertainty_penalty":-2.7558116119084772},"none":{"ceiling_score":60.72491770132335,"expected_score":45.71365133740565,"reliability_score":56.89982022099265,"uncertainty_avg":43.10017977900735,"uncertainty_penalty":9.183604841007728}}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:0547893a49940f13","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.008820586750000001,"median":0.007023681,"min":0.00271606,"recorded_attempt_count":19,"run_count":8,"total":0.07056469400000001},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468000000001},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.008820586750000001,"median":0.007023681,"min":0.00271606,"recorded_attempt_count":19,"run_count":8,"total":0.070564694}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.01660212,"mean":0.00430918425,"median":0.0025298300000000003,"min":0.00045831,"recorded_attempt_count":48,"run_count":24,"total":0.10342042200000003},"codegen_latency_ms":{"attempt_count":48,"max_ms":622759,"mean_ms":232922.5,"min_ms":19833,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":622759,"mean_ms":483202.0,"min_ms":329312,"run_count":8},"medium":{"attempt_count":16,"max_ms":213246,"mean_ms":118332.0,"min_ms":41554,"run_count":8},"none":{"attempt_count":13,"max_ms":226636,"mean_ms":97233.5,"min_ms":19833,"run_count":8}},"codegen_output_tokens":{"attempt_count":48,"output_max":43929,"output_mean":12519.625,"output_min":1331,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":43929,"output_mean":28964.5,"output_min":18493,"run_count":8},"medium":{"attempt_count":16,"output_max":8961,"output_mean":5674.0,"output_min":2048,"run_count":8},"none":{"attempt_count":13,"output_max":5763,"output_mean":2920.375,"output_min":1331,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":32.014193269094406,"highest":31.297397210158135,"medium":33.330776405133705,"none":25.054577547391222},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["error","stop"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":13,"total_output_tokens":300471,"total_reasoning_output_tokens":2697,"total_visible_output_tokens":20666,"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":"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":"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":1,"first_pass_rate":0.125,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03","GB2-05"],"model_code_failure_rate":0.375,"model_code_failures":3,"repaired_admitted":5,"repaired_rate":0.625}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:31Z","match_totals_all":{"draws":605,"losses":682,"wins":347},"match_totals_tracks":{"highest":{"draws":166,"losses":150,"wins":98},"medium":{"draws":312,"losses":238,"wins":139},"none":{"draws":127,"losses":294,"wins":110}},"model_slug":"openai-gpt-oss-120b","overall":{"max":66.5532044937622,"mean":28.098738934536954,"min":10.87785451326086},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-02":10.87785451326086,"GB2-04":22.716708587278752,"GB2-06":66.5532044937622,"GB2-07":34.24914236422956,"GB2-08":22.090076092259295},"per_game_all":{"GB2-04":20.56655647993941,"GB2-06":51.032072885717696,"GB2-08":24.443950441626118},"per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":92,"wins":46},"GB2-02":{"draws":133,"losses":19,"wins":4},"GB2-03":{"draws":78,"losses":34,"wins":14},"GB2-04":{"draws":148,"losses":56,"wins":20},"GB2-05":{"draws":0,"losses":137,"wins":73},"GB2-06":{"draws":7,"losses":156,"wins":125},"GB2-07":{"draws":0,"losses":124,"wins":48},"GB2-08":{"draws":195,"losses":64,"wins":17}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":58,"losses":14,"wins":0},"GB2-04":{"draws":39,"losses":23,"wins":14},"GB2-06":{"draws":6,"losses":30,"wins":48},"GB2-07":{"draws":0,"losses":61,"wins":31},"GB2-08":{"draws":63,"losses":22,"wins":5}},"medium":{"GB2-01":{"draws":24,"losses":43,"wins":27},"GB2-02":{"draws":75,"losses":5,"wins":4},"GB2-03":{"draws":43,"losses":11,"wins":8},"GB2-04":{"draws":83,"losses":11,"wins":2},"GB2-05":{"draws":0,"losses":67,"wins":47},"GB2-06":{"draws":1,"losses":78,"wins":42},"GB2-08":{"draws":86,"losses":23,"wins":9}},"none":{"GB2-01":{"draws":20,"losses":49,"wins":19},"GB2-03":{"draws":35,"losses":23,"wins":6},"GB2-04":{"draws":26,"losses":22,"wins":4},"GB2-05":{"draws":0,"losses":70,"wins":26},"GB2-06":{"draws":0,"losses":48,"wins":35},"GB2-07":{"draws":0,"losses":63,"wins":17},"GB2-08":{"draws":46,"losses":19,"wins":3}}},"per_game_raw_elo_all":{"GB2-04":1450.211717489763,"GB2-06":1486.55039845726,"GB2-08":1427.5954991707094},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1438.6077181148798,"GB2-04":1465.3413516403082,"GB2-06":1639.439897764506,"GB2-07":1401.9371892145195,"GB2-08":1410.0939080345697},"medium":{"GB2-01":1456.6726793206537,"GB2-02":1482.281346131285,"GB2-03":1430.255627323167,"GB2-04":1465.1792260115858,"GB2-05":1455.3098804014994,"GB2-06":1384.137730967665,"GB2-08":1444.8116248114163},"none":{"GB2-01":1366.1615915517368,"GB2-03":1400.7495647402448,"GB2-04":1420.114574817395,"GB2-05":1326.272383068994,"GB2-06":1436.073566639609,"GB2-07":1281.7021143336742,"GB2-08":1427.880964666142}},"per_game_tracks":{"highest":{"GB2-02":10.87785451326086,"GB2-04":22.716708587278752,"GB2-06":66.5532044937622,"GB2-07":34.24914236422956,"GB2-08":22.090076092259295},"medium":{"GB2-01":41.54726967322666,"GB2-02":25.98156528887542,"GB2-03":29.171925207422163,"GB2-04":27.134886304266157,"GB2-05":38.408119849833696,"GB2-06":42.11628633456594,"GB2-08":28.95538217774586},"none":{"GB2-01":29.575915709416066,"GB2-03":21.15319521590135,"GB2-04":11.848074548273324,"GB2-05":24.302124280326495,"GB2-06":44.426727828824966,"GB2-07":21.789612194123116,"GB2-08":22.28639305487321}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.827758523316913,"medium":32.236467358124216,"none":24.231990922169725},"reasoning_agg":{"highest":{"max":66.5532044937622,"mean":27.827758523316913,"min":10.87785451326086},"medium":{"max":42.11628633456594,"mean":32.236467358124216,"min":25.98156528887542},"none":{"max":44.426727828824966,"mean":24.231990922169725,"min":11.848074548273324}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":66.5532044937622,"expected_score":26.19656117474791,"reasoning_variance":8.00447643595449,"reliability_score":71.20132399570285,"uncertainty_avg":28.798676004297146,"uncertainty_penalty":-1.9021777597890441},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.5532044937622,"expected_score":20.00628059163529,"reliability_score":65.92269453745556,"uncertainty_avg":34.07730546254445,"uncertainty_penalty":-7.821477931681624},"medium":{"ceiling_score":42.11628633456594,"expected_score":25.497882958855637,"reliability_score":92.7470060806915,"uncertainty_avg":7.252993919308489,"uncertainty_penalty":-6.7385843992685786},"none":{"ceiling_score":44.426727828824966,"expected_score":26.94196566278979,"reliability_score":58.28039653151275,"uncertainty_avg":41.71960346848725,"uncertainty_penalty":2.7099747406200656}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:e25aa4a60eafd473","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"evidence_basis":"Standard list-price estimate","max":1.91725,"mean":1.58262125,"median":1.5854,"min":1.05322,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":12.66097},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6981,"mean":0.5046499999999999,"median":0.511355,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0371999999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6981,"mean":0.5046499999999999,"median":0.511355,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0372},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"evidence_basis":"Standard list-price estimate","max":1.91725,"mean":1.58262125,"median":1.5854,"min":1.05322,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":12.660969999999999}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.91725,"mean":1.043635625,"median":0.8756600000000001,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":19},"run_count":16,"token_priced_attempt_count":19,"total":16.69817},"codegen_latency_ms":{"attempt_count":19,"max_ms":409229,"mean_ms":200864.125,"min_ms":48099,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":409229,"mean_ms":316399.125,"min_ms":206163,"run_count":8},"medium":{"attempt_count":8,"max_ms":135206,"mean_ms":85329.125,"min_ms":48099,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":35932,"output_mean":17962.875,"output_min":4319,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":35932,"output_mean":28345.125,"output_min":18778,"run_count":8},"medium":{"attempt_count":8,"output_max":11549,"output_mean":7580.625,"output_min":4319,"run_count":8}},"display_name":"Claude Fable 5","economics":{"highest":84.6293808975043,"medium":68.6964642118633},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":23,"output_token_observations":19,"total_output_tokens":287406},"generation_policy":{"generation_policy":"quality_generation_policy","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","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"infra_failures_excluded":4,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-08-05T04:44:21Z","match_totals_all":{"draws":162,"losses":263,"wins":907},"match_totals_tracks":{"highest":{"draws":94,"losses":116,"wins":502},"medium":{"draws":68,"losses":147,"wins":405}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":75.53520861590758,"min":47.83931957227835},"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":"partial","per_game":{"GB2-01":79.68193767817715,"GB2-02":75.80812316419362,"GB2-03":70.49045424400458,"GB2-04":100.0,"GB2-05":90.25579059650316,"GB2-06":93.83172258846857,"GB2-07":66.9670189086873,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":60,"wins":122},"GB2-02":{"draws":67,"losses":13,"wins":78},"GB2-03":{"draws":30,"losses":7,"wins":27},"GB2-04":{"draws":50,"losses":22,"wins":106},"GB2-05":{"draws":0,"losses":58,"wins":146},"GB2-06":{"draws":14,"losses":32,"wins":128},"GB2-07":{"draws":0,"losses":55,"wins":125},"GB2-08":{"draws":1,"losses":16,"wins":175}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":35,"wins":63},"GB2-02":{"draws":37,"losses":4,"wins":41},"GB2-03":{"draws":30,"losses":7,"wins":27},"GB2-04":{"draws":17,"losses":5,"wins":76},"GB2-05":{"draws":0,"losses":16,"wins":82},"GB2-06":{"draws":9,"losses":10,"wins":63},"GB2-07":{"draws":0,"losses":35,"wins":55},"GB2-08":{"draws":1,"losses":4,"wins":95}},"medium":{"GB2-01":{"draws":0,"losses":25,"wins":59},"GB2-02":{"draws":30,"losses":9,"wins":37},"GB2-04":{"draws":33,"losses":17,"wins":30},"GB2-05":{"draws":0,"losses":42,"wins":64},"GB2-06":{"draws":5,"losses":22,"wins":65},"GB2-07":{"draws":0,"losses":20,"wins":70},"GB2-08":{"draws":0,"losses":12,"wins":80}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1810.7971143350485,"GB2-02":1701.6468619133602,"GB2-03":1700.3473191690596,"GB2-04":1865.823673582791,"GB2-05":2007.5728572044336,"GB2-06":1877.949290834117,"GB2-07":1713.9112383774284,"GB2-08":2047.0897119000806},"medium":{"GB2-01":1753.8905307528914,"GB2-02":1690.47443747152,"GB2-04":1582.9690692214492,"GB2-05":1673.6388165109624,"GB2-06":1783.3077264160918,"GB2-07":1762.4042745072609,"GB2-08":1814.5336004592846}},"per_game_tracks":{"highest":{"GB2-01":79.68193767817715,"GB2-02":75.80812316419362,"GB2-03":70.49045424400458,"GB2-04":100.0,"GB2-05":90.25579059650316,"GB2-06":93.83172258846857,"GB2-07":66.9670189086873,"GB2-08":100.0},"medium":{"GB2-01":73.22615883803878,"GB2-02":72.88223492302193,"GB2-04":47.83931957227835,"GB2-05":58.88434592732646,"GB2-06":84.02163040431354,"GB2-07":71.79611330973476,"GB2-08":72.22544650832927}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":84.62938089750429,"medium":66.44103633431087},"reasoning_agg":{"highest":{"max":100.0,"mean":84.62938089750429,"min":66.9670189086873},"medium":{"max":84.02163040431354,"mean":66.44103633431087,"min":47.83931957227835}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":18.188344563193425},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":82.32343320511589,"reliability_score":90.66207488502853,"uncertainty_avg":9.337925114971469,"uncertainty_penalty":-2.3059476923884006},"medium":{"ceiling_score":84.02163040431354,"expected_score":85.63692455544869,"reliability_score":90.71932942836283,"uncertainty_avg":9.28067057163717,"uncertainty_penalty":19.19588822113782}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:fa85c3da121cf5b2","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425},"codegen_latency_ms":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1}},"codegen_output_tokens":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1}},"display_name":"GPT 4.1 Nano","economics":{"none":47.75501155028078},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":1,"finish_reasons":["stop"],"indexed_attempts":2,"output_token_observations":2,"reasoning_token_observations":1,"total_output_tokens":2006,"total_visible_output_tokens":64,"visible_token_observations":1},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-08-05T04:10:10Z","match_totals_all":{"draws":26,"losses":22,"wins":34},"match_totals_tracks":{"none":{"draws":26,"losses":22,"wins":34}},"model_slug":"gpt-4-1-nano","overall":{"max":47.75501155028078,"mean":47.75501155028078,"min":47.75501155028078},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":22,"wins":34}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":26,"losses":22,"wins":34}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1517.321654013368}},"per_game_tracks":{"none":{"GB2-01":47.75501155028078}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":47.75501155028078},"reasoning_agg":{"none":{"max":47.75501155028078,"mean":47.75501155028078,"min":47.75501155028078}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":47.75501155028078},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":47.75501155028078,"expected_score":40.998581055348424,"reliability_score":88.86787000515483,"uncertainty_avg":11.132129994845172,"uncertainty_penalty":-6.756430494932353}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:bda869958eedd23a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"local_list_price_estimate":3},"evidence_basis":"Standard list-price estimate","max":0.469661,"mean":0.469661,"median":0.469661,"min":0.469661,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":1},"run_count":2,"token_priced_attempt_count":3,"total":0.939322},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.132112,"mean":0.0780535,"median":0.06797,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":0.624428},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"provider_dashboard_reconciled":1},"evidence_basis":"Combined: Provider-reported + Recorded attempt","max":0.09014,"mean":0.09014,"median":0.09014,"min":0.09014,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":2,"run_count":1,"total":0.09014}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.132112,"mean":0.0780535,"median":0.06797,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6244280000000001},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"provider_dashboard_reconciled":1},"evidence_basis":"Combined: Provider-reported + Recorded attempt","max":0.09014,"mean":0.09014,"median":0.09014,"min":0.09014,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":2,"run_count":1,"total":0.09014},"historical-provider-setting-intensive":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"local_list_price_estimate":3},"evidence_basis":"Standard list-price estimate","max":0.469661,"mean":0.469661,"median":0.469661,"min":0.469661,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":1},"run_count":2,"token_priced_attempt_count":3,"total":0.939322}},"codegen_cost_usd":{"admitted_cell_count":10,"cell_count":10,"cost_basis_counts":{"estimated":1,"local_list_price_estimate":12,"provider_dashboard_reconciled":1},"evidence_basis":"Combined: Provider-reported + Recorded attempt + Standard list-price estimate","failed_cell_count":1,"max":0.469661,"mean":0.11842290000000003,"median":0.074902,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":11},"recorded_attempt_count":2,"run_count":11,"token_priced_attempt_count":12,"total":1.6538899999999999},"codegen_latency_ms":{"attempt_count":13,"max_ms":590864,"mean_ms":103930.63636363637,"min_ms":2034,"run_count":11},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":590864,"mean_ms":400966.0,"min_ms":211068,"run_count":2},"medium":{"attempt_count":9,"max_ms":95118,"mean_ms":42408.875,"min_ms":23645,"run_count":8},"none":{"attempt_count":1,"max_ms":2034,"mean_ms":2034.0,"min_ms":2034,"run_count":1}},"codegen_output_tokens":{"attempt_count":14,"output_max":62762,"output_mean":11857.363636363636,"output_min":3136,"run_count":11},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":62762,"output_mean":43014.5,"output_min":23267,"run_count":2},"medium":{"attempt_count":9,"output_max":10845,"output_mean":5045.625,"output_min":3136,"run_count":8},"none":{"attempt_count":2,"output_max":4037,"output_mean":4037.0,"output_min":4037,"run_count":1}},"display_name":"Claude Sonnet 5","economics":{"highest":52.22657439455518,"medium":41.5232388450807,"none":44.83323249072341},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":13,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":16,"output_token_observations":14,"reasoning_token_observations":3,"requested_max_output_token_observations":4,"requested_max_output_tokens":[128000],"total_output_tokens":130431,"total_reasoning_output_tokens":47819,"total_visible_output_tokens":6893,"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":null,"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.125},"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},"intensive":{"admitted_plugins":2,"evaluated_cells":2,"first_pass_admitted":2,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:02:41Z","match_totals_all":{"draws":373,"losses":270,"wins":339},"match_totals_tracks":{"highest":{"draws":70,"losses":48,"wins":56},"medium":{"draws":237,"losses":212,"wins":275},"none":{"draws":66,"losses":10,"wins":8}},"model_slug":"claude-sonnet-5","overall":{"max":52.82357979001043,"mean":45.73992115934501,"min":26.602617521323882},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-03":52.22657439455518},"per_game_match_totals_all":{"GB2-01":{"draws":75,"losses":48,"wins":57},"GB2-02":{"draws":71,"losses":4,"wins":1},"GB2-03":{"draws":70,"losses":48,"wins":56},"GB2-04":{"draws":70,"losses":11,"wins":19},"GB2-05":{"draws":0,"losses":38,"wins":66},"GB2-06":{"draws":4,"losses":51,"wins":61},"GB2-07":{"draws":0,"losses":50,"wins":72},"GB2-08":{"draws":83,"losses":20,"wins":7}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":70,"losses":48,"wins":56}},"medium":{"GB2-01":{"draws":9,"losses":38,"wins":49},"GB2-02":{"draws":71,"losses":4,"wins":1},"GB2-04":{"draws":70,"losses":11,"wins":19},"GB2-05":{"draws":0,"losses":38,"wins":66},"GB2-06":{"draws":4,"losses":51,"wins":61},"GB2-07":{"draws":0,"losses":50,"wins":72},"GB2-08":{"draws":83,"losses":20,"wins":7}},"none":{"GB2-01":{"draws":66,"losses":10,"wins":8}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1573.8932580896576},"medium":{"GB2-01":1561.2086367687052,"GB2-02":1487.86953058894,"GB2-04":1488.2760299875736,"GB2-05":1592.58297021455,"GB2-06":1466.154060432485,"GB2-07":1548.1539016254237,"GB2-08":1426.2683033126514},"none":{"GB2-01":1489.6057722063917}},"per_game_tracks":{"highest":{"GB2-03":52.22657439455518},"medium":{"GB2-01":52.82357979001043,"GB2-02":26.753406537020762,"GB2-04":31.478769660606087,"GB2-05":51.19986121676889,"GB2-06":50.76005671360996,"GB2-07":51.044380476224916,"GB2-08":26.602617521323882},"none":{"GB2-01":44.83323249072341}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.22657439455518,"medium":40.15995659275643,"none":44.83323249072341},"reasoning_agg":{"highest":{"max":52.22657439455518,"mean":52.22657439455518,"min":52.22657439455518},"medium":{"max":52.82357979001043,"mean":40.15995659275643,"min":26.602617521323882},"none":{"max":44.83323249072341,"mean":44.83323249072341,"min":44.83323249072341}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":52.82357979001043,"reasoning_variance":12.066617801798749},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.22657439455518,"expected_score":42.610551559289824,"reliability_score":90.13391050361021,"uncertainty_avg":9.866089496389785,"uncertainty_penalty":-9.616022835265355},"medium":{"ceiling_score":52.82357979001043,"expected_score":41.038385992281114,"reliability_score":94.4555917832107,"uncertainty_avg":5.544408216789291,"uncertainty_penalty":0.8784293995246841},"none":{"ceiling_score":44.83323249072341,"expected_score":37.6162274222741,"reliability_score":89.51738554533596,"uncertainty_avg":10.482614454664043,"uncertainty_penalty":-7.217005068449311}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:d06731d4b4c0d390","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.48907706250000005,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.9126164999999995},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","max":0.5145615,"mean":0.34875300000000004,"median":0.335163,"min":0.254883,"recorded_attempt_count":19,"run_count":8,"total":2.7900240000000003},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","max":0.5145615,"mean":0.34875300000000004,"median":0.335163,"min":0.254883,"recorded_attempt_count":19,"run_count":8,"total":2.790024},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545000000001},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.48907706250000005,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.9126164999999995}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":24,"cost_basis_counts":{"provider_reported":51},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.6921525,"mean":0.30153312499999996,"median":0.335163,"min":0.025422,"recorded_attempt_count":51,"run_count":24,"total":7.236795},"codegen_latency_ms":{"attempt_count":37,"max_ms":391025,"mean_ms":206292.5625,"min_ms":126419,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":391025,"mean_ms":243664.625,"min_ms":198838,"run_count":8},"medium":{"attempt_count":19,"max_ms":243355,"mean_ms":168920.5,"min_ms":126419,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":74213,"output_mean":43169.4375,"output_min":25565,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":74213,"output_mean":51048.625,"output_min":41983,"run_count":8},"medium":{"attempt_count":19,"output_max":52941,"output_mean":35290.25,"output_min":25565,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"highest":40.466137703026426,"medium":53.54328630060818},"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":690711},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":8,"repaired_rate":1.0},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.75}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:04:52Z","match_totals_all":{"draws":382,"losses":380,"wins":490},"match_totals_tracks":{"highest":{"draws":148,"losses":193,"wins":179},"medium":{"draws":234,"losses":187,"wins":311}},"model_slug":"google-gemini-3-5-flash","overall":{"max":93.17614952930187,"mean":45.60063533806962,"min":13.591710349239374},"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":"partial","per_game":{"GB2-03":37.494654124976805,"GB2-04":18.838331311955223,"GB2-05":41.21284375873298,"GB2-06":77.64645353476814,"GB2-07":54.012833138486045,"GB2-08":13.591710349239374},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":9,"wins":75},"GB2-02":{"draws":70,"losses":10,"wins":10},"GB2-03":{"draws":83,"losses":27,"wins":32},"GB2-04":{"draws":86,"losses":52,"wins":48},"GB2-05":{"draws":0,"losses":107,"wins":101},"GB2-06":{"draws":16,"losses":29,"wins":123},"GB2-07":{"draws":0,"losses":91,"wins":101},"GB2-08":{"draws":127,"losses":55,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":53,"losses":12,"wins":9},"GB2-04":{"draws":30,"losses":37,"wins":21},"GB2-05":{"draws":0,"losses":53,"wins":43},"GB2-06":{"draws":5,"losses":17,"wins":60},"GB2-07":{"draws":0,"losses":40,"wins":46},"GB2-08":{"draws":60,"losses":34,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":9,"wins":75},"GB2-02":{"draws":70,"losses":10,"wins":10},"GB2-03":{"draws":30,"losses":15,"wins":23},"GB2-04":{"draws":56,"losses":15,"wins":27},"GB2-05":{"draws":0,"losses":54,"wins":58},"GB2-06":{"draws":11,"losses":12,"wins":63},"GB2-07":{"draws":0,"losses":51,"wins":55},"GB2-08":{"draws":67,"losses":21,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1499.3273441827764,"GB2-04":1438.573033769448,"GB2-05":1504.9062628518725,"GB2-06":1743.6380722729027,"GB2-07":1602.3036199131727,"GB2-08":1336.7791209706893},"medium":{"GB2-01":1939.5874331556233,"GB2-02":1495.3389302620424,"GB2-03":1571.8753694864479,"GB2-04":1556.148668508276,"GB2-05":1549.9264735902525,"GB2-06":1843.3512911845396,"GB2-07":1583.0678904088375,"GB2-08":1368.2923757001072}},"per_game_tracks":{"highest":{"GB2-03":37.494654124976805,"GB2-04":18.838331311955223,"GB2-05":41.21284375873298,"GB2-06":77.64645353476814,"GB2-07":54.012833138486045,"GB2-08":13.591710349239374},"medium":{"GB2-01":93.17614952930187,"GB2-02":29.285703310875242,"GB2-03":51.11619311992135,"GB2-04":43.737382109924624,"GB2-05":47.30683087113872,"GB2-06":90.25968655583348,"GB2-07":54.26204637051112,"GB2-08":19.20229853735902}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.657984375531065,"medium":53.54328630060818},"reasoning_agg":{"highest":{"max":77.64645353476814,"mean":37.657984375531065,"min":13.591710349239374},"medium":{"max":93.17614952930187,"mean":53.54328630060818,"min":19.20229853735902}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":93.17614952930187,"reasoning_variance":15.885301925077115},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.64645353476814,"expected_score":31.155064185502752,"reliability_score":68.31214488205812,"uncertainty_avg":31.687855117941876,"uncertainty_penalty":-6.502920190028313},"medium":{"ceiling_score":93.17614952930187,"expected_score":58.32019906702789,"reliability_score":91.3662422237155,"uncertainty_avg":8.633757776284494,"uncertainty_penalty":4.776912766419713}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:19198473790d4b05","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"provider_reported":7},"evidence_basis":"Provider-reported","max":0.09063263032999999,"mean":0.09063263032999999,"median":0.09063263032999999,"min":0.09063263032999999,"recorded_attempt_count":7,"run_count":2,"total":0.18126526065999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804},"historical-provider-setting-intensive":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"provider_reported":7},"evidence_basis":"Provider-reported","max":0.09063263032999999,"mean":0.09063263032999999,"median":0.09063263032999999,"min":0.09063263032999999,"recorded_attempt_count":7,"run_count":2,"total":0.18126526065999998}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":17,"cost_basis_counts":{"provider_reported":47},"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.04690495967823529,"median":0.030447832,"min":0.0106770175,"recorded_attempt_count":47,"run_count":26,"total":1.0676026350599999},"codegen_latency_ms":{"attempt_count":7,"max_ms":2481480,"mean_ms":1484485.0,"min_ms":487490,"run_count":2},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":7,"max_ms":2481480,"mean_ms":1484485.0,"min_ms":487490,"run_count":2}},"codegen_output_tokens":{"attempt_count":7,"output_max":153344,"output_mean":90656.0,"output_min":27968,"run_count":2},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":7,"output_max":153344,"output_mean":90656.0,"output_min":27968,"run_count":2}},"display_name":"GLM-5.2","economics":{"all":37.073178183703774,"highest":42.15233778736079,"medium":40.36964566822355,"none":40.61922412738445},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":7,"finish_reasons":["stop"],"indexed_attempts":7,"output_token_observations":7,"reasoning_token_observations":5,"total_output_tokens":181312,"total_reasoning_output_tokens":94090,"total_visible_output_tokens":10550,"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":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":7,"repaired_rate":0.4375},"intensive":{"admitted_plugins":2,"evaluated_cells":2,"first_pass_admitted":2,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-08-05T04:45:51Z","match_totals_all":{"draws":622,"losses":577,"wins":569},"match_totals_tracks":{"highest":{"draws":21,"losses":18,"wins":27},"medium":{"draws":225,"losses":160,"wins":177},"none":{"draws":376,"losses":399,"wins":365}},"model_slug":"z-ai-glm-5-2","overall":{"max":69.68324241888193,"mean":41.04706919432293,"min":20.60128829346809},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-03":42.15233778736079},"per_game_all":{"GB2-03":37.073178183703774},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":106,"wins":94},"GB2-02":{"draws":178,"losses":9,"wins":1},"GB2-03":{"draws":116,"losses":61,"wins":53},"GB2-04":{"draws":144,"losses":39,"wins":31},"GB2-05":{"draws":0,"losses":122,"wins":122},"GB2-06":{"draws":24,"losses":87,"wins":101},"GB2-07":{"draws":0,"losses":111,"wins":113},"GB2-08":{"draws":124,"losses":42,"wins":54}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":21,"losses":18,"wins":27}},"medium":{"GB2-01":{"draws":7,"losses":30,"wins":43},"GB2-02":{"draws":61,"losses":1,"wins":0},"GB2-03":{"draws":38,"losses":11,"wins":3},"GB2-04":{"draws":49,"losses":10,"wins":7},"GB2-05":{"draws":0,"losses":40,"wins":42},"GB2-06":{"draws":8,"losses":25,"wins":35},"GB2-07":{"draws":0,"losses":32,"wins":46},"GB2-08":{"draws":62,"losses":11,"wins":1}},"none":{"GB2-01":{"draws":29,"losses":76,"wins":51},"GB2-02":{"draws":117,"losses":8,"wins":1},"GB2-03":{"draws":57,"losses":32,"wins":23},"GB2-04":{"draws":95,"losses":29,"wins":24},"GB2-05":{"draws":0,"losses":82,"wins":80},"GB2-06":{"draws":16,"losses":62,"wins":66},"GB2-07":{"draws":0,"losses":79,"wins":67},"GB2-08":{"draws":62,"losses":31,"wins":53}}},"per_game_raw_elo_all":{"GB2-03":1490.5160686444135},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1533.5781271742296},"medium":{"GB2-01":1469.1718670852033,"GB2-02":1475.841977949159,"GB2-03":1446.0068426521739,"GB2-04":1501.1308285615892,"GB2-05":1575.0888414631513,"GB2-06":1655.2045242420968,"GB2-07":1545.2260932564172,"GB2-08":1427.9759189337483},"none":{"GB2-01":1362.3304641440059,"GB2-02":1465.2688292024814,"GB2-03":1491.9632361068366,"GB2-04":1501.714578014611,"GB2-05":1527.9857641872218,"GB2-06":1603.5598024695696,"GB2-07":1530.539579591432,"GB2-08":1592.1255280580322}},"per_game_tracks":{"highest":{"GB2-03":42.15233778736079},"medium":{"GB2-01":42.524252957277774,"GB2-02":22.919618819874938,"GB2-03":30.880698337056444,"GB2-04":32.1670764313632,"GB2-05":49.08920702046711,"GB2-06":69.68324241888193,"GB2-07":49.862871057100186,"GB2-08":25.83019830376679},"none":{"GB2-01":30.981232011417283,"GB2-02":20.60128829346809,"GB2-03":38.18649842669409,"GB2-04":32.73976498521204,"GB2-05":44.618288762349096,"GB2-06":64.32999385511812,"GB2-07":48.24855218994896,"GB2-08":45.24817449486797}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.15233778736079,"medium":40.36964566822354,"none":40.619224127384456},"reasoning_agg":{"highest":{"max":42.15233778736079,"mean":42.15233778736079,"min":42.15233778736079},"medium":{"max":69.68324241888193,"mean":40.36964566822354,"min":22.919618819874938},"none":{"max":64.32999385511812,"mean":40.619224127384456,"min":20.60128829346809}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":69.68324241888193,"expected_score":34.53741222809595,"reasoning_variance":1.782692119137252,"reliability_score":70.1784568106457,"uncertainty_avg":29.821543189354298,"uncertainty_penalty":-6.509656966226977},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.15233778736079,"expected_score":35.211345047392754,"reliability_score":57.9728732746497,"uncertainty_avg":42.0271267253503,"uncertainty_penalty":-6.9409927399680384},"medium":{"ceiling_score":69.68324241888193,"expected_score":39.0592402720968,"reliability_score":84.07761036926033,"uncertainty_avg":15.92238963073968,"uncertainty_penalty":-1.3104053961267397},"none":{"ceiling_score":64.32999385511812,"expected_score":46.51318856212495,"reliability_score":84.6143740633617,"uncertainty_avg":15.385625936638302,"uncertainty_penalty":5.8939644347404965}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:740077efda94b582","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.10909930499999998,"mean":0.082847753875,"median":0.084146916,"min":0.03951746,"recorded_attempt_count":16,"run_count":8,"total":0.662782031},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.029078938,"mean":0.015562441375000001,"median":0.013116718500000001,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.12449953100000001}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.029078938,"mean":0.015562441375000001,"median":0.013116718500000001,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.12449953100000001},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.10909930499999998,"mean":0.082847753875,"median":0.084146916,"min":0.03951746,"recorded_attempt_count":16,"run_count":8,"total":0.662782031}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.10909930499999998,"mean":0.049205097625000006,"median":0.034298199,"min":0.005612805,"recorded_attempt_count":28,"run_count":16,"total":0.787281562},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214284,"mean_ms":465438.125,"min_ms":42870,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":1214284,"mean_ms":845698.625,"min_ms":162422,"run_count":8},"none":{"attempt_count":12,"max_ms":162843,"mean_ms":85177.625,"min_ms":42870,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":80681,"output_mean":29459.75,"output_min":2689,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":80681,"output_mean":54027.75,"output_min":8210,"run_count":8},"none":{"attempt_count":12,"output_max":7681,"output_mean":4891.75,"output_min":2689,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"highest":44.28286266599719,"none":40.574001935890315},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":471356},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":3,"repaired_rate":0.375},"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,"repaired_admitted":5,"repaired_rate":0.625}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:41Z","match_totals_all":{"draws":364,"losses":454,"wins":418},"match_totals_tracks":{"highest":{"draws":132,"losses":242,"wins":202},"none":{"draws":232,"losses":212,"wins":216}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":71.11107962938964,"mean":40.22586600111486,"min":23.61062430589122},"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":"partial","per_game":{"GB2-01":43.61554479729633,"GB2-04":26.709033756995762,"GB2-05":71.11107962938964,"GB2-06":45.6628100593333,"GB2-07":54.98808344707694,"GB2-08":23.61062430589122},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":88,"wins":67},"GB2-02":{"draws":78,"losses":6,"wins":2},"GB2-03":{"draws":18,"losses":29,"wins":15},"GB2-04":{"draws":52,"losses":25,"wins":9},"GB2-05":{"draws":0,"losses":85,"wins":107},"GB2-06":{"draws":10,"losses":85,"wins":105},"GB2-07":{"draws":0,"losses":94,"wins":100},"GB2-08":{"draws":141,"losses":42,"wins":13}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":44,"wins":33},"GB2-04":{"draws":52,"losses":25,"wins":9},"GB2-05":{"draws":0,"losses":35,"wins":61},"GB2-06":{"draws":2,"losses":61,"wins":51},"GB2-07":{"draws":0,"losses":52,"wins":44},"GB2-08":{"draws":59,"losses":25,"wins":4}},"none":{"GB2-01":{"draws":46,"losses":44,"wins":34},"GB2-02":{"draws":78,"losses":6,"wins":2},"GB2-03":{"draws":18,"losses":29,"wins":15},"GB2-05":{"draws":0,"losses":50,"wins":46},"GB2-06":{"draws":8,"losses":24,"wins":54},"GB2-07":{"draws":0,"losses":42,"wins":56},"GB2-08":{"draws":82,"losses":17,"wins":9}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1475.4991443772221,"GB2-04":1465.1059463245633,"GB2-05":1805.1338387843662,"GB2-06":1418.5606086737382,"GB2-07":1592.3030320455705,"GB2-08":1405.469355363088},"none":{"GB2-01":1488.5540474275292,"GB2-02":1479.248896520903,"GB2-03":1406.28947900497,"GB2-05":1431.2181246632692,"GB2-06":1642.2089240234834,"GB2-07":1486.6131615979011,"GB2-08":1525.8670668329498}},"per_game_tracks":{"highest":{"GB2-01":43.61554479729633,"GB2-04":26.709033756995762,"GB2-05":71.11107962938964,"GB2-06":45.6628100593333,"GB2-07":54.98808344707694,"GB2-08":23.61062430589122},"none":{"GB2-01":45.53770120402753,"GB2-02":25.40534241954475,"GB2-03":25.516168554327326,"GB2-05":35.82165124902767,"GB2-06":68.86134465387879,"GB2-07":44.504203648777164,"GB2-08":38.37160182164898}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.20984717192794,"none":39.24188483030178},"reasoning_agg":{"highest":{"max":71.11107962938964,"mean":41.20984717192794,"min":23.61062430589122},"none":{"max":68.86134465387879,"mean":39.24188483030178,"min":25.40534241954475}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":71.11107962938964,"reasoning_variance":1.967962341626162},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":71.11107962938964,"expected_score":31.88635590107415,"reliability_score":92.82788567928895,"uncertainty_avg":7.172114320711047,"uncertainty_penalty":-9.32349127085379},"none":{"ceiling_score":68.86134465387879,"expected_score":40.14848161136009,"reliability_score":91.77325640723635,"uncertainty_avg":8.226743592763656,"uncertainty_penalty":0.9065967810583118}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:8fed194f257c1858","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793050000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"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},"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-07-30":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":{"highest":37.80503304728465,"medium":39.9368552071157},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":2,"repaired_rate":0.25}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:06Z","match_totals_all":{"draws":398,"losses":516,"wins":458},"match_totals_tracks":{"highest":{"draws":225,"losses":268,"wins":241},"medium":{"draws":173,"losses":248,"wins":217}},"model_slug":"gpt-5","overall":{"max":68.24458515523042,"mean":38.215344908162436,"min":16.47955768015164},"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":"partial","per_game":{"GB2-01":42.21919853575708,"GB2-02":16.47955768015164,"GB2-03":26.836159834589736,"GB2-04":22.596644926517598,"GB2-05":52.07459338705543,"GB2-06":68.24458515523042,"GB2-07":50.4873271878866,"GB2-08":23.50219767108876},"per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":105,"wins":72},"GB2-02":{"draws":57,"losses":15,"wins":2},"GB2-03":{"draws":61,"losses":49,"wins":24},"GB2-04":{"draws":126,"losses":38,"wins":24},"GB2-05":{"draws":0,"losses":99,"wins":101},"GB2-06":{"draws":15,"losses":71,"wins":102},"GB2-07":{"draws":0,"losses":81,"wins":109},"GB2-08":{"draws":116,"losses":58,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":52,"wins":50},"GB2-02":{"draws":57,"losses":15,"wins":2},"GB2-03":{"draws":26,"losses":30,"wins":16},"GB2-04":{"draws":66,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":47,"wins":51},"GB2-06":{"draws":8,"losses":31,"wins":49},"GB2-07":{"draws":0,"losses":42,"wins":50},"GB2-08":{"draws":62,"losses":32,"wins":16}},"medium":{"GB2-01":{"draws":17,"losses":53,"wins":22},"GB2-03":{"draws":35,"losses":19,"wins":8},"GB2-04":{"draws":60,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":52,"wins":50},"GB2-06":{"draws":7,"losses":40,"wins":53},"GB2-07":{"draws":0,"losses":39,"wins":59},"GB2-08":{"draws":54,"losses":26,"wins":8}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1475.9313234311355,"GB2-02":1462.47622141143,"GB2-03":1431.5010278143418,"GB2-04":1457.9324472888316,"GB2-05":1619.3923852536077,"GB2-06":1653.1996547008405,"GB2-07":1565.486896567064,"GB2-08":1415.6136814138022},"medium":{"GB2-01":1309.3826997250194,"GB2-03":1399.3895422530882,"GB2-04":1495.669383234101,"GB2-05":1602.5266986191143,"GB2-06":1589.115508396417,"GB2-07":1638.5757431946397,"GB2-08":1387.3551553183834}},"per_game_tracks":{"highest":{"GB2-01":42.21919853575708,"GB2-02":16.47955768015164,"GB2-03":26.836159834589736,"GB2-04":22.596644926517598,"GB2-05":52.07459338705543,"GB2-06":68.24458515523042,"GB2-07":50.4873271878866,"GB2-08":23.50219767108876},"medium":{"GB2-01":25.676297098775773,"GB2-03":24.46366360644326,"GB2-04":32.67442303505885,"GB2-05":52.1027343192657,"GB2-06":63.54103500269817,"GB2-07":59.63713222006284,"GB2-08":21.462701167505323}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.80503304728466,"medium":38.6256567690402},"reasoning_agg":{"highest":{"max":68.24458515523042,"mean":37.80503304728466,"min":16.47955768015164},"medium":{"max":63.54103500269817,"mean":38.6256567690402,"min":21.462701167505323}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":68.24458515523042,"reasoning_variance":0.8206237217555383},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.24458515523042,"expected_score":28.101790898717596,"reliability_score":69.78750897087232,"uncertainty_avg":30.21249102912768,"uncertainty_penalty":-9.703242148567064},"medium":{"ceiling_score":63.54103500269817,"expected_score":37.568474563478574,"reliability_score":91.1958457128477,"uncertainty_avg":8.804154287152304,"uncertainty_penalty":-1.0571822055616238}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:626f807d89d29d00","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999998},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.72882375},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875000000003}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":38.59132435668447,"none":39.86320548854211},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:11Z","match_totals_all":{"draws":474,"losses":467,"wins":427},"match_totals_tracks":{"medium":{"draws":263,"losses":244,"wins":223},"none":{"draws":211,"losses":223,"wins":204}},"model_slug":"qwen-qwen3-7-max","overall":{"max":66.08924139036272,"mean":37.93936360364965,"min":20.826508924484237},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":84,"wins":55},"GB2-02":{"draws":144,"losses":19,"wins":11},"GB2-03":{"draws":50,"losses":10,"wins":6},"GB2-04":{"draws":64,"losses":23,"wins":17},"GB2-05":{"draws":0,"losses":113,"wins":111},"GB2-06":{"draws":13,"losses":104,"wins":89},"GB2-07":{"draws":0,"losses":53,"wins":123},"GB2-08":{"draws":150,"losses":61,"wins":15}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":30,"losses":54,"wins":12},"GB2-02":{"draws":82,"losses":13,"wins":3},"GB2-04":{"draws":64,"losses":23,"wins":17},"GB2-05":{"draws":0,"losses":61,"wins":59},"GB2-06":{"draws":11,"losses":41,"wins":56},"GB2-07":{"draws":0,"losses":21,"wins":65},"GB2-08":{"draws":76,"losses":31,"wins":11}},"none":{"GB2-01":{"draws":23,"losses":30,"wins":43},"GB2-02":{"draws":62,"losses":6,"wins":8},"GB2-03":{"draws":50,"losses":10,"wins":6},"GB2-05":{"draws":0,"losses":52,"wins":52},"GB2-06":{"draws":2,"losses":63,"wins":33},"GB2-07":{"draws":0,"losses":32,"wins":58},"GB2-08":{"draws":74,"losses":30,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1303.4905060606818,"GB2-02":1472.8304846432588,"GB2-04":1490.3790983677727,"GB2-05":1546.0164057321053,"GB2-06":1583.301435818596,"GB2-07":1696.3443936235544,"GB2-08":1447.77340818449},"none":{"GB2-01":1572.4078988417914,"GB2-02":1491.6324167926382,"GB2-03":1437.7587628203037,"GB2-05":1525.3995628419666,"GB2-06":1279.3223943837968,"GB2-07":1705.0967292013736,"GB2-08":1416.188024322118}},"per_game_tracks":{"medium":{"GB2-01":23.261465808297835,"GB2-02":20.826508924484237,"GB2-04":28.91029406876563,"GB2-05":45.394758803516936,"GB2-06":61.224644528934874,"GB2-07":63.10196361472715,"GB2-08":27.4196347480646},"none":{"GB2-01":54.02675103959072,"GB2-02":27.610135698210527,"GB2-03":30.549441181835455,"GB2-05":44.85922359902054,"GB2-06":30.541429111812185,"GB2-07":66.08924139036272,"GB2-08":25.366216398962596}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.324302104748774,"none":38.554425102550525},"reasoning_agg":{"medium":{"max":63.10196361472715,"mean":37.324302104748774,"min":20.826508924484237},"none":{"max":66.08924139036272,"mean":38.554425102550525,"min":25.366216398962596}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.08924139036272,"reasoning_variance":1.2301229978017503},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.10196361472715,"expected_score":39.82486466556435,"reliability_score":73.00357736447071,"uncertainty_avg":26.996422635529292,"uncertainty_penalty":2.500562560815574},"none":{"ceiling_score":66.08924139036272,"expected_score":39.649312278826514,"reliability_score":91.15217583254382,"uncertainty_avg":8.847824167456185,"uncertainty_penalty":1.0948871762759893}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:a57de75253bd5178","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302952},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":15,"cost_basis_counts":{"provider_reported":27},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.2996388,"mean":0.08564151856,"median":0.0495450162,"min":0.0057139812,"recorded_attempt_count":27,"run_count":15,"total":1.2846227784},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":40.34170066301551,"none":39.644261976279},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["error","length","stop"],"indexed_attempts":27,"output_token_observations":27,"total_output_tokens":643548},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5714285714285714,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"repaired_admitted":2,"repaired_rate":0.2857142857142857}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:01Z","match_totals_all":{"draws":261,"losses":420,"wins":397},"match_totals_tracks":{"medium":{"draws":125,"losses":221,"wins":184},"none":{"draws":136,"losses":199,"wins":213}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":69.21005238359456,"mean":37.8438557392716,"min":19.841275546599956},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":32,"losses":51,"wins":33},"GB2-02":{"draws":64,"losses":7,"wins":5},"GB2-03":{"draws":39,"losses":15,"wins":14},"GB2-04":{"draws":50,"losses":22,"wins":22},"GB2-05":{"draws":0,"losses":117,"wins":89},"GB2-06":{"draws":3,"losses":89,"wins":118},"GB2-07":{"draws":0,"losses":94,"wins":114},"GB2-08":{"draws":73,"losses":25,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":50,"losses":22,"wins":22},"GB2-05":{"draws":0,"losses":71,"wins":39},"GB2-06":{"draws":2,"losses":45,"wins":63},"GB2-07":{"draws":0,"losses":58,"wins":58},"GB2-08":{"draws":73,"losses":25,"wins":2}},"none":{"GB2-01":{"draws":32,"losses":51,"wins":33},"GB2-02":{"draws":64,"losses":7,"wins":5},"GB2-03":{"draws":39,"losses":15,"wins":14},"GB2-05":{"draws":0,"losses":46,"wins":50},"GB2-06":{"draws":1,"losses":44,"wins":55},"GB2-07":{"draws":0,"losses":36,"wins":56}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1555.320457917925,"GB2-05":1365.2585538585686,"GB2-06":1656.371302041338,"GB2-07":1499.0811147075337,"GB2-08":1388.5044432580917},"none":{"GB2-01":1427.5356647847705,"GB2-02":1499.0331584380926,"GB2-03":1453.3589845100641,"GB2-05":1450.2800289578179,"GB2-06":1441.8800041097018,"GB2-07":1554.93981257272}},"per_game_tracks":{"medium":{"GB2-04":40.0964147057753,"GB2-05":28.241575056843985,"GB2-06":69.21005238359456,"GB2-07":44.31918562226375,"GB2-08":19.841275546599956},"none":{"GB2-01":38.853074260758646,"GB2-02":29.295127175194555,"GB2-03":33.0378996400634,"GB2-05":37.62067621907194,"GB2-06":47.87752410093403,"GB2-07":51.181270461651444}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.54218266144462,"none":38.14552881709858},"reasoning_agg":{"medium":{"max":69.21005238359456,"mean":37.54218266144462,"min":19.841275546599956},"none":{"max":51.181270461651444,"mean":38.14552881709858,"min":29.295127175194555}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":69.21005238359456,"reasoning_variance":0.6033461556539592},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":69.21005238359456,"expected_score":50.58808403622483,"reliability_score":73.77408927570025,"uncertainty_avg":26.22591072429975,"uncertainty_penalty":13.045901374780208},"none":{"ceiling_score":51.181270461651444,"expected_score":42.02039676941893,"reliability_score":91.12250272858206,"uncertainty_avg":8.877497271417942,"uncertainty_penalty":3.8748679523203506}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:f5db0c1d0a868367","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001},"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":37.37477392760793},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":3,"repaired_rate":0.375}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:31Z","match_totals_all":{"draws":257,"losses":262,"wins":210},"match_totals_tracks":{"none":{"draws":257,"losses":262,"wins":210}},"model_slug":"gpt-4-1","overall":{"max":60.675097556373565,"mean":37.374773927607926,"min":12.488827301220297},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":47,"wins":57},"GB2-02":{"draws":70,"losses":12,"wins":2},"GB2-03":{"draws":27,"losses":30,"wins":25},"GB2-04":{"draws":66,"losses":14,"wins":4},"GB2-05":{"draws":0,"losses":64,"wins":28},"GB2-06":{"draws":10,"losses":34,"wins":44},"GB2-07":{"draws":0,"losses":45,"wins":39},"GB2-08":{"draws":79,"losses":16,"wins":11}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":5,"losses":47,"wins":57},"GB2-02":{"draws":70,"losses":12,"wins":2},"GB2-03":{"draws":27,"losses":30,"wins":25},"GB2-04":{"draws":66,"losses":14,"wins":4},"GB2-05":{"draws":0,"losses":64,"wins":28},"GB2-06":{"draws":10,"losses":34,"wins":44},"GB2-07":{"draws":0,"losses":45,"wins":39},"GB2-08":{"draws":79,"losses":16,"wins":11}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1591.5902539682866,"GB2-02":1463.4359726589596,"GB2-03":1525.8397181307937,"GB2-04":1469.2709415655665,"GB2-05":1184.8550619458447,"GB2-06":1564.774398115172,"GB2-07":1549.1610657525957,"GB2-08":1415.6268161240855}},"per_game_tracks":{"none":{"GB2-01":56.353504319456164,"GB2-02":21.690874544258786,"GB2-03":44.74207105225406,"GB2-04":27.37461139902881,"GB2-05":12.488827301220297,"GB2-06":60.675097556373565,"GB2-07":50.41579682248144,"GB2-08":25.257408425790306}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":37.374773927607926},"reasoning_agg":{"none":{"max":60.675097556373565,"mean":37.374773927607926,"min":12.488827301220297}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.675097556373565},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":60.675097556373565,"expected_score":38.933770428215624,"reliability_score":91.44532424872008,"uncertainty_avg":8.554675751279921,"uncertainty_penalty":1.558996500607698}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:c03104ecd4a13abe","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":40.076067521730096},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":6,"repaired_rate":0.75}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:26:41Z","match_totals_all":{"draws":183,"losses":221,"wins":240},"match_totals_tracks":{"medium":{"draws":183,"losses":221,"wins":240}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":53.725778913783415,"mean":37.29498316942586,"min":22.092590644226938},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":51,"wins":51},"GB2-02":{"draws":90,"losses":22,"wins":4},"GB2-04":{"draws":79,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":51,"wins":57},"GB2-07":{"draws":0,"losses":52,"wins":62},"GB2-08":{"draws":10,"losses":30,"wins":58}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":51,"wins":51},"GB2-02":{"draws":90,"losses":22,"wins":4},"GB2-04":{"draws":79,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":51,"wins":57},"GB2-07":{"draws":0,"losses":52,"wins":62},"GB2-08":{"draws":10,"losses":30,"wins":58}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1482.9632959237965,"GB2-02":1473.889844365115,"GB2-04":1461.3622341881628,"GB2-05":1601.2056239341523,"GB2-07":1533.621615846795,"GB2-08":1674.6742605175516}},"per_game_tracks":{"medium":{"GB2-01":42.8706174363605,"GB2-02":22.092590644226938,"GB2-04":23.4947403350086,"GB2-05":50.54275135535724,"GB2-07":47.72992644564387,"GB2-08":53.725778913783415}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.29498316942586},"reasoning_agg":{"medium":{"max":53.725778913783415,"mean":37.29498316942586,"min":22.092590644226938}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":53.725778913783415},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":53.725778913783415,"expected_score":42.01937616343178,"reliability_score":74.79334318260108,"uncertainty_avg":25.206656817398926,"uncertainty_penalty":4.7243929940059175}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:94f2248333cf147d","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":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},"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-2026-07-30":25},"run_count":16,"token_priced_attempt_count":25,"total":0.3954491500000001},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":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},"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-2026-07-30":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821379},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":40.73000972203922,"none":38.331723252405894},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":7,"repaired_rate":0.4375}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:07Z","match_totals_all":{"draws":552,"losses":922,"wins":798},"match_totals_tracks":{"medium":{"draws":221,"losses":492,"wins":445},"none":{"draws":331,"losses":430,"wins":353}},"model_slug":"gpt-5-4-nano","overall":{"max":65.72313807060283,"mean":36.78761643752565,"min":15.418465089790947},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":77,"losses":188,"wins":113},"GB2-02":{"draws":229,"losses":17,"wins":4},"GB2-03":{"draws":32,"losses":28,"wins":28},"GB2-04":{"draws":62,"losses":9,"wins":25},"GB2-05":{"draws":0,"losses":230,"wins":154},"GB2-06":{"draws":7,"losses":172,"wins":225},"GB2-07":{"draws":0,"losses":174,"wins":118},"GB2-08":{"draws":145,"losses":104,"wins":131}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":26,"losses":129,"wins":33},"GB2-02":{"draws":75,"losses":3,"wins":0},"GB2-04":{"draws":62,"losses":9,"wins":25},"GB2-05":{"draws":0,"losses":94,"wins":112},"GB2-06":{"draws":6,"losses":86,"wins":118},"GB2-07":{"draws":0,"losses":112,"wins":80},"GB2-08":{"draws":52,"losses":59,"wins":77}},"none":{"GB2-01":{"draws":51,"losses":59,"wins":80},"GB2-02":{"draws":154,"losses":14,"wins":4},"GB2-03":{"draws":32,"losses":28,"wins":28},"GB2-05":{"draws":0,"losses":136,"wins":42},"GB2-06":{"draws":1,"losses":86,"wins":107},"GB2-07":{"draws":0,"losses":62,"wins":38},"GB2-08":{"draws":93,"losses":45,"wins":54}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1213.8022511283734,"GB2-02":1482.129902029356,"GB2-04":1564.996519212638,"GB2-05":1548.6652469966723,"GB2-06":1608.6886921793475,"GB2-07":1421.8563076431074,"GB2-08":1610.5029346193264},"none":{"GB2-01":1602.4391919461466,"GB2-02":1471.396359014816,"GB2-03":1508.3524419563448,"GB2-05":1236.6737860033923,"GB2-06":1508.7080123574883,"GB2-07":1377.7199812397787,"GB2-08":1535.6791586355407}},"per_game_tracks":{"medium":{"GB2-01":15.418465089790947,"GB2-02":25.578831533804646,"GB2-04":45.26997029285312,"GB2-05":47.02166558579286,"GB2-06":65.72313807060283,"GB2-07":38.013798787289424,"GB2-08":48.084198694140696},"none":{"GB2-01":57.22166014466003,"GB2-02":23.617486633688323,"GB2-03":42.304281381765435,"GB2-05":17.314483317000402,"GB2-06":54.921126092380206,"GB2-07":33.70010205201074,"GB2-08":39.2429231453361}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.903544958605444,"none":35.671687916445855},"reasoning_agg":{"medium":{"max":65.72313807060283,"mean":37.903544958605444,"min":15.418465089790947},"none":{"max":57.22166014466003,"mean":35.671687916445855,"min":17.314483317000402}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.72313807060283,"reasoning_variance":2.2318570421595894},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":65.72313807060283,"expected_score":45.13600550066493,"reliability_score":92.51646262027712,"uncertainty_avg":7.483537379722882,"uncertainty_penalty":7.232460542059485},"none":{"ceiling_score":57.22166014466003,"expected_score":39.11109071353274,"reliability_score":92.07939410290778,"uncertainty_avg":7.920605897092222,"uncertainty_penalty":3.439402797086885}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:fa0cf056c5665489","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":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},"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":2.0151682500000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":2.0151682500000003},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":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},"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-2026-07-30":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":44.591590451455545,"none":28.63144123682781},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":2,"repaired_rate":0.25}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:18Z","match_totals_all":{"draws":586,"losses":508,"wins":435},"match_totals_tracks":{"medium":{"draws":250,"losses":247,"wins":308},"none":{"draws":336,"losses":261,"wins":127}},"model_slug":"gpt-5-4-mini","overall":{"max":62.06281243846746,"mean":36.61151584414168,"min":10.185410895530666},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":83,"wins":75},"GB2-02":{"draws":166,"losses":5,"wins":3},"GB2-03":{"draws":125,"losses":24,"wins":16},"GB2-04":{"draws":118,"losses":24,"wins":36},"GB2-05":{"draws":0,"losses":112,"wins":100},"GB2-06":{"draws":18,"losses":88,"wins":98},"GB2-07":{"draws":0,"losses":122,"wins":72},"GB2-08":{"draws":115,"losses":50,"wins":35}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":39,"wins":53},"GB2-02":{"draws":84,"losses":3,"wins":3},"GB2-03":{"draws":48,"losses":20,"wins":15},"GB2-04":{"draws":61,"losses":9,"wins":20},"GB2-05":{"draws":0,"losses":48,"wins":72},"GB2-06":{"draws":12,"losses":42,"wins":52},"GB2-07":{"draws":0,"losses":48,"wins":58},"GB2-08":{"draws":41,"losses":38,"wins":35}},"none":{"GB2-01":{"draws":40,"losses":44,"wins":22},"GB2-02":{"draws":82,"losses":2,"wins":0},"GB2-03":{"draws":77,"losses":4,"wins":1},"GB2-04":{"draws":57,"losses":15,"wins":16},"GB2-05":{"draws":0,"losses":64,"wins":28},"GB2-06":{"draws":6,"losses":46,"wins":46},"GB2-07":{"draws":0,"losses":74,"wins":14},"GB2-08":{"draws":74,"losses":12,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1613.2596975548165,"GB2-02":1478.9493057309376,"GB2-03":1485.5548858435868,"GB2-04":1561.7564985722227,"GB2-05":1568.875101313137,"GB2-06":1574.0883296357088,"GB2-07":1545.2161928372725,"GB2-08":1436.6611574632266},"none":{"GB2-01":1392.215360433307,"GB2-02":1469.565751019137,"GB2-03":1480.7237122491786,"GB2-04":1470.7557500321805,"GB2-05":1348.5279664398565,"GB2-06":1365.4665711563578,"GB2-07":1144.1874341325886,"GB2-08":1439.4052725343836}},"per_game_tracks":{"medium":{"GB2-01":58.415585713195995,"GB2-02":25.554134372396923,"GB2-03":38.63707357709248,"GB2-04":44.441938728209706,"GB2-05":49.214571951063434,"GB2-06":62.06281243846746,"GB2-07":50.492651104691994,"GB2-08":27.91395572652641},"none":{"GB2-01":34.877002635313595,"GB2-02":23.086494711467868,"GB2-03":37.860150083019626,"GB2-04":27.82354680882762,"GB2-05":27.935953546031328,"GB2-06":39.705796487312476,"GB2-07":10.185410895530666,"GB2-08":27.577174727119328}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":44.59159045145555,"none":28.63144123682781},"reasoning_agg":{"medium":{"max":62.06281243846746,"mean":44.59159045145555,"min":25.554134372396923},"none":{"max":39.705796487312476,"mean":28.63144123682781,"min":10.185410895530666}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":62.06281243846746,"reasoning_variance":15.96014921462774},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":62.06281243846746,"expected_score":46.344441569214574,"reliability_score":93.8870375926252,"uncertainty_avg":6.1129624073748,"uncertainty_penalty":1.7528511177590218},"none":{"ceiling_score":39.705796487312476,"expected_score":28.419613598102316,"reliability_score":91.355442607025,"uncertainty_avg":8.644557392975,"uncertainty_penalty":-0.21182763872549515}}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:f60a5042bde2be06","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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},"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-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-30":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-30":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999},"historical-provider-setting-intensive":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":29,"cell_count":24,"cost_basis_counts":{"estimated":40,"local_standard_estimate":29},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":19,"max":0.17217,"mean":0.08358424999999998,"median":0.08653749999999999,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-30":56},"recorded_attempt_count":40,"run_count":48,"token_priced_attempt_count":29,"total":4.201686},"codegen_latency_ms":{"attempt_count":29,"max_ms":130647,"mean_ms":59683.958333333336,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":13,"max_ms":130647,"mean_ms":108464.0,"min_ms":46796,"run_count":8}},"codegen_output_tokens":{"attempt_count":69,"output_max":15813,"output_mean":8194.3125,"output_min":2653,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":21,"output_max":14517,"output_mean":8935.125,"output_min":5431,"run_count":8}},"display_name":"O3","economics":{"all":41.88024973578258,"highest":40.145487538652965,"medium":45.78379908119175,"none":32.993705903564226},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":93,"output_token_observations":69,"reasoning_token_observations":13,"total_output_tokens":393327,"total_reasoning_output_tokens":26752,"total_visible_output_tokens":24077,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.5,"model_code_failures":4},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.59375,"model_code_failure_rate":0.40625,"model_code_failures":13}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-08-05T05:17:46Z","match_totals_all":{"draws":383,"losses":871,"wins":855},"match_totals_tracks":{"highest":{"draws":122,"losses":515,"wins":546},"medium":{"draws":157,"losses":222,"wins":247},"none":{"draws":104,"losses":134,"wins":62}},"model_slug":"o3","overall":{"max":65.54813103397758,"mean":35.19701876585024,"min":24.102373476112174},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-01":47.90487405871482,"GB2-03":31.228907975804475,"GB2-05":40.20081700407619,"GB2-06":50.99483797073365,"GB2-07":40.03071689347571,"GB2-08":30.512771329112983},"per_game_all":{"GB2-01":40.42996644084463,"GB2-06":50.863075384368095,"GB2-07":47.481433584845945,"GB2-08":28.746523533071628},"per_game_match_totals_all":{"GB2-01":{"draws":58,"losses":154,"wins":136},"GB2-03":{"draws":20,"losses":12,"wins":12},"GB2-04":{"draws":67,"losses":12,"wins":9},"GB2-05":{"draws":0,"losses":171,"wins":209},"GB2-06":{"draws":35,"losses":179,"wins":188},"GB2-07":{"draws":0,"losses":234,"wins":212},"GB2-08":{"draws":203,"losses":109,"wins":89}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":67,"wins":95},"GB2-03":{"draws":20,"losses":12,"wins":12},"GB2-05":{"draws":0,"losses":123,"wins":145},"GB2-06":{"draws":7,"losses":95,"wins":120},"GB2-07":{"draws":0,"losses":155,"wins":115},"GB2-08":{"draws":83,"losses":63,"wins":59}},"medium":{"GB2-01":{"draws":17,"losses":46,"wins":35},"GB2-04":{"draws":67,"losses":12,"wins":9},"GB2-05":{"draws":0,"losses":48,"wins":64},"GB2-06":{"draws":10,"losses":42,"wins":50},"GB2-07":{"draws":0,"losses":42,"wins":60},"GB2-08":{"draws":63,"losses":32,"wins":29}},"none":{"GB2-01":{"draws":29,"losses":41,"wins":6},"GB2-06":{"draws":18,"losses":42,"wins":18},"GB2-07":{"draws":0,"losses":37,"wins":37},"GB2-08":{"draws":57,"losses":14,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1467.7917400253573,"GB2-06":1489.5817515167591,"GB2-07":1536.0644201117823,"GB2-08":1466.9485401104564},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1555.7883171781857,"GB2-03":1476.9889629953232,"GB2-05":1511.0897511504677,"GB2-06":1506.2972836372262,"GB2-07":1473.3384324946082,"GB2-08":1498.627888866674},"medium":{"GB2-01":1494.2465984289327,"GB2-04":1463.6610917058263,"GB2-05":1546.9217609319278,"GB2-06":1607.5937026330773,"GB2-07":1624.3448206991122,"GB2-08":1466.4297670164335},"none":{"GB2-01":1353.3403044689535,"GB2-06":1354.8542682799737,"GB2-07":1510.5100071416261,"GB2-08":1435.7879644482614}},"per_game_tracks":{"highest":{"GB2-01":47.90487405871482,"GB2-03":31.228907975804475,"GB2-05":40.20081700407619,"GB2-06":50.99483797073365,"GB2-07":40.03071689347571,"GB2-08":30.512771329112983},"medium":{"GB2-01":45.6739398929183,"GB2-04":26.534569513484524,"GB2-05":47.02325201056916,"GB2-06":65.54813103397758,"GB2-07":58.2984762422112,"GB2-08":31.624425793989726},"none":{"GB2-01":27.71108537090077,"GB2-06":36.04625714839305,"GB2-07":44.1151076188509,"GB2-08":24.102373476112174}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.24014138419697,"medium":42.60662589311128,"none":27.744289020242476},"reasoning_agg":{"highest":{"max":50.99483797073365,"mean":35.24014138419697,"min":30.512771329112983},"medium":{"max":65.54813103397758,"mean":42.60662589311128,"min":26.534569513484524},"none":{"max":44.1151076188509,"mean":27.744289020242476,"min":24.102373476112174}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":65.54813103397758,"expected_score":37.494075465309606,"reasoning_variance":14.862336872868802,"reliability_score":68.21971510172688,"uncertainty_avg":31.780284898273116,"uncertainty_penalty":2.297056699459368},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.99483797073365,"expected_score":30.69055317987772,"reliability_score":47.86399368657385,"uncertainty_avg":52.13600631342615,"uncertainty_penalty":-4.549588204319246},"medium":{"ceiling_score":65.54813103397758,"expected_score":45.74233248505317,"reliability_score":94.82631407518608,"uncertainty_avg":5.173685924813929,"uncertainty_penalty":3.13570659194189},"none":{"ceiling_score":44.1151076188509,"expected_score":31.874232156180998,"reliability_score":60.29338144711172,"uncertainty_avg":39.70661855288828,"uncertainty_penalty":4.129943135938522}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:c77180cf8fb08edd","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528459999999995}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007},"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":34.04254490373653},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":8,"repaired_rate":1.0}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:34:43Z","match_totals_all":{"draws":315,"losses":290,"wins":221},"match_totals_tracks":{"medium":{"draws":315,"losses":290,"wins":221}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":51.82300342768883,"mean":34.04254490373653,"min":23.203770649071114},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":43,"wins":42},"GB2-02":{"draws":86,"losses":3,"wins":3},"GB2-03":{"draws":31,"losses":20,"wins":17},"GB2-04":{"draws":84,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":58,"wins":64},"GB2-06":{"draws":0,"losses":71,"wins":51},"GB2-07":{"draws":0,"losses":73,"wins":33},"GB2-08":{"draws":91,"losses":15,"wins":6}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":23,"losses":43,"wins":42},"GB2-02":{"draws":86,"losses":3,"wins":3},"GB2-03":{"draws":31,"losses":20,"wins":17},"GB2-04":{"draws":84,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":58,"wins":64},"GB2-06":{"draws":0,"losses":71,"wins":51},"GB2-07":{"draws":0,"losses":73,"wins":33},"GB2-08":{"draws":91,"losses":15,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1501.4383086612108,"GB2-02":1485.6883786648543,"GB2-03":1452.3307063559512,"GB2-04":1485.0261871880703,"GB2-05":1611.8150260457114,"GB2-06":1417.594146627393,"GB2-07":1307.8916232961728,"GB2-08":1436.7720758672476}},"per_game_tracks":{"medium":{"GB2-01":44.92433554994799,"GB2-02":23.203770649071114,"GB2-03":29.900297866687094,"GB2-04":27.287196375393837,"GB2-05":51.82300342768883,"GB2-06":44.08045186567497,"GB2-07":25.202311210174184,"GB2-08":25.918992285254213}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.04254490373653},"reasoning_agg":{"medium":{"max":51.82300342768883,"mean":34.04254490373653,"min":23.203770649071114}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":51.82300342768883},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":51.82300342768883,"expected_score":32.030109257581614,"reliability_score":72.95355384974127,"uncertainty_avg":27.046446150258735,"uncertainty_penalty":-2.0124356461549127}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:3efce85b482761c7","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.5164659199999999},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":43.52384843515179,"none":27.309041386370055},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-08-05T03:48:47Z","match_totals_all":{"draws":373,"losses":468,"wins":338},"match_totals_tracks":{"medium":{"draws":198,"losses":216,"wins":222},"none":{"draws":175,"losses":252,"wins":116}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":74.1617078908414,"mean":32.59000467698186,"min":8.83134021951195},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":95,"wins":59},"GB2-02":{"draws":171,"losses":4,"wins":1},"GB2-04":{"draws":57,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":116,"wins":108},"GB2-06":{"draws":7,"losses":102,"wins":90},"GB2-07":{"draws":0,"losses":123,"wins":75},"GB2-08":{"draws":94,"losses":20,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":18,"losses":40,"wins":40},"GB2-02":{"draws":81,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":64,"wins":60},"GB2-06":{"draws":5,"losses":31,"wins":64},"GB2-07":{"draws":0,"losses":57,"wins":57},"GB2-08":{"draws":94,"losses":20,"wins":0}},"none":{"GB2-01":{"draws":26,"losses":55,"wins":19},"GB2-02":{"draws":90,"losses":0,"wins":0},"GB2-04":{"draws":57,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":52,"wins":48},"GB2-06":{"draws":2,"losses":71,"wins":26},"GB2-07":{"draws":0,"losses":66,"wins":18}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1530.3703249093664,"GB2-02":1489.1136087685727,"GB2-05":1579.9273324684477,"GB2-06":1706.3705923810853,"GB2-07":1471.5202267893505,"GB2-08":1432.9907321597134},"none":{"GB2-01":1351.2113457571206,"GB2-02":1472.4062283762817,"GB2-04":1474.1281441770377,"GB2-05":1504.6944028280163,"GB2-06":1276.4806787457837,"GB2-07":1131.5762374150424}},"per_game_tracks":{"medium":{"GB2-01":47.751145429420006,"GB2-02":23.34842170383965,"GB2-05":48.778489355144025,"GB2-06":74.1617078908414,"GB2-07":41.70177239399337,"GB2-08":25.40155383767231},"none":{"GB2-01":30.350197668676998,"GB2-02":24.06441481400451,"GB2-04":27.51487556975524,"GB2-05":42.83286645498502,"GB2-06":30.26055359128659,"GB2-07":8.83134021951195}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.503504840575566,"none":24.676504513388153},"reasoning_agg":{"medium":{"max":74.1617078908414,"mean":40.503504840575566,"min":23.34842170383965},"none":{"max":42.83286645498502,"mean":24.676504513388153,"min":8.83134021951195}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":74.1617078908414,"reasoning_variance":15.827000327187413},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":74.1617078908414,"expected_score":44.86351015040852,"reliability_score":73.72884873242621,"uncertainty_avg":26.27115126757378,"uncertainty_penalty":4.360005309832957},"none":{"ceiling_score":42.83286645498502,"expected_score":27.229123473359817,"reliability_score":91.16839029642475,"uncertainty_avg":8.831609703575259,"uncertainty_penalty":2.5526189599716638}}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:b1da6d00e44bbdf5","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796000000001},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":28.794662059114653,"none":38.20459574532885},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.21428571428571427,"model_code_failures":3,"repaired_admitted":4,"repaired_rate":0.2857142857142857},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.35714285714285715}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:16Z","match_totals_all":{"draws":781,"losses":713,"wins":556},"match_totals_tracks":{"medium":{"draws":366,"losses":298,"wins":174},"none":{"draws":415,"losses":415,"wins":382}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":52.594117482982824,"mean":31.93510151640261,"min":18.97110273604848},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":130,"wins":107},"GB2-02":{"draws":198,"losses":5,"wins":3},"GB2-03":{"draws":130,"losses":94,"wins":70},"GB2-04":{"draws":50,"losses":22,"wins":6},"GB2-05":{"draws":0,"losses":192,"wins":194},"GB2-06":{"draws":8,"losses":112,"wins":76},"GB2-07":{"draws":0,"losses":106,"wins":88},"GB2-08":{"draws":328,"losses":52,"wins":12}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":13,"losses":28,"wins":29},"GB2-02":{"draws":101,"losses":1,"wins":0},"GB2-03":{"draws":59,"losses":48,"wins":31},"GB2-04":{"draws":50,"losses":22,"wins":6},"GB2-05":{"draws":0,"losses":122,"wins":72},"GB2-06":{"draws":4,"losses":54,"wins":30},"GB2-08":{"draws":139,"losses":23,"wins":6}},"none":{"GB2-01":{"draws":54,"losses":102,"wins":78},"GB2-02":{"draws":97,"losses":4,"wins":3},"GB2-03":{"draws":71,"losses":46,"wins":39},"GB2-05":{"draws":0,"losses":70,"wins":122},"GB2-06":{"draws":4,"losses":58,"wins":46},"GB2-07":{"draws":0,"losses":106,"wins":88},"GB2-08":{"draws":189,"losses":29,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1485.3773249800106,"GB2-02":1490.2086713176134,"GB2-03":1466.3175616005683,"GB2-04":1450.4106272254921,"GB2-05":1384.5936547110098,"GB2-06":1323.5567794486105,"GB2-08":1444.586080274788},"none":{"GB2-01":1523.7215971564779,"GB2-02":1474.448849917776,"GB2-03":1454.8627401134768,"GB2-05":1608.9598470652513,"GB2-06":1270.3210113293824,"GB2-07":1548.4789026376432,"GB2-08":1423.3405534391286}},"per_game_tracks":{"medium":{"GB2-01":41.34256667887432,"GB2-02":18.97110273604848,"GB2-03":31.88151024956463,"GB2-04":20.33720025505064,"GB2-05":29.83100441041674,"GB2-06":33.16163840382044,"GB2-08":26.037611680027343},"none":{"GB2-01":49.20338899029913,"GB2-02":25.188695148003053,"GB2-03":33.72130392267117,"GB2-05":52.594117482982824,"GB2-06":29.784727597962565,"GB2-07":50.644464757221996,"GB2-08":26.29547231816128}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.109914524444687,"none":36.76028850836054},"reasoning_agg":{"medium":{"max":41.34256667887432,"mean":27.109914524444687,"min":18.97110273604848},"none":{"max":52.594117482982824,"mean":36.76028850836054,"min":25.188695148003053}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":52.594117482982824,"reasoning_variance":9.650373983915852},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":41.34256667887432,"expected_score":23.829389165023112,"reliability_score":60.88795234392013,"uncertainty_avg":39.11204765607987,"uncertainty_penalty":-3.280525359421574},"none":{"ceiling_score":52.594117482982824,"expected_score":36.91388265942721,"reliability_score":94.10228451592243,"uncertainty_avg":5.897715484077561,"uncertainty_penalty":0.1535941510666703}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:3c5fef0475ec7b6e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139173999999999}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":30.623488700978687,"none":36.02354942102359},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:51Z","match_totals_all":{"draws":391,"losses":435,"wins":340},"match_totals_tracks":{"highest":{"draws":153,"losses":285,"wins":194},"none":{"draws":238,"losses":150,"wins":146}},"model_slug":"tencent-hy3-preview","overall":{"max":71.41435556334146,"mean":31.1411717990917,"min":9.407687981142418},"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":"partial","per_game":{"GB2-01":54.06767438679486,"GB2-02":9.407687981142418,"GB2-04":19.444697310565857,"GB2-05":44.75054191596875,"GB2-06":30.65897798586819,"GB2-07":26.48344557638085,"GB2-08":29.551395750129856},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":54,"wins":105},"GB2-02":{"draws":115,"losses":18,"wins":1},"GB2-03":{"draws":27,"losses":28,"wins":29},"GB2-04":{"draws":100,"losses":32,"wins":22},"GB2-05":{"draws":0,"losses":111,"wins":85},"GB2-06":{"draws":0,"losses":63,"wins":25},"GB2-07":{"draws":0,"losses":65,"wins":37},"GB2-08":{"draws":114,"losses":64,"wins":36}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":35,"wins":45},"GB2-02":{"draws":51,"losses":12,"wins":1},"GB2-04":{"draws":58,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":48,"wins":46},"GB2-06":{"draws":0,"losses":63,"wins":25},"GB2-07":{"draws":0,"losses":65,"wins":37},"GB2-08":{"draws":26,"losses":43,"wins":33}},"none":{"GB2-01":{"draws":17,"losses":19,"wins":60},"GB2-02":{"draws":64,"losses":6,"wins":0},"GB2-03":{"draws":27,"losses":28,"wins":29},"GB2-04":{"draws":42,"losses":13,"wins":15},"GB2-05":{"draws":0,"losses":63,"wins":39},"GB2-08":{"draws":88,"losses":21,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1588.8200827421863,"GB2-02":1436.1191021856469,"GB2-04":1443.4364488018932,"GB2-05":1542.9564297708673,"GB2-06":1299.898542312292,"GB2-07":1320.9276344632324,"GB2-08":1468.7095025143608},"none":{"GB2-01":1734.2538039468136,"GB2-02":1454.0917807935598,"GB2-03":1450.2133962405546,"GB2-04":1509.5599956004069,"GB2-05":1379.0311903903728,"GB2-08":1436.4194727656443}},"per_game_tracks":{"highest":{"GB2-01":54.06767438679486,"GB2-02":9.407687981142418,"GB2-04":19.444697310565857,"GB2-05":44.75054191596875,"GB2-06":30.65897798586819,"GB2-07":26.48344557638085,"GB2-08":29.551395750129856},"none":{"GB2-01":71.41435556334146,"GB2-02":18.633293372543374,"GB2-03":33.28541772823972,"GB2-04":33.952233073927275,"GB2-05":31.009668601208,"GB2-08":27.84632818688169}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.758653464874232,"none":33.523690133309174},"reasoning_agg":{"highest":{"max":54.06767438679486,"mean":28.758653464874232,"min":9.407687981142418},"none":{"max":71.41435556334146,"mean":33.523690133309174,"min":18.633293372543374}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":71.41435556334146,"reasoning_variance":4.7650366684349414},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.06767438679486,"expected_score":17.746648387444715,"reliability_score":69.411271067186,"uncertainty_avg":30.58872893281401,"uncertainty_penalty":-11.012005077429517},"none":{"ceiling_score":71.41435556334146,"expected_score":37.320596167316516,"reliability_score":90.41990069031253,"uncertainty_avg":9.580099309687474,"uncertainty_penalty":3.7969060340073426}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:6ff688fbb800bfea","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.0165325}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.016532500000000002}},"codegen_cost_usd":{"admitted_cell_count":10,"cell_count":14,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0092087,"mean":0.004466478571428571,"median":0.0042425399999999995,"min":0.00144036,"recorded_attempt_count":23,"run_count":14,"total":0.0625307},"codegen_latency_ms":{"attempt_count":23,"max_ms":550842,"mean_ms":222264.07142857142,"min_ms":41984,"run_count":14},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":550842,"mean_ms":354649.85714285716,"min_ms":219950,"run_count":7},"none":{"attempt_count":8,"max_ms":161392,"mean_ms":89878.28571428571,"min_ms":41984,"run_count":7}},"codegen_output_tokens":{"attempt_count":23,"output_max":12552,"output_mean":5500.928571428572,"output_min":1283,"run_count":14},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":12552,"output_mean":8851.57142857143,"output_min":6019,"run_count":7},"none":{"attempt_count":8,"output_max":4235,"output_mean":2150.285714285714,"output_min":1283,"run_count":7}},"display_name":"Gemma 4 31B","economics":{"medium":37.22399240106636,"none":30.588833048590292},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":23,"total_output_tokens":77013},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":4,"evaluated_cells":7,"failed_game_aliases":["GB2-02","GB2-03","GB2-08"],"infra_excluded_game_aliases":["GB2-01"],"infra_failures_excluded":1,"model_code_failure_rate":0.42857142857142855,"model_code_failures":3,"repaired_admitted":4,"repaired_rate":0.5714285714285714},"baseline":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.7142857142857143,"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.14285714285714285}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-08-05T03:57:18Z","match_totals_all":{"draws":260,"losses":447,"wins":331},"match_totals_tracks":{"medium":{"draws":74,"losses":194,"wins":168},"none":{"draws":186,"losses":253,"wins":163}},"model_slug":"google-gemma-4-31b-it","overall":{"max":45.90001524707614,"mean":30.898264549296297,"min":14.548948613994082},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":38,"wins":55},"GB2-04":{"draws":140,"losses":15,"wins":19},"GB2-05":{"draws":0,"losses":124,"wins":92},"GB2-06":{"draws":3,"losses":135,"wins":82},"GB2-07":{"draws":0,"losses":114,"wins":80},"GB2-08":{"draws":92,"losses":21,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":73,"losses":6,"wins":9},"GB2-05":{"draws":0,"losses":57,"wins":65},"GB2-06":{"draws":1,"losses":76,"wins":41},"GB2-07":{"draws":0,"losses":55,"wins":53}},"none":{"GB2-01":{"draws":25,"losses":38,"wins":55},"GB2-04":{"draws":67,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":67,"wins":27},"GB2-06":{"draws":2,"losses":59,"wins":41},"GB2-07":{"draws":0,"losses":59,"wins":27},"GB2-08":{"draws":92,"losses":21,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1492.8974532015468,"GB2-05":1549.707459487237,"GB2-06":1353.3784605717633,"GB2-07":1429.5635626395624},"none":{"GB2-01":1479.4739373802697,"GB2-04":1491.3691141009099,"GB2-05":1206.244527485814,"GB2-06":1373.38682774224,"GB2-07":1288.3055324602838,"GB2-08":1436.356567823582}},"per_game_tracks":{"medium":{"GB2-04":28.508028292488625,"GB2-05":45.90001524707614,"GB2-06":37.13197671164298,"GB2-07":37.35594935305769},"none":{"GB2-01":44.46648998691777,"GB2-04":31.480599265900732,"GB2-05":14.548948613994082,"GB2-06":40.63225251749573,"GB2-07":24.48890361547792,"GB2-08":27.91580429175553}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.364092867730605,"none":29.432436230861992},"reasoning_agg":{"medium":{"max":45.90001524707614,"mean":32.364092867730605,"min":28.508028292488625},"none":{"max":44.46648998691777,"mean":29.432436230861992,"min":14.548948613994082}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":45.90001524707614,"reasoning_variance":2.931656636868613},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.90001524707614,"expected_score":41.44478432603168,"reliability_score":74.89661653772636,"uncertainty_avg":25.103383462273637,"uncertainty_penalty":9.080691458301075},"none":{"ceiling_score":44.46648998691777,"expected_score":31.32897375240387,"reliability_score":93.77723730003919,"uncertainty_avg":6.222762699960806,"uncertainty_penalty":1.8965375215418767}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:9efcd5e1b19ad9d9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0221782524,"mean":0.00999808046,"median":0.009941171,"min":0.00212373,"recorded_attempt_count":14,"run_count":8,"total":0.07998464368},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.050973330659999996},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00408087,"mean":0.0022664345375,"median":0.0017928150000000001,"min":0.0013289177,"recorded_attempt_count":11,"run_count":8,"total":0.0181314763}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.050973330659999996},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00408087,"mean":0.0022664345375,"median":0.0017928150000000001,"min":0.0013289177,"recorded_attempt_count":11,"run_count":8,"total":0.0181314763},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0221782524,"mean":0.00999808046,"median":0.009941171,"min":0.00212373,"recorded_attempt_count":14,"run_count":8,"total":0.07998464368000001}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":49},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0221782524,"mean":0.005150116054583333,"median":0.00311373,"min":0.0013289177,"recorded_attempt_count":49,"run_count":32,"total":0.14908945063999998},"codegen_latency_ms":{"attempt_count":25,"max_ms":1394682,"mean_ms":281124.875,"min_ms":22331,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1394682,"mean_ms":494109.375,"min_ms":61403,"run_count":8},"none":{"attempt_count":11,"max_ms":129944,"mean_ms":68140.375,"min_ms":22331,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":82048,"output_mean":17675.4375,"output_min":1698,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":82048,"output_mean":31903.25,"output_min":4091,"run_count":8},"none":{"attempt_count":11,"output_max":6315,"output_mean":3447.625,"output_min":1698,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":32.799363452798694,"highest":39.4359988819996,"medium":31.58701354365491,"none":26.078342532879816},"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":282807},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":4,"repaired_rate":0.25},"baseline":{"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,"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":3,"repaired_rate":0.375}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:23:15Z","match_totals_all":{"draws":757,"losses":894,"wins":545},"match_totals_tracks":{"highest":{"draws":149,"losses":217,"wins":170},"medium":{"draws":360,"losses":421,"wins":241},"none":{"draws":248,"losses":256,"wins":134}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":69.71379024439247,"mean":30.823810468802048,"min":9.943666245746922},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-01":33.4805377654376,"GB2-02":28.386103413880857,"GB2-05":47.95611862982329,"GB2-06":32.48264176849661,"GB2-07":69.71379024439247,"GB2-08":24.5968014699668},"per_game_all":{"GB2-02":24.30202932256091,"GB2-05":36.92937605160245,"GB2-06":28.170883631937837,"GB2-07":48.92973319812373,"GB2-08":25.664795059768554},"per_game_match_totals_all":{"GB2-01":{"draws":55,"losses":129,"wins":56},"GB2-02":{"draws":246,"losses":31,"wins":7},"GB2-03":{"draws":57,"losses":48,"wins":35},"GB2-04":{"draws":97,"losses":35,"wins":8},"GB2-05":{"draws":0,"losses":197,"wins":165},"GB2-06":{"draws":3,"losses":228,"wins":101},"GB2-07":{"draws":0,"losses":163,"wins":161},"GB2-08":{"draws":299,"losses":63,"wins":12}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":49,"wins":25},"GB2-02":{"draws":57,"losses":9,"wins":4},"GB2-05":{"draws":0,"losses":44,"wins":52},"GB2-06":{"draws":1,"losses":57,"wins":24},"GB2-07":{"draws":0,"losses":29,"wins":63},"GB2-08":{"draws":73,"losses":29,"wins":2}},"medium":{"GB2-01":{"draws":37,"losses":80,"wins":31},"GB2-02":{"draws":111,"losses":19,"wins":2},"GB2-03":{"draws":18,"losses":21,"wins":15},"GB2-04":{"draws":53,"losses":9,"wins":4},"GB2-05":{"draws":0,"losses":89,"wins":65},"GB2-06":{"draws":1,"losses":101,"wins":58},"GB2-07":{"draws":0,"losses":86,"wins":62},"GB2-08":{"draws":140,"losses":16,"wins":4}},"none":{"GB2-02":{"draws":78,"losses":3,"wins":1},"GB2-03":{"draws":39,"losses":27,"wins":20},"GB2-04":{"draws":44,"losses":26,"wins":4},"GB2-05":{"draws":0,"losses":64,"wins":48},"GB2-06":{"draws":1,"losses":70,"wins":19},"GB2-07":{"draws":0,"losses":48,"wins":36},"GB2-08":{"draws":86,"losses":18,"wins":6}}},"per_game_raw_elo_all":{"GB2-02":1478.272170316656,"GB2-05":1443.5202341638108,"GB2-06":1260.2651616379073,"GB2-07":1534.5362081654232,"GB2-08":1420.8786372472516},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1382.025506422629,"GB2-02":1496.9276220539098,"GB2-05":1559.7911348935588,"GB2-06":1301.2737990682394,"GB2-07":1741.0405753174614,"GB2-08":1410.422225981586},"medium":{"GB2-01":1382.8120697560494,"GB2-02":1466.7374764232438,"GB2-03":1524.4985638630642,"GB2-04":1482.6080624665635,"GB2-05":1345.8203598823284,"GB2-06":1301.6867097939717,"GB2-07":1455.9013049678656,"GB2-08":1427.6670918396599},"none":{"GB2-02":1471.1514124728146,"GB2-03":1438.523896395089,"GB2-04":1376.1312280226116,"GB2-05":1424.9492077155455,"GB2-06":1177.8349760515114,"GB2-07":1406.6667442109426,"GB2-08":1424.5465939205094}},"per_game_tracks":{"highest":{"GB2-01":33.4805377654376,"GB2-02":28.386103413880857,"GB2-05":47.95611862982329,"GB2-06":32.48264176849661,"GB2-07":69.71379024439247,"GB2-08":24.5968014699668},"medium":{"GB2-01":33.05771191946257,"GB2-02":21.190773152388033,"GB2-03":43.00749050094252,"GB2-04":28.801808670018016,"GB2-05":27.320286766981738,"GB2-06":32.46925549155916,"GB2-07":40.84966093971727,"GB2-08":25.99912090816997},"none":{"GB2-02":23.329211401413826,"GB2-03":31.578832477807513,"GB2-04":9.943666245746922,"GB2-05":35.51172275800236,"GB2-06":19.56075363575773,"GB2-07":36.22574841026145,"GB2-08":26.3984628011689}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.699332183133805,"medium":30.549955352489913,"none":25.222143870782425},"reasoning_agg":{"highest":{"max":69.71379024439247,"mean":36.699332183133805,"min":24.5968014699668},"medium":{"max":43.00749050094252,"mean":30.549955352489913,"min":21.190773152388033},"none":{"max":36.22574841026145,"mean":25.222143870782425,"min":9.943666245746922}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":69.71379024439247,"expected_score":25.08356451073817,"reasoning_variance":11.47718831235138,"reliability_score":89.8676418273685,"uncertainty_avg":10.132358172631498,"uncertainty_penalty":-5.740245958063877},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":69.71379024439247,"expected_score":24.75596712424425,"reliability_score":90.83688428638534,"uncertainty_avg":9.16311571361466,"uncertainty_penalty":-11.943365058889555},"medium":{"ceiling_score":43.00749050094252,"expected_score":26.732362222606678,"reliability_score":84.64544088871065,"uncertainty_avg":15.354559111289346,"uncertainty_penalty":-3.8175931298832353},"none":{"ceiling_score":36.22574841026145,"expected_score":23.095494752742137,"reliability_score":91.26948812096254,"uncertainty_avg":8.730511879037467,"uncertainty_penalty":-2.1266491180402873}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:5ca3d328ffb17b98","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.48618750699999996},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.00169122,"recorded_attempt_count":37,"run_count":24,"total":0.06890521579999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"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},"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":0.21411433160000004},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.030685472800000002},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.19736108440000003}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":16,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.00169122,"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":32.2599069408473,"highest":34.182546170823265,"medium":30.70075582283712,"none":35.45466399034528},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"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,"repaired_admitted":5,"repaired_rate":0.625}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:45Z","match_totals_all":{"draws":1189,"losses":1247,"wins":896},"match_totals_tracks":{"highest":{"draws":224,"losses":81,"wins":47},"medium":{"draws":555,"losses":586,"wins":367},"none":{"draws":410,"losses":580,"wins":482}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":62.62712426295049,"mean":30.139545504730307,"min":18.9315557741441},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-01":18.9315557741441,"GB2-02":30.2390924954411,"GB2-04":32.47394764651104,"GB2-06":62.62712426295049,"GB2-08":26.641010675069595},"per_game_all":{"GB2-01":33.70231753929507,"GB2-02":25.16435071330035,"GB2-04":29.622491781966726,"GB2-06":49.24724235319121,"GB2-08":23.56313231648313},"per_game_match_totals_all":{"GB2-01":{"draws":122,"losses":275,"wins":193},"GB2-02":{"draws":339,"losses":33,"wins":12},"GB2-03":{"draws":41,"losses":26,"wins":19},"GB2-04":{"draws":379,"losses":76,"wins":43},"GB2-05":{"draws":0,"losses":269,"wins":225},"GB2-06":{"draws":15,"losses":241,"wins":202},"GB2-07":{"draws":0,"losses":198,"wins":172},"GB2-08":{"draws":293,"losses":129,"wins":30}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":41,"losses":29,"wins":2},"GB2-02":{"draws":56,"losses":11,"wins":3},"GB2-04":{"draws":52,"losses":10,"wins":6},"GB2-06":{"draws":6,"losses":28,"wins":34},"GB2-08":{"draws":69,"losses":3,"wins":2}},"medium":{"GB2-01":{"draws":19,"losses":116,"wins":77},"GB2-02":{"draws":220,"losses":21,"wins":9},"GB2-04":{"draws":217,"losses":57,"wins":16},"GB2-05":{"draws":0,"losses":138,"wins":102},"GB2-06":{"draws":5,"losses":77,"wins":42},"GB2-07":{"draws":0,"losses":101,"wins":97},"GB2-08":{"draws":94,"losses":76,"wins":24}},"none":{"GB2-01":{"draws":62,"losses":130,"wins":114},"GB2-02":{"draws":63,"losses":1,"wins":0},"GB2-03":{"draws":41,"losses":26,"wins":19},"GB2-04":{"draws":110,"losses":9,"wins":21},"GB2-05":{"draws":0,"losses":131,"wins":123},"GB2-06":{"draws":4,"losses":136,"wins":126},"GB2-07":{"draws":0,"losses":97,"wins":75},"GB2-08":{"draws":130,"losses":50,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1389.380805535906,"GB2-02":1488.1815657582563,"GB2-04":1489.1736205530972,"GB2-06":1461.8142909247556,"GB2-08":1411.755558794197},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1251.9402308692768,"GB2-02":1505.0662350094012,"GB2-04":1502.1064415265755,"GB2-06":1588.8776884828033,"GB2-08":1434.8137881433222},"medium":{"GB2-01":1401.8023272025948,"GB2-02":1485.265940417252,"GB2-04":1473.20990283907,"GB2-05":1388.6096661150161,"GB2-06":1354.325516280026,"GB2-07":1477.2820003415932,"GB2-08":1413.6262448047164},"none":{"GB2-01":1514.3998585358459,"GB2-02":1474.2125218481146,"GB2-03":1463.1084595149894,"GB2-04":1492.2045172936457,"GB2-05":1514.79079258633,"GB2-06":1442.2396680114384,"GB2-07":1385.0218716764423,"GB2-08":1386.826643434552}},"per_game_tracks":{"highest":{"GB2-01":18.9315557741441,"GB2-02":30.2390924954411,"GB2-04":32.47394764651104,"GB2-06":62.62712426295049,"GB2-08":26.641010675069595},"medium":{"GB2-01":34.19298039167491,"GB2-02":22.527432167882964,"GB2-04":25.60477558634496,"GB2-05":30.783354882592267,"GB2-06":37.4033081726625,"GB2-07":41.85354162714708,"GB2-08":22.539897931555156},"none":{"GB2-01":47.98241645206621,"GB2-02":22.726527476576994,"GB2-03":35.328921102635334,"GB2-04":30.78875211304417,"GB2-05":43.47068028863717,"GB2-06":47.71129462396064,"GB2-07":34.12023152301707,"GB2-08":21.508488342824627}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.39305901913992,"medium":27.74126447385223,"none":32.28431302119879},"reasoning_agg":{"highest":{"max":62.62712426295049,"mean":30.39305901913992,"min":18.9315557741441},"medium":{"max":41.85354162714708,"mean":27.74126447385223,"min":22.527432167882964},"none":{"max":47.98241645206621,"mean":32.28431302119879,"min":21.508488342824627}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":62.62712426295049,"expected_score":24.9978784255518,"reasoning_variance":4.543048547346562,"reliability_score":82.12298456472493,"uncertainty_avg":17.877015435275077,"uncertainty_penalty":-5.141667079178507},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.62712426295049,"expected_score":21.197787031805866,"reliability_score":84.55389269750205,"uncertainty_avg":15.446107302497945,"uncertainty_penalty":-9.195271987334053},"medium":{"ceiling_score":41.85354162714708,"expected_score":29.09855234700648,"reliability_score":73.67869564235221,"uncertainty_avg":26.321304357647794,"uncertainty_penalty":1.3572878731542488},"none":{"ceiling_score":47.98241645206621,"expected_score":36.7886108322714,"reliability_score":89.35519511933211,"uncertainty_avg":10.644804880667893,"uncertainty_penalty":4.504297811072611}}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:306f6bca3b4c3882","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.5845103399999999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":25.776653397200334,"none":37.896902705966774},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":2,"repaired_rate":0.25}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-08-05T04:33:21Z","match_totals_all":{"draws":373,"losses":569,"wins":370},"match_totals_tracks":{"medium":{"draws":240,"losses":345,"wins":147},"none":{"draws":133,"losses":224,"wins":223}},"model_slug":"minimax-minimax-m3","overall":{"max":51.404796674852406,"mean":30.098700766251334,"min":2.3222203559783994},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":31,"losses":106,"wins":87},"GB2-02":{"draws":140,"losses":17,"wins":1},"GB2-03":{"draws":33,"losses":25,"wins":32},"GB2-04":{"draws":76,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":161,"wins":57},"GB2-06":{"draws":0,"losses":79,"wins":41},"GB2-07":{"draws":0,"losses":106,"wins":98},"GB2-08":{"draws":93,"losses":68,"wins":47}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":68,"wins":27},"GB2-02":{"draws":71,"losses":14,"wins":1},"GB2-04":{"draws":76,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":103,"wins":3},"GB2-06":{"draws":0,"losses":79,"wins":41},"GB2-07":{"draws":0,"losses":55,"wins":61},"GB2-08":{"draws":86,"losses":19,"wins":7}},"none":{"GB2-01":{"draws":24,"losses":38,"wins":60},"GB2-02":{"draws":69,"losses":3,"wins":0},"GB2-03":{"draws":33,"losses":25,"wins":32},"GB2-05":{"draws":0,"losses":58,"wins":54},"GB2-07":{"draws":0,"losses":51,"wins":37},"GB2-08":{"draws":7,"losses":49,"wins":40}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1327.0032979772882,"GB2-02":1445.3018284688678,"GB2-04":1500.5080466753927,"GB2-05":1091.7576172341132,"GB2-06":1350.2598567148952,"GB2-07":1518.0117601373145,"GB2-08":1436.4684130812043},"none":{"GB2-01":1543.4553724122525,"GB2-02":1462.4496711139095,"GB2-03":1480.8755147233076,"GB2-05":1469.2367408862915,"GB2-07":1440.0116718921627,"GB2-08":1523.101241228136}},"per_game_tracks":{"medium":{"GB2-01":25.9976913296341,"GB2-02":13.643544255379368,"GB2-04":29.43239275691567,"GB2-05":2.3222203559783994,"GB2-06":36.860401930611594,"GB2-07":46.29733821571418,"GB2-08":25.882984936169017},"none":{"GB2-01":51.404796674852406,"GB2-02":20.685292976640326,"GB2-03":38.18446384616218,"GB2-05":39.69149287984802,"GB2-07":39.64455151180685,"GB2-08":37.77081834649088}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.930359729410473,"none":35.26704180309219},"reasoning_agg":{"medium":{"max":46.29733821571418,"mean":24.930359729410473,"min":2.3222203559783994},"none":{"max":51.404796674852406,"mean":35.26704180309219,"min":20.685292976640326}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":51.404796674852406,"reasoning_variance":10.336682073681718},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":46.29733821571418,"expected_score":23.82671640678935,"reliability_score":73.09388883277227,"uncertainty_avg":26.90611116722774,"uncertainty_penalty":-1.1036433226211209},"none":{"ceiling_score":51.404796674852406,"expected_score":38.54818419908276,"reliability_score":92.61307619271473,"uncertainty_avg":7.386923807285272,"uncertainty_penalty":3.281142395990571}}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:4f1d1a6fc03112d2","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.214047204}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.11484688800000001,"mean":0.09513821700000001,"median":0.094364214,"min":0.07353490800000001,"recorded_attempt_count":53,"run_count":11,"total":1.042744896},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":5,"cell_count":5,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.097374552,"mean":0.068722872,"median":0.085761432,"min":0.023163,"recorded_attempt_count":17,"run_count":5,"total":0.34361436},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.60040646},"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":28.665869954402904,"none":34.08605740775033},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":11,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.6363636363636364,"model_code_failure_rate":0.36363636363636365,"model_code_failures":4},"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,"repaired_admitted":6,"repaired_rate":0.375}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:26Z","match_totals_all":{"draws":695,"losses":895,"wins":614},"match_totals_tracks":{"medium":{"draws":183,"losses":374,"wins":243},"none":{"draws":512,"losses":521,"wins":371}},"model_slug":"meituan-longcat-2-0","overall":{"max":51.81464157035592,"mean":29.28499351265294,"min":13.631497595831043},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":82,"losses":93,"wins":65},"GB2-02":{"draws":135,"losses":6,"wins":1},"GB2-03":{"draws":96,"losses":63,"wins":53},"GB2-04":{"draws":123,"losses":58,"wins":31},"GB2-05":{"draws":0,"losses":213,"wins":125},"GB2-06":{"draws":26,"losses":195,"wins":151},"GB2-07":{"draws":0,"losses":180,"wins":162},"GB2-08":{"draws":233,"losses":87,"wins":26}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":42,"losses":1,"wins":1},"GB2-03":{"draws":22,"losses":12,"wins":16},"GB2-04":{"draws":69,"losses":36,"wins":9},"GB2-05":{"draws":0,"losses":87,"wins":77},"GB2-06":{"draws":9,"losses":92,"wins":63},"GB2-07":{"draws":0,"losses":81,"wins":59},"GB2-08":{"draws":41,"losses":65,"wins":18}},"none":{"GB2-01":{"draws":82,"losses":93,"wins":65},"GB2-02":{"draws":93,"losses":5,"wins":0},"GB2-03":{"draws":74,"losses":51,"wins":37},"GB2-04":{"draws":54,"losses":22,"wins":22},"GB2-05":{"draws":0,"losses":126,"wins":48},"GB2-06":{"draws":17,"losses":103,"wins":88},"GB2-07":{"draws":0,"losses":99,"wins":103},"GB2-08":{"draws":192,"losses":22,"wins":8}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1491.2765108129372,"GB2-03":1502.1284962693098,"GB2-04":1428.9050722087582,"GB2-05":1471.0699456891364,"GB2-06":1398.2976003952504,"GB2-07":1431.5948380411917,"GB2-08":1408.0654464521704},"none":{"GB2-01":1407.5389657970331,"GB2-02":1471.8760079780336,"GB2-03":1410.7672192302994,"GB2-04":1586.3561576652844,"GB2-05":1198.143112700935,"GB2-06":1478.2567073413627,"GB2-07":1459.7639380942178,"GB2-08":1436.8580197603374}},"per_game_tracks":{"medium":{"GB2-02":18.40784673510266,"GB2-03":35.51286102183472,"GB2-04":13.687976243904558,"GB2-05":37.411492646607414,"GB2-06":40.71582481684514,"GB2-07":36.08163384316626,"GB2-08":18.843454373359577},"none":{"GB2-01":36.76737781757434,"GB2-02":24.33755198695994,"GB2-03":27.14500345598673,"GB2-04":49.225562918867894,"GB2-05":13.631497595831043,"GB2-06":51.81464157035592,"GB2-07":41.888503192541094,"GB2-08":27.878320723885658}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":25.60303589173286,"none":32.96695113357302},"reasoning_agg":{"medium":{"max":40.71582481684514,"mean":25.60303589173286,"min":13.687976243904558},"none":{"max":51.81464157035592,"mean":32.96695113357302,"min":13.631497595831043}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":51.81464157035592,"reasoning_variance":7.363915241840161},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.71582481684514,"expected_score":26.22709441691482,"reliability_score":51.290995606399065,"uncertainty_avg":48.709004393600935,"uncertainty_penalty":0.6240585251819617},"none":{"ceiling_score":51.81464157035592,"expected_score":37.47410990433833,"reliability_score":93.7125318525091,"uncertainty_avg":6.287468147490904,"uncertainty_penalty":4.507158770765308}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:fff0903df45f4b1d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.3147617},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924717999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.31476170000000003},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.11219570000000001,"mean":0.0416694575,"median":0.033877925,"min":0.00984735,"recorded_attempt_count":59,"run_count":24,"total":1.00006698},"codegen_latency_ms":{"attempt_count":59,"max_ms":511905,"mean_ms":204675.625,"min_ms":73907,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":20,"max_ms":511905,"mean_ms":284845.75,"min_ms":132388,"run_count":8},"medium":{"attempt_count":19,"max_ms":302393,"mean_ms":201389.625,"min_ms":134501,"run_count":8},"none":{"attempt_count":20,"max_ms":209946,"mean_ms":127791.5,"min_ms":73907,"run_count":8}},"codegen_output_tokens":{"attempt_count":59,"output_max":93362,"output_mean":33067.75,"output_min":6729,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":93362,"output_mean":49316.75,"output_min":16213,"run_count":8},"medium":{"attempt_count":19,"output_max":59186,"output_mean":30987.25,"output_min":18109,"run_count":8},"none":{"attempt_count":20,"output_max":28972,"output_mean":18899.25,"output_min":6729,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":41.01522317996705,"highest":29.291490904881062,"medium":34.73179707606592,"none":37.689134564680714},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":59,"finish_reasons":["stop"],"indexed_attempts":59,"output_token_observations":59,"reasoning_token_observations":20,"total_output_tokens":793626,"total_reasoning_output_tokens":89090,"total_visible_output_tokens":62104,"visible_token_observations":20},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03","GB2-07","GB2-08"],"model_code_failure_rate":0.5,"model_code_failures":4,"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.5,"model_code_failures":4,"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"repaired_admitted":5,"repaired_rate":0.625}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:59Z","match_totals_all":{"draws":278,"losses":539,"wins":350},"match_totals_tracks":{"highest":{"draws":74,"losses":255,"wins":144},"medium":{"draws":149,"losses":160,"wins":97},"none":{"draws":55,"losses":124,"wins":109}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":61.23827813661711,"mean":28.980909796261443,"min":15.139582069381618},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-01":15.139582069381618,"GB2-05":37.474899556627776,"GB2-06":42.140290158190794,"GB2-07":30.32531783828087,"GB2-08":21.377364901924253},"per_game_all":{"GB2-05":36.59175286833629,"GB2-06":45.43869349159781},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":60,"wins":14},"GB2-02":{"draws":74,"losses":9,"wins":1},"GB2-04":{"draws":74,"losses":11,"wins":11},"GB2-05":{"draws":0,"losses":149,"wins":127},"GB2-06":{"draws":6,"losses":162,"wins":120},"GB2-07":{"draws":0,"losses":111,"wins":76},"GB2-08":{"draws":118,"losses":37,"wins":1}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":60,"wins":14},"GB2-05":{"draws":0,"losses":50,"wins":54},"GB2-06":{"draws":2,"losses":60,"wins":40},"GB2-07":{"draws":0,"losses":64,"wins":35},"GB2-08":{"draws":66,"losses":21,"wins":1}},"medium":{"GB2-02":{"draws":74,"losses":9,"wins":1},"GB2-04":{"draws":74,"losses":11,"wins":11},"GB2-05":{"draws":0,"losses":64,"wins":52},"GB2-06":{"draws":1,"losses":76,"wins":33}},"none":{"GB2-05":{"draws":0,"losses":35,"wins":21},"GB2-06":{"draws":3,"losses":26,"wins":47},"GB2-07":{"draws":0,"losses":47,"wins":41},"GB2-08":{"draws":52,"losses":16,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1454.2189291342336,"GB2-06":1431.9997730455818},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1232.3529714785363,"GB2-05":1463.0951747410882,"GB2-06":1403.6267806671017,"GB2-07":1360.418971602498,"GB2-08":1405.0097337160018},"medium":{"GB2-02":1483.647195989816,"GB2-04":1524.4271477634718,"GB2-05":1490.9069818743108,"GB2-06":1299.6101532628288},"none":{"GB2-05":1408.6546307873011,"GB2-06":1592.7623852068155,"GB2-07":1432.8399822560605,"GB2-08":1425.745642412368}},"per_game_tracks":{"highest":{"GB2-01":15.139582069381618,"GB2-05":37.474899556627776,"GB2-06":42.140290158190794,"GB2-07":30.32531783828087,"GB2-08":21.377364901924253},"medium":{"GB2-02":26.292540253374842,"GB2-04":37.89921383372028,"GB2-05":41.79792203718302,"GB2-06":32.937512179985525},"none":{"GB2-05":30.50243701119809,"GB2-06":61.23827813661711,"GB2-07":36.98262964892139,"GB2-08":22.033193461986272}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.044227582746185,"medium":29.205843656583273,"none":31.69265814945488},"reasoning_agg":{"highest":{"max":42.140290158190794,"mean":26.044227582746185,"min":15.139582069381618},"medium":{"max":41.79792203718302,"mean":29.205843656583273,"min":26.292540253374842},"none":{"max":61.23827813661711,"mean":31.69265814945488,"min":22.033193461986272}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":61.23827813661711,"expected_score":35.020438764034125,"reasoning_variance":5.648430566708694,"reliability_score":76.06192070470131,"uncertainty_avg":23.93807929529869,"uncertainty_penalty":6.039528967772682},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.140290158190794,"expected_score":13.608961075497096,"reliability_score":71.2149072095584,"uncertainty_avg":28.785092790441592,"uncertainty_penalty":-12.43526650724909},"medium":{"ceiling_score":41.79792203718302,"expected_score":35.65793400393534,"reliability_score":94.07929028723191,"uncertainty_avg":5.920709712768092,"uncertainty_penalty":6.452090347352065},"none":{"ceiling_score":61.23827813661711,"expected_score":39.902551417667055,"reliability_score":57.04899454537872,"uncertainty_avg":42.95100545462128,"uncertainty_penalty":8.209893268212177}}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:a8eec1465fa7e4b4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.3891924}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.5047206500000001}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.2116408499999998},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":38.80799514160345,"highest":27.441305954041592,"medium":35.535482548305495,"none":33.84070816163852},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"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,"repaired_admitted":7,"repaired_rate":0.4375}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-08-05T04:29:54Z","match_totals_all":{"draws":677,"losses":684,"wins":412},"match_totals_tracks":{"highest":{"draws":323,"losses":302,"wins":158},"medium":{"draws":182,"losses":177,"wins":119},"none":{"draws":172,"losses":205,"wins":135}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":66.09501277916272,"mean":28.741343599571106,"min":12.422397885640807},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-01":29.808038955158167,"GB2-02":17.505656326341292,"GB2-04":20.693442822538298,"GB2-05":34.77351511539399,"GB2-06":39.94026033234647,"GB2-08":21.92692217247133},"per_game_all":{"GB2-01":44.21600770592829,"GB2-06":45.952090005543276,"GB2-08":26.25588771333879},"per_game_match_totals_all":{"GB2-01":{"draws":54,"losses":124,"wins":88},"GB2-02":{"draws":194,"losses":21,"wins":3},"GB2-03":{"draws":36,"losses":9,"wins":3},"GB2-04":{"draws":107,"losses":26,"wins":13},"GB2-05":{"draws":0,"losses":147,"wins":141},"GB2-06":{"draws":14,"losses":142,"wins":107},"GB2-07":{"draws":0,"losses":134,"wins":32},"GB2-08":{"draws":272,"losses":81,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":48,"wins":22},"GB2-02":{"draws":112,"losses":16,"wins":2},"GB2-04":{"draws":61,"losses":19,"wins":6},"GB2-05":{"draws":0,"losses":114,"wins":88},"GB2-06":{"draws":6,"losses":56,"wins":25},"GB2-08":{"draws":124,"losses":49,"wins":15}},"medium":{"GB2-01":{"draws":20,"losses":36,"wins":38},"GB2-02":{"draws":82,"losses":5,"wins":1},"GB2-06":{"draws":8,"losses":37,"wins":51},"GB2-07":{"draws":0,"losses":72,"wins":20},"GB2-08":{"draws":72,"losses":27,"wins":9}},"none":{"GB2-01":{"draws":14,"losses":40,"wins":28},"GB2-03":{"draws":36,"losses":9,"wins":3},"GB2-04":{"draws":46,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":33,"wins":53},"GB2-06":{"draws":0,"losses":49,"wins":31},"GB2-07":{"draws":0,"losses":62,"wins":12},"GB2-08":{"draws":76,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1488.4518371249253,"GB2-06":1432.4356845220893,"GB2-08":1432.2699990298795},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1365.3506179183505,"GB2-02":1470.8422251646493,"GB2-04":1449.5187890361944,"GB2-05":1435.4301689763815,"GB2-06":1387.7788982716947,"GB2-08":1407.32775976306},"medium":{"GB2-01":1525.958621253768,"GB2-02":1463.2953460829026,"GB2-06":1613.9350142082228,"GB2-07":1165.7290719890677,"GB2-08":1440.809420939187},"none":{"GB2-01":1574.046272202658,"GB2-03":1414.2361193788938,"GB2-04":1504.4747006526225,"GB2-05":1597.6892957530818,"GB2-06":1295.593141086351,"GB2-07":1179.1916405345034,"GB2-08":1448.6728163873909}},"per_game_tracks":{"highest":{"GB2-01":29.808038955158167,"GB2-02":17.505656326341292,"GB2-04":20.693442822538298,"GB2-05":34.77351511539399,"GB2-06":39.94026033234647,"GB2-08":21.92692217247133},"medium":{"GB2-01":48.990872009700986,"GB2-02":21.883388248077022,"GB2-06":66.09501277916272,"GB2-07":12.422397885640807,"GB2-08":28.28574181894595},"none":{"GB2-01":53.84911215292571,"GB2-03":25.69906909498186,"GB2-04":32.34819561268509,"GB2-05":51.31857245670056,"GB2-06":31.82099690512065,"GB2-07":13.294011760456632,"GB2-08":28.55499914859909}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.76486806922119,"medium":30.679204262663337,"none":31.779958466828784},"reasoning_agg":{"highest":{"max":39.94026033234647,"mean":23.76486806922119,"min":17.505656326341292},"medium":{"max":66.09501277916272,"mean":30.679204262663337,"min":12.422397885640807},"none":{"max":53.84911215292571,"mean":31.779958466828784,"min":13.294011760456632}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.09501277916272,"expected_score":29.363533041959272,"reasoning_variance":8.015090397607594,"reliability_score":84.03102732156408,"uncertainty_avg":15.968972678435918,"uncertainty_penalty":0.6221894423881658},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":39.94026033234647,"expected_score":14.847659121447073,"reliability_score":68.06905249077622,"uncertainty_avg":31.93094750922378,"uncertainty_penalty":-8.917208947774117},"medium":{"ceiling_score":66.09501277916272,"expected_score":30.21273131000212,"reliability_score":92.7889962282329,"uncertainty_avg":7.211003771767101,"uncertainty_penalty":-0.466472952661217},"none":{"ceiling_score":53.84911215292571,"expected_score":37.75928284309419,"reliability_score":84.87750277126891,"uncertainty_avg":15.122497228731092,"uncertainty_penalty":5.9793243762654065}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:ac46b2b3feb2053c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.1572507100000005},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.25526928},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.2552692800000003},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.15725071}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":145},"evidence_basis":"Provider-reported","failed_cell_count":21,"max":0.302804525,"mean":0.12502029041666668,"median":0.082332765,"min":0.01945095,"recorded_attempt_count":145,"run_count":48,"total":6.000973940000001},"codegen_latency_ms":{"attempt_count":145,"max_ms":712912,"mean_ms":234062.20833333334,"min_ms":20774,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":712912,"mean_ms":506639.625,"min_ms":278552,"run_count":16},"medium":{"attempt_count":53,"max_ms":476873,"mean_ms":144633.375,"min_ms":47325,"run_count":16},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":145,"output_max":80000,"output_mean":25786.458333333332,"output_min":1372,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":80000,"output_mean":58672.9375,"output_min":35008,"run_count":16},"medium":{"attempt_count":53,"output_max":32558,"output_mean":14052.75,"output_min":3762,"run_count":16},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":30.40693664211783,"highest":27.236848647884678,"medium":31.222332345871028,"none":35.40708035253854},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":145,"finish_reasons":["length","stop"],"indexed_attempts":145,"output_token_observations":145,"reasoning_token_observations":102,"total_output_tokens":1237750,"total_reasoning_output_tokens":697293,"total_visible_output_tokens":161414,"visible_token_observations":99},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.625,"model_code_failures":10,"repaired_admitted":1,"repaired_rate":0.0625},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.25,"model_code_failures":4,"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,"repaired_admitted":5,"repaired_rate":0.3125}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:54Z","match_totals_all":{"draws":658,"losses":960,"wins":557},"match_totals_tracks":{"highest":{"draws":167,"losses":276,"wins":123},"medium":{"draws":111,"losses":193,"wins":99},"none":{"draws":380,"losses":491,"wins":335}},"model_slug":"thinkingmachines-inkling","overall":{"max":63.27779754414018,"mean":26.990199775004637,"min":14.786907510390217},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-01":26.898650929285388,"GB2-02":16.681032418541818,"GB2-03":29.873359195800802,"GB2-04":23.36619296619383,"GB2-05":20.614276485732244,"GB2-06":54.719235037247856,"GB2-07":26.686045371959437,"GB2-08":19.05599677831604},"per_game_all":{"GB2-01":25.898394310596164,"GB2-03":43.237916929450144,"GB2-04":26.670488599113366,"GB2-05":25.40976975463347,"GB2-07":24.6444784594152,"GB2-08":36.580571799498664},"per_game_match_totals_all":{"GB2-01":{"draws":121,"losses":177,"wins":40},"GB2-02":{"draws":135,"losses":12,"wins":3},"GB2-03":{"draws":99,"losses":63,"wins":82},"GB2-04":{"draws":184,"losses":48,"wins":40},"GB2-05":{"draws":0,"losses":315,"wins":151},"GB2-06":{"draws":4,"losses":85,"wins":87},"GB2-07":{"draws":0,"losses":177,"wins":79},"GB2-08":{"draws":115,"losses":83,"wins":75}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":24,"losses":26,"wins":4},"GB2-02":{"draws":47,"losses":2,"wins":1},"GB2-03":{"draws":13,"losses":12,"wins":9},"GB2-04":{"draws":27,"losses":12,"wins":15},"GB2-05":{"draws":0,"losses":98,"wins":36},"GB2-06":{"draws":3,"losses":29,"wins":34},"GB2-07":{"draws":0,"losses":63,"wins":21},"GB2-08":{"draws":53,"losses":34,"wins":3}},"medium":{"GB2-01":{"draws":13,"losses":27,"wins":14},"GB2-03":{"draws":8,"losses":14,"wins":24},"GB2-04":{"draws":35,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":78,"wins":44},"GB2-07":{"draws":0,"losses":58,"wins":10},"GB2-08":{"draws":55,"losses":12,"wins":4}},"none":{"GB2-01":{"draws":84,"losses":124,"wins":22},"GB2-02":{"draws":88,"losses":10,"wins":2},"GB2-03":{"draws":78,"losses":37,"wins":49},"GB2-04":{"draws":122,"losses":32,"wins":22},"GB2-05":{"draws":0,"losses":139,"wins":71},"GB2-06":{"draws":1,"losses":56,"wins":53},"GB2-07":{"draws":0,"losses":56,"wins":48},"GB2-08":{"draws":7,"losses":37,"wins":68}}},"per_game_raw_elo_all":{"GB2-01":1325.540331808011,"GB2-03":1541.222084627913,"GB2-04":1486.517249968807,"GB2-05":1328.1268158457058,"GB2-07":1296.8092861811517,"GB2-08":1520.6553149338142},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1354.9115333507139,"GB2-02":1482.565459593351,"GB2-03":1489.6154597021434,"GB2-04":1493.9386277122185,"GB2-05":1298.0725132394223,"GB2-06":1536.1147152275953,"GB2-07":1329.7720405010791,"GB2-08":1384.5064376721202},"medium":{"GB2-01":1407.8495385633466,"GB2-03":1607.1778209283398,"GB2-04":1492.516457423049,"GB2-05":1331.9093913458112,"GB2-07":1196.149393725581,"GB2-08":1442.2338469609456},"none":{"GB2-01":1213.859923509973,"GB2-02":1496.1585038473304,"GB2-03":1526.872973253256,"GB2-04":1473.096664771153,"GB2-05":1354.3985429518834,"GB2-06":1364.1456650071532,"GB2-07":1364.5064243167951,"GB2-08":1735.2256601683764}},"per_game_tracks":{"highest":{"GB2-01":26.898650929285388,"GB2-02":16.681032418541818,"GB2-03":29.873359195800802,"GB2-04":23.36619296619383,"GB2-05":20.614276485732244,"GB2-06":54.719235037247856,"GB2-07":26.686045371959437,"GB2-08":19.05599677831604},"medium":{"GB2-01":34.916500267983515,"GB2-03":54.946552450271184,"GB2-04":28.397881427239696,"GB2-05":26.878231343301803,"GB2-07":14.786907510390217,"GB2-08":27.407921076039756},"none":{"GB2-01":15.88003173451959,"GB2-02":29.957237052457256,"GB2-03":44.893839142278445,"GB2-04":28.247391403906573,"GB2-05":28.736801434866358,"GB2-06":39.80306201224402,"GB2-07":32.460482495895945,"GB2-08":63.27779754414018}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.58780284809997,"medium":24.432795454223083,"none":32.950001022690856},"reasoning_agg":{"highest":{"max":54.719235037247856,"mean":23.58780284809997,"min":16.681032418541818},"medium":{"max":54.946552450271184,"mean":24.432795454223083,"min":14.786907510390217},"none":{"max":63.27779754414018,"mean":32.950001022690856,"min":15.88003173451959}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":63.27779754414018,"expected_score":30.634892406909803,"reasoning_variance":9.362198174590887,"reliability_score":74.76857030910294,"uncertainty_avg":25.23142969089706,"uncertainty_penalty":3.6446926319051656},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.719235037247856,"expected_score":17.439668486634737,"reliability_score":49.38844795615025,"uncertainty_avg":50.61155204384975,"uncertainty_penalty":-6.148134361465232},"medium":{"ceiling_score":54.946552450271184,"expected_score":30.965061583990593,"reliability_score":80.2827099105485,"uncertainty_avg":19.7172900894515,"uncertainty_penalty":6.53226612976751},"none":{"ceiling_score":63.27779754414018,"expected_score":41.6691498387507,"reliability_score":94.2519038731857,"uncertainty_avg":5.748096126814302,"uncertainty_penalty":8.719148816059842}}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:0641171d97b75bfa","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.81977125},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.4057992500000007},"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":24.379395262676457,"none":34.49125409606728},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":7,"repaired_rate":0.4375}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:20Z","match_totals_all":{"draws":347,"losses":495,"wins":280},"match_totals_tracks":{"medium":{"draws":56,"losses":302,"wins":126},"none":{"draws":291,"losses":193,"wins":154}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":59.024723737278265,"mean":24.86401053026094,"min":5.696416759421026},"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":"partial","per_game_match_totals_all":{"GB2-02":{"draws":71,"losses":11,"wins":2},"GB2-03":{"draws":76,"losses":40,"wins":22},"GB2-04":{"draws":81,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":124,"wins":84},"GB2-06":{"draws":12,"losses":141,"wins":43},"GB2-07":{"draws":0,"losses":88,"wins":116},"GB2-08":{"draws":107,"losses":83,"wins":8}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":33,"losses":26,"wins":13},"GB2-05":{"draws":0,"losses":72,"wins":32},"GB2-06":{"draws":10,"losses":76,"wins":20},"GB2-07":{"draws":0,"losses":59,"wins":53},"GB2-08":{"draws":13,"losses":69,"wins":8}},"none":{"GB2-02":{"draws":71,"losses":11,"wins":2},"GB2-03":{"draws":43,"losses":14,"wins":9},"GB2-04":{"draws":81,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":52,"wins":52},"GB2-06":{"draws":2,"losses":65,"wins":23},"GB2-07":{"draws":0,"losses":29,"wins":63},"GB2-08":{"draws":94,"losses":14,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1432.5349424095307,"GB2-05":1315.5974695891684,"GB2-06":1253.7861307495552,"GB2-07":1450.0872590593376,"GB2-08":1274.3292533208191},"none":{"GB2-02":1464.2426317683783,"GB2-03":1450.3899699523217,"GB2-04":1475.0635006450743,"GB2-05":1500.9159982859114,"GB2-06":1271.588396713997,"GB2-07":1633.70258494576,"GB2-08":1431.0354741384447}},"per_game_tracks":{"medium":{"GB2-03":27.175958376626816,"GB2-05":23.41411822823543,"GB2-06":26.078598419102768,"GB2-07":39.53188452999624,"GB2-08":5.696416759421026},"none":{"GB2-02":21.874533667805792,"GB2-03":32.476184640834816,"GB2-04":28.853421449925953,"GB2-05":42.54851301568021,"GB2-06":29.534623279080066,"GB2-07":59.024723737278265,"GB2-08":27.126778881865853}},"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":21.676688312409,"none":28.051332748112884},"reasoning_agg":{"medium":{"max":39.53188452999624,"mean":21.676688312409,"min":5.696416759421026},"none":{"max":59.024723737278265,"mean":28.051332748112884,"min":21.874533667805792}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":59.024723737278265,"reasoning_variance":6.374644435703885},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":39.53188452999624,"expected_score":18.31109817276448,"reliability_score":70.05546712010782,"uncertainty_avg":29.944532879892183,"uncertainty_penalty":-3.3655901396445174},"none":{"ceiling_score":59.024723737278265,"expected_score":36.882063300525225,"reliability_score":91.24080018311774,"uncertainty_avg":8.759199816882255,"uncertainty_penalty":8.83073055241234}}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:b5a9710ceba35181","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":45},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":45,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":45,"max_ms":905283,"mean_ms":194374.625,"min_ms":21975,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":905283,"mean_ms":509118.375,"min_ms":288605,"run_count":8},"none":{"attempt_count":30,"max_ms":62079,"mean_ms":37002.75,"min_ms":21975,"run_count":16}},"codegen_output_tokens":{"attempt_count":45,"output_max":52275,"output_mean":12297.333333333334,"output_min":1733,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":52275,"output_mean":30105.875,"output_min":9014,"run_count":8},"none":{"attempt_count":30,"output_max":6330,"output_mean":3393.0625,"output_min":1733,"run_count":16}},"display_name":"North Mini Code","economics":{"medium":30.62503365364087,"none":25.767952587353744},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":45,"finish_reasons":["stop"],"indexed_attempts":45,"output_token_observations":45,"total_output_tokens":295136},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":5,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.1875,"model_code_failure_rate":0.6875,"model_code_failures":11,"repaired_admitted":2,"repaired_rate":0.125}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":378,"losses":512,"wins":272},"match_totals_tracks":{"medium":{"draws":186,"losses":261,"wins":185},"none":{"draws":192,"losses":251,"wins":87}},"model_slug":"cohere-north-mini-code","overall":{"max":43.6188762763087,"mean":23.88292168813816,"min":19.266038248032807},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":98,"losses":101,"wins":23},"GB2-03":{"draws":27,"losses":24,"wins":9},"GB2-04":{"draws":80,"losses":15,"wins":7},"GB2-05":{"draws":0,"losses":54,"wins":72},"GB2-06":{"draws":1,"losses":79,"wins":34},"GB2-07":{"draws":0,"losses":197,"wins":123},"GB2-08":{"draws":172,"losses":42,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":27,"losses":24,"wins":9},"GB2-04":{"draws":80,"losses":15,"wins":7},"GB2-05":{"draws":0,"losses":54,"wins":72},"GB2-06":{"draws":1,"losses":79,"wins":34},"GB2-07":{"draws":0,"losses":67,"wins":63},"GB2-08":{"draws":78,"losses":22,"wins":0}},"none":{"GB2-01":{"draws":98,"losses":101,"wins":23},"GB2-07":{"draws":0,"losses":130,"wins":60},"GB2-08":{"draws":94,"losses":20,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1414.1613620278795,"GB2-04":1474.2020263508612,"GB2-05":1524.9883204418932,"GB2-06":1291.4802446130302,"GB2-07":1451.8589119440062,"GB2-08":1394.6272805817675},"none":{"GB2-01":1299.3132286826562,"GB2-07":1302.1104543187066,"GB2-08":1422.2229879671406}},"per_game_tracks":{"medium":{"GB2-03":23.428307136703403,"GB2-04":25.82750955564381,"GB2-05":43.6188762763087,"GB2-06":30.414777820507236,"GB2-07":40.09138610591313,"GB2-08":20.369345026768944},"none":{"GB2-01":24.96235519414845,"GB2-07":26.064607743882533,"GB2-08":26.27689482403025}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":28.49980512824352,"none":19.266038248032807},"reasoning_agg":{"medium":{"max":43.6188762763087,"mean":28.49980512824352,"min":20.369345026768944},"none":{"max":26.27689482403025,"mean":19.266038248032807,"min":24.96235519414845}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":43.6188762763087,"reasoning_variance":9.233766880210712},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.6188762763087,"expected_score":27.82783962488737,"reliability_score":72.34230152792307,"uncertainty_avg":27.657698472076934,"uncertainty_penalty":-0.671965503356148},"none":{"ceiling_score":26.27689482403025,"expected_score":18.467101121268495,"reliability_score":95.58815253718281,"uncertainty_avg":4.411847462817193,"uncertainty_penalty":-0.7989371267643115}}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:ebf74d4ed7b0916f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.3927285,"mean":0.1902770625,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":14,"run_count":9,"total":1.9149450000000001},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.042994687499999996,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.3439575}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.042994687499999996,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.34395749999999997},"historical-provider-setting-intensive":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.3927285,"mean":0.1902770625,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":14,"run_count":9,"total":1.9149450000000001}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.3927285,"mean":0.116635875,"median":0.0747585,"min":0.0223935,"recorded_attempt_count":28,"run_count":17,"total":2.2589025},"codegen_latency_ms":{"attempt_count":28,"max_ms":776640,"mean_ms":218770.82352941178,"min_ms":28440,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":776640,"mean_ms":364061.1111111111,"min_ms":132587,"run_count":9},"none":{"attempt_count":14,"max_ms":130711,"mean_ms":55319.25,"min_ms":28440,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":52664,"output_mean":15146.29411764706,"output_min":1452,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":52664,"output_mean":25839.666666666668,"output_min":10169,"run_count":9},"none":{"attempt_count":14,"output_max":5014,"output_mean":3116.25,"output_min":1452,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":21.494721172537112,"none":35.37784506240002},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":257487},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.5,"model_code_failures":4,"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":4,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.2222222222222222,"model_code_failure_rate":0.5555555555555556,"model_code_failures":5,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:02:41Z","match_totals_all":{"draws":126,"losses":427,"wins":204},"match_totals_tracks":{"highest":{"draws":19,"losses":257,"wins":80},"none":{"draws":107,"losses":170,"wins":124}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":44.576050565533166,"mean":23.64973471887243,"min":14.583182450662427},"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":"partial","per_game":{"GB2-01":14.583182450662427,"GB2-05":19.886909831937842,"GB2-06":32.00389460443945,"GB2-07":19.504897803108722},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":110,"wins":51},"GB2-05":{"draws":0,"losses":115,"wins":67},"GB2-06":{"draws":8,"losses":107,"wins":63},"GB2-07":{"draws":0,"losses":73,"wins":21},"GB2-08":{"draws":90,"losses":22,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":61,"wins":8},"GB2-05":{"draws":0,"losses":63,"wins":23},"GB2-06":{"draws":0,"losses":60,"wins":28},"GB2-07":{"draws":0,"losses":73,"wins":21}},"none":{"GB2-01":{"draws":9,"losses":49,"wins":43},"GB2-05":{"draws":0,"losses":52,"wins":44},"GB2-06":{"draws":8,"losses":47,"wins":35},"GB2-08":{"draws":90,"losses":22,"wins":2}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1224.277071770066,"GB2-05":1282.3618154778578,"GB2-06":1312.5406298877297,"GB2-07":1253.3442248132515},"none":{"GB2-01":1483.4317022040432,"GB2-05":1391.2176833271508,"GB2-06":1378.8243454602684,"GB2-08":1403.1981627791558}},"per_game_tracks":{"highest":{"GB2-01":14.583182450662427,"GB2-05":19.886909831937842,"GB2-06":32.00389460443945,"GB2-07":19.504897803108722},"none":{"GB2-01":44.576050565533166,"GB2-05":32.0464884077659,"GB2-06":40.942819015465346,"GB2-08":23.94602226083568}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.550366345371355,"none":29.749103092373506},"reasoning_agg":{"highest":{"max":32.00389460443945,"mean":17.550366345371355,"min":14.583182450662427},"none":{"max":44.576050565533166,"mean":29.749103092373506,"min":23.94602226083568}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":44.576050565533166,"reasoning_variance":12.198736747002151},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":32.00389460443945,"expected_score":1.6615976908129868,"reliability_score":69.41560063912533,"uncertainty_avg":30.584399360874677,"uncertainty_penalty":-15.888768654558369},"none":{"ceiling_score":44.576050565533166,"expected_score":28.990928648766428,"reliability_score":93.92145808659343,"uncertainty_avg":6.0785419134065695,"uncertainty_penalty":-0.7581744436070785}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:4a5b21798b8d9375","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":92},"evidence_basis":"Provider-reported","failed_cell_count":15,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":92,"run_count":32,"total":0.0},"codegen_latency_ms":{"attempt_count":93,"max_ms":410978,"mean_ms":158095.9375,"min_ms":18717,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":53,"max_ms":410978,"mean_ms":269539.1875,"min_ms":161500,"run_count":16},"none":{"attempt_count":40,"max_ms":90441,"mean_ms":46652.6875,"min_ms":18717,"run_count":16}},"codegen_output_tokens":{"attempt_count":92,"output_max":92074,"output_mean":33594.125,"output_min":2036,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":52,"output_max":92074,"output_mean":60516.0,"output_min":20000,"run_count":16},"none":{"attempt_count":40,"output_max":17378,"output_mean":6672.25,"output_min":2036,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"medium":26.689974102730304,"none":27.637609971091326},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":93,"finish_reasons":["length","stop","unknown"],"indexed_attempts":94,"output_token_observations":93,"reasoning_token_observations":65,"total_output_tokens":1075012,"total_reasoning_output_tokens":626571,"total_visible_output_tokens":109787,"visible_token_observations":55},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"repaired_admitted":4,"repaired_rate":0.25}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:59Z","match_totals_all":{"draws":794,"losses":670,"wins":326},"match_totals_tracks":{"medium":{"draws":132,"losses":237,"wins":123},"none":{"draws":662,"losses":433,"wins":203}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":40.71668659092171,"mean":22.899725766295553,"min":14.944434766576471},"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":"partial","per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":151,"wins":97},"GB2-02":{"draws":154,"losses":15,"wins":3},"GB2-03":{"draws":84,"losses":77,"wins":35},"GB2-04":{"draws":171,"losses":20,"wins":13},"GB2-06":{"draws":5,"losses":259,"wins":90},"GB2-07":{"draws":0,"losses":111,"wins":83},"GB2-08":{"draws":262,"losses":37,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":17,"losses":37,"wins":4},"GB2-02":{"draws":44,"losses":8,"wins":2},"GB2-04":{"draws":70,"losses":14,"wins":6},"GB2-06":{"draws":1,"losses":67,"wins":28},"GB2-07":{"draws":0,"losses":111,"wins":83}},"none":{"GB2-01":{"draws":101,"losses":114,"wins":93},"GB2-02":{"draws":110,"losses":7,"wins":1},"GB2-03":{"draws":84,"losses":77,"wins":35},"GB2-04":{"draws":101,"losses":6,"wins":7},"GB2-06":{"draws":4,"losses":192,"wins":62},"GB2-08":{"draws":262,"losses":37,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1343.2462229301345,"GB2-02":1466.9368942846404,"GB2-04":1449.7167570727886,"GB2-06":1300.0206728248031,"GB2-07":1465.343706908703},"none":{"GB2-01":1435.2355596845537,"GB2-02":1459.7462631719882,"GB2-03":1383.9748824540438,"GB2-04":1496.113459457968,"GB2-06":1170.0753284490197,"GB2-08":1421.9452372916912}},"per_game_tracks":{"medium":{"GB2-01":25.921401697168093,"GB2-02":14.944434766576471,"GB2-04":20.941506078017632,"GB2-06":30.92584138096761,"GB2-07":40.71668659092171},"none":{"GB2-01":40.20061892348984,"GB2-02":22.380386424640683,"GB2-03":23.666335927907475,"GB2-04":33.35713798385482,"GB2-06":19.463800160566905,"GB2-08":26.757380406088267}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":21.22575515545204,"none":24.573696377139072},"reasoning_agg":{"medium":{"max":40.71668659092171,"mean":21.22575515545204,"min":14.944434766576471},"none":{"max":40.20061892348984,"mean":24.573696377139072,"min":19.463800160566905}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":40.71668659092171,"reasoning_variance":3.3479412216870337},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.71668659092171,"expected_score":21.15318689778319,"reliability_score":62.98225490478446,"uncertainty_avg":37.01774509521554,"uncertainty_penalty":-0.07256825766884845},"none":{"ceiling_score":40.20061892348984,"expected_score":23.361345193208734,"reliability_score":98.06566303247382,"uncertainty_avg":1.9343369675261766,"uncertainty_penalty":-1.2123511839303376}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:caa30ce7ab70c2c5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.08108399999999999},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.348093},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":23.678706767569437,"highest":25.66695092309063,"medium":28.95062705855644,"none":19.163277618622367},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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,"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,"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,"repaired_admitted":5,"repaired_rate":0.625}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-08-05T05:18:42Z","match_totals_all":{"draws":373,"losses":779,"wins":325},"match_totals_tracks":{"highest":{"draws":128,"losses":248,"wins":93},"medium":{"draws":160,"losses":323,"wins":159},"none":{"draws":85,"losses":208,"wins":73}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":49.375926945379035,"mean":22.267310132093026,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":null,"overall_ranking_status":"partial","per_game":{"GB2-04":21.753586194664617,"GB2-05":16.44510307833982,"GB2-06":31.215153717922618,"GB2-07":37.264518924471545,"GB2-08":21.65639270005456},"per_game_all":{"GB2-05":15.91468493877945,"GB2-06":42.3043170031223,"GB2-07":12.817118360806566},"per_game_match_totals_all":{"GB2-01":{"draws":69,"losses":83,"wins":28},"GB2-02":{"draws":59,"losses":2,"wins":1},"GB2-04":{"draws":136,"losses":24,"wins":14},"GB2-05":{"draws":0,"losses":195,"wins":65},"GB2-06":{"draws":1,"losses":178,"wins":122},"GB2-07":{"draws":0,"losses":218,"wins":50},"GB2-08":{"draws":108,"losses":79,"wins":45}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":60,"losses":20,"wins":6},"GB2-05":{"draws":0,"losses":68,"wins":18},"GB2-06":{"draws":0,"losses":64,"wins":29},"GB2-07":{"draws":0,"losses":68,"wins":34},"GB2-08":{"draws":68,"losses":28,"wins":6}},"medium":{"GB2-01":{"draws":44,"losses":38,"wins":22},"GB2-04":{"draws":76,"losses":4,"wins":8},"GB2-05":{"draws":0,"losses":70,"wins":28},"GB2-06":{"draws":0,"losses":80,"wins":50},"GB2-07":{"draws":0,"losses":80,"wins":12},"GB2-08":{"draws":40,"losses":51,"wins":39}},"none":{"GB2-01":{"draws":25,"losses":45,"wins":6},"GB2-02":{"draws":59,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":57,"wins":19},"GB2-06":{"draws":1,"losses":34,"wins":43},"GB2-07":{"draws":0,"losses":70,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1228.4074717423641,"GB2-06":1395.6947355522168,"GB2-07":1175.9293288202564},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1455.353922850699,"GB2-05":1245.704202029921,"GB2-06":1303.513648432589,"GB2-07":1429.18954362656,"GB2-08":1402.128132796408},"medium":{"GB2-01":1468.2228066206737,"GB2-04":1505.6208754393567,"GB2-05":1239.8542944594315,"GB2-06":1451.1115221856815,"GB2-07":1052.903259206907,"GB2-08":1436.5502098452275},"none":{"GB2-01":1181.3686609045587,"GB2-02":1482.8419989760441,"GB2-05":1199.66391873774,"GB2-06":1432.4590360383802,"GB2-07":1045.6951836273022}},"per_game_tracks":{"highest":{"GB2-04":21.753586194664617,"GB2-05":16.44510307833982,"GB2-06":31.215153717922618,"GB2-07":37.264518924471545,"GB2-08":21.65639270005456},"medium":{"GB2-01":43.00333801213897,"GB2-04":34.157939951088196,"GB2-05":17.8000252646134,"GB2-06":49.375926945379035,"GB2-07":1.18683615794815,"GB2-08":28.179696020170926},"none":{"GB2-01":11.482216539302486,"GB2-02":24.513374734358962,"GB2-05":13.498926473385124,"GB2-06":46.321870346065246,"GB2-07":0.0}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":22.821505172505795,"medium":26.94159421474535,"none":17.038831009027934},"reasoning_agg":{"highest":{"max":37.264518924471545,"mean":22.821505172505795,"min":16.44510307833982},"medium":{"max":49.375926945379035,"mean":26.94159421474535,"min":1.18683615794815},"none":{"max":46.321870346065246,"mean":17.038831009027934,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.375926945379035,"expected_score":15.401559672324451,"reasoning_variance":9.902763205717417,"reliability_score":84.38880090199197,"uncertainty_avg":15.611199098008031,"uncertainty_penalty":-6.8657504597685755},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.264518924471545,"expected_score":9.355729928110275,"reliability_score":71.27688532568388,"uncertainty_avg":28.72311467431613,"uncertainty_penalty":-13.46577524439552},"medium":{"ceiling_score":49.375926945379035,"expected_score":27.763855326159028,"reliability_score":95.1842711421289,"uncertainty_avg":4.815728857871089,"uncertainty_penalty":0.8222611114136775},"none":{"ceiling_score":46.321870346065246,"expected_score":14.835506111030252,"reliability_score":85.56118454804542,"uncertainty_avg":14.438815451954582,"uncertainty_penalty":-2.203324897997682}}}],"public_release_id":"gb2-20260807-e64919171e70","results_cut_id":"gb2-20260807-e64919171e70","schema_version":1,"snapshot_id":"20260807_123334","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-08-07 12:33 UTC","versus_totals_all":{"claude-fable-5":{"claude-fable-5":{"draws":4,"losses":12,"wins":12},"claude-opus-4-5":{"draws":7,"losses":8,"wins":45},"claude-opus-4-8":{"draws":6,"losses":26,"wins":28},"claude-opus-5":{"draws":25,"losses":58,"wins":57},"claude-sonnet-5":{"draws":6,"losses":0,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":22},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":28},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":8},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":34},"gpt-5.4":{"draws":8,"losses":28,"wins":30},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":13},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":37},"gpt-5.5":{"draws":8,"losses":22,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":33},"gpt-5.6-sol":{"draws":13,"losses":20,"wins":41},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":48},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":27},"o3":{"draws":1,"losses":2,"wins":31},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":19},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":19},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":20},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":30},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":21}},"claude-opus-4-5":{"claude-fable-5":{"draws":5,"losses":29,"wins":6},"claude-opus-4-5":{"draws":19,"losses":12,"wins":17},"claude-opus-4-8":{"draws":8,"losses":29,"wins":17},"claude-opus-5":{"draws":23,"losses":128,"wins":15},"claude-sonnet-5":{"draws":10,"losses":11,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":20},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":11},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":8},"google/gemini-3.5-flash-lite":{"draws":46,"losses":22,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":48,"wins":34},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":13},"gpt-4.1":{"draws":8,"losses":6,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":14,"losses":9,"wins":11},"gpt-5.4":{"draws":17,"losses":28,"wins":15},"gpt-5.4-mini":{"draws":17,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":24},"gpt-5.5":{"draws":18,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":16,"wins":21},"gpt-5.6-sol":{"draws":16,"losses":34,"wins":8},"gpt-5.6-terra":{"draws":24,"losses":21,"wins":17},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":21,"losses":12,"wins":24},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":26,"wins":19},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":20},"o3":{"draws":14,"losses":27,"wins":49},"openai/gpt-oss-120b":{"draws":18,"losses":4,"wins":40},"poolside/laguna-s-2.1":{"draws":26,"losses":4,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":9,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":25},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":13},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":32},"x-ai/grok-4.5":{"draws":27,"losses":32,"wins":23},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":9},"z-ai/glm-5.2":{"draws":6,"losses":13,"wins":17}},"claude-opus-4-8":{"claude-fable-5":{"draws":6,"losses":28,"wins":26},"claude-opus-4-5":{"draws":17,"losses":25,"wins":52},"claude-opus-4-8":{"draws":8,"losses":10,"wins":10},"claude-opus-5":{"draws":21,"losses":66,"wins":31},"claude-sonnet-5":{"draws":6,"losses":7,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":18,"wins":11},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":19,"losses":27,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":11},"gpt-5":{"draws":11,"losses":13,"wins":26},"gpt-5.4":{"draws":15,"losses":32,"wins":23},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":36},"gpt-5.5":{"draws":19,"losses":35,"wins":22},"gpt-5.6-luna":{"draws":17,"losses":19,"wins":26},"gpt-5.6-sol":{"draws":15,"losses":40,"wins":23},"gpt-5.6-terra":{"draws":22,"losses":17,"wins":27},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":17},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":31},"o3":{"draws":4,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":23},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":17},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":15,"losses":20,"wins":19},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":12,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":25}},"claude-opus-5":{"claude-fable-5":{"draws":25,"losses":57,"wins":58},"claude-opus-4-5":{"draws":35,"losses":27,"wins":170},"claude-opus-4-8":{"draws":21,"losses":31,"wins":66},"claude-opus-5":{"draws":48,"losses":172,"wins":172},"claude-sonnet-5":{"draws":9,"losses":5,"wins":42},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":46},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":55},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":11,"wins":60},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":84},"google/gemini-3.6-flash":{"draws":14,"losses":33,"wins":99},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":20},"gpt-4.1":{"draws":10,"losses":2,"wins":41},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":5,"wins":51},"gpt-5.4":{"draws":23,"losses":48,"wins":83},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":32},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":54},"gpt-5.5":{"draws":21,"losses":33,"wins":94},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":68},"gpt-5.6-sol":{"draws":29,"losses":35,"wins":122},"gpt-5.6-terra":{"draws":37,"losses":18,"wins":107},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":22},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":48},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":33},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":29},"moonshotai/kimi-k3":{"draws":14,"losses":11,"wins":61},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":43},"o3":{"draws":2,"losses":6,"wins":68},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":66},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":55},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":20},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":26},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":48},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":52},"x-ai/grok-4.5":{"draws":16,"losses":21,"wins":83},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":1,"wins":35},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":60}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-opus-4-5":{"draws":21,"losses":14,"wins":19},"claude-opus-4-8":{"draws":6,"losses":5,"wins":7},"claude-opus-5":{"draws":9,"losses":42,"wins":5},"claude-sonnet-5":{"draws":4,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":21,"losses":4,"wins":17},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":4},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":9,"losses":6,"wins":7},"gpt-5.4":{"draws":10,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":13},"gpt-5.5":{"draws":9,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":20,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":15},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":4,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":4},"o3":{"draws":6,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":14,"losses":5,"wins":11},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":7,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":4,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":4,"wins":18}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":9,"losses":22,"wins":3},"claude-opus-4-8":{"draws":7,"losses":15,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"claude-sonnet-5":{"draws":6,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":13,"wins":13},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":1},"google/gemini-3.5-flash-lite":{"draws":19,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":17,"wins":4},"gpt-5.4":{"draws":8,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":27,"wins":11},"gpt-5.5":{"draws":14,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":10,"wins":6},"meituan/longcat-2.0":{"draws":22,"losses":18,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":15,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":13},"o3":{"draws":12,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":21,"losses":2,"wins":15},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":5,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":24,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":5}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":3,"losses":22,"wins":3},"claude-opus-4-5":{"draws":28,"losses":33,"wins":11},"claude-opus-4-8":{"draws":11,"losses":28,"wins":7},"claude-opus-5":{"draws":8,"losses":46,"wins":2},"claude-sonnet-5":{"draws":8,"losses":12,"wins":2},"cohere/north-mini-code":{"draws":15,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":38,"losses":25,"wins":25},"deepseek/deepseek-v4-pro":{"draws":18,"losses":28,"wins":10},"google/gemini-3.1-flash-lite":{"draws":13,"losses":27,"wins":32},"google/gemini-3.5-flash":{"draws":18,"losses":15,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":9},"google/gemini-3.6-flash":{"draws":16,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":14,"losses":19,"wins":15},"gpt-4.1":{"draws":13,"losses":9,"wins":8},"gpt-5":{"draws":13,"losses":17,"wins":4},"gpt-5.4":{"draws":23,"losses":31,"wins":12},"gpt-5.4-mini":{"draws":25,"losses":19,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":18,"wins":27},"gpt-5.5":{"draws":28,"losses":31,"wins":1},"gpt-5.6-luna":{"draws":32,"losses":21,"wins":25},"gpt-5.6-sol":{"draws":5,"losses":39,"wins":12},"gpt-5.6-terra":{"draws":22,"losses":37,"wins":7},"inclusionai/ling-3.0-flash":{"draws":26,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":13},"minimax/minimax-m3":{"draws":14,"losses":19,"wins":15},"mistralai/mistral-medium-3-5":{"draws":9,"losses":14,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":23,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":22,"wins":24},"o3":{"draws":11,"losses":15,"wins":20},"openai/gpt-oss-120b":{"draws":24,"losses":22,"wins":12},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":10},"qwen/qwen3.7-max":{"draws":18,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":18,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":18,"wins":20},"tencent/hy3-preview":{"draws":21,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":17,"wins":20},"x-ai/grok-4.5":{"draws":2,"losses":12,"wins":6},"x-ai/grok-build-0.1":{"draws":11,"losses":7,"wins":6},"xiaomi/mimo-v2.5":{"draws":48,"losses":49,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":32,"losses":34,"wins":12}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":19,"losses":19,"wins":12},"claude-opus-4-8":{"draws":11,"losses":23,"wins":12},"claude-opus-5":{"draws":6,"losses":55,"wins":3},"claude-sonnet-5":{"draws":5,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":28},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":14,"losses":6,"wins":14},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":10},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":4,"losses":6,"wins":14},"gpt-5.4":{"draws":9,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":12},"gpt-5.5":{"draws":15,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":10},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":12},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":14},"o3":{"draws":11,"losses":15,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":17,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":11,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":11,"wins":16}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":2,"losses":22,"wins":0},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":9,"losses":27,"wins":4},"claude-opus-5":{"draws":4,"losses":27,"wins":1},"claude-sonnet-5":{"draws":5,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":13,"losses":32,"wins":27},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":17,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":12},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":16,"wins":14},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-5":{"draws":14,"losses":18,"wins":2},"gpt-5.4":{"draws":6,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":21,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":29,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":25,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":11,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":24,"wins":13},"o3":{"draws":10,"losses":24,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":24,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.5":{"draws":35,"losses":42,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":21,"wins":8}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-opus-4-5":{"draws":18,"losses":16,"wins":22},"claude-opus-4-8":{"draws":13,"losses":11,"wins":18},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-sonnet-5":{"draws":10,"losses":5,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":14},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":8,"losses":8,"wins":18},"gpt-5.4":{"draws":15,"losses":17,"wins":10},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":17},"gpt-5.5":{"draws":11,"losses":21,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":20},"o3":{"draws":8,"losses":18,"wins":10},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":9,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":7,"losses":11,"wins":16}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":47,"losses":42,"wins":23},"claude-opus-4-8":{"draws":13,"losses":24,"wins":9},"claude-opus-5":{"draws":17,"losses":84,"wins":9},"claude-sonnet-5":{"draws":21,"losses":17,"wins":4},"cohere/north-mini-code":{"draws":19,"losses":11,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":12,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":4},"google/gemini-3.5-flash-lite":{"draws":82,"losses":81,"wins":81},"google/gemini-3.6-flash":{"draws":93,"losses":93,"wins":49},"google/gemma-4-31b-it":{"draws":7,"losses":15,"wins":4},"gpt-4.1":{"draws":6,"losses":6,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":5,"wins":4},"gpt-5":{"draws":19,"losses":10,"wins":7},"gpt-5.4":{"draws":15,"losses":18,"wins":1},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":7},"gpt-5.4-nano":{"draws":19,"losses":12,"wins":19},"gpt-5.5":{"draws":30,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":25,"losses":13,"wins":6},"gpt-5.6-sol":{"draws":11,"losses":13,"wins":6},"gpt-5.6-terra":{"draws":26,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":50,"losses":15,"wins":39},"meituan/longcat-2.0":{"draws":38,"losses":47,"wins":54},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":45,"losses":63,"wins":26},"nex-agi/nex-n2-pro":{"draws":13,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":8},"o3":{"draws":27,"losses":105,"wins":50},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":38},"poolside/laguna-s-2.1":{"draws":60,"losses":44,"wins":38},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":9,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":25,"wins":18},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":48,"losses":43,"wins":63},"x-ai/grok-4.5":{"draws":29,"losses":67,"wins":32},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":17,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":11},"z-ai/glm-5.2":{"draws":9,"losses":7,"wins":10}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":22,"wins":14},"claude-opus-4-5":{"draws":29,"losses":34,"wins":49},"claude-opus-4-8":{"draws":19,"losses":16,"wins":27},"claude-opus-5":{"draws":14,"losses":99,"wins":33},"claude-sonnet-5":{"draws":13,"losses":7,"wins":16},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":22},"deepseek/deepseek-v4-pro":{"draws":13,"losses":7,"wins":16},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":93,"losses":49,"wins":93},"google/gemini-3.6-flash":{"draws":58,"losses":71,"wins":71},"google/gemma-4-31b-it":{"draws":10,"losses":9,"wins":7},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":5,"losses":3,"wins":2},"gpt-5":{"draws":5,"losses":12,"wins":21},"gpt-5.4":{"draws":25,"losses":26,"wins":17},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":23},"gpt-5.4-nano":{"draws":18,"losses":11,"wins":19},"gpt-5.5":{"draws":25,"losses":23,"wins":26},"gpt-5.6-luna":{"draws":24,"losses":16,"wins":30},"gpt-5.6-sol":{"draws":15,"losses":28,"wins":21},"gpt-5.6-terra":{"draws":21,"losses":19,"wins":30},"inclusionai/ling-3.0-flash":{"draws":67,"losses":19,"wins":46},"meituan/longcat-2.0":{"draws":45,"losses":28,"wins":59},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":40,"losses":42,"wins":58},"nex-agi/nex-n2-pro":{"draws":15,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":21},"o3":{"draws":30,"losses":56,"wins":76},"openai/gpt-oss-120b":{"draws":16,"losses":4,"wins":33},"poolside/laguna-s-2.1":{"draws":63,"losses":26,"wins":49},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":22},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":18},"thinkingmachines/inkling":{"draws":64,"losses":23,"wins":67},"x-ai/grok-4.5":{"draws":31,"losses":57,"wins":64},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":11,"losses":4,"wins":7}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":8,"wins":1},"claude-opus-4-5":{"draws":11,"losses":13,"wins":14},"claude-opus-4-8":{"draws":10,"losses":16,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":0},"claude-sonnet-5":{"draws":5,"losses":4,"wins":3},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":14,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":7,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":5,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":8,"wins":3},"gpt-5.4":{"draws":5,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":13},"gpt-5.5":{"draws":7,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":2},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":13},"o3":{"draws":8,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":4,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":1,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":13,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":26,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":3}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"claude-sonnet-5":{"draws":6,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-fable-5":{"draws":2,"losses":34,"wins":2},"claude-opus-4-5":{"draws":25,"losses":21,"wins":20},"claude-opus-4-8":{"draws":11,"losses":26,"wins":13},"claude-opus-5":{"draws":10,"losses":51,"wins":5},"claude-sonnet-5":{"draws":9,"losses":7,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":4,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":18,"wins":8},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":21,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":8},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":13},"gpt-5.5":{"draws":11,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":19,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":15},"o3":{"draws":6,"losses":16,"wins":20},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":8,"losses":18,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":31,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":19}},"gpt-5.4":{"claude-fable-5":{"draws":8,"losses":30,"wins":28},"claude-opus-4-5":{"draws":28,"losses":25,"wins":37},"claude-opus-4-8":{"draws":15,"losses":23,"wins":32},"claude-opus-5":{"draws":23,"losses":83,"wins":48},"claude-sonnet-5":{"draws":10,"losses":4,"wins":10},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":23,"losses":12,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":28},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":15,"losses":10,"wins":17},"google/gemini-3.5-flash-lite":{"draws":15,"losses":1,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":17,"wins":26},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":13},"gpt-4.1":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":11,"losses":7,"wins":28},"gpt-5.4":{"draws":14,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":22,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":40},"gpt-5.5":{"draws":29,"losses":23,"wins":32},"gpt-5.6-luna":{"draws":33,"losses":10,"wins":43},"gpt-5.6-sol":{"draws":15,"losses":25,"wins":50},"gpt-5.6-terra":{"draws":30,"losses":19,"wins":43},"inclusionai/ling-3.0-flash":{"draws":17,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":11},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":19},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":14},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":3,"wins":27},"o3":{"draws":7,"losses":7,"wins":28},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":26},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":19},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":17,"losses":4,"wins":23},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":15},"x-ai/grok-4.5":{"draws":12,"losses":12,"wins":30},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.5":{"draws":36,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":23},"z-ai/glm-5.2":{"draws":32,"losses":13,"wins":17}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-opus-4-5":{"draws":25,"losses":27,"wins":18},"claude-opus-4-8":{"draws":18,"losses":17,"wins":15},"claude-opus-5":{"draws":10,"losses":32,"wins":6},"claude-sonnet-5":{"draws":13,"losses":3,"wins":8},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":21},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":9},"google/gemini-3.5-flash-lite":{"draws":17,"losses":7,"wins":16},"google/gemini-3.6-flash":{"draws":13,"losses":23,"wins":9},"google/gemma-4-31b-it":{"draws":5,"losses":10,"wins":11},"gpt-4.1":{"draws":14,"losses":3,"wins":9},"gpt-5":{"draws":7,"losses":6,"wins":9},"gpt-5.4":{"draws":22,"losses":21,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":14,"losses":29,"wins":15},"gpt-5.5":{"draws":19,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":9,"wins":12},"gpt-5.6-sol":{"draws":15,"losses":18,"wins":5},"gpt-5.6-terra":{"draws":26,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":17},"minimax/minimax-m3":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":9},"o3":{"draws":3,"losses":4,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":12},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":27,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"z-ai/glm-5.2":{"draws":30,"losses":17,"wins":7}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":37,"wins":5},"claude-opus-4-5":{"draws":24,"losses":33,"wins":33},"claude-opus-4-8":{"draws":13,"losses":36,"wins":17},"claude-opus-5":{"draws":14,"losses":54,"wins":12},"claude-sonnet-5":{"draws":7,"losses":13,"wins":8},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":27},"deepseek/deepseek-v4-flash":{"draws":17,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":19,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":17,"wins":6},"google/gemini-3.5-flash-lite":{"draws":19,"losses":19,"wins":12},"google/gemini-3.6-flash":{"draws":18,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":3,"losses":13,"wins":22},"gpt-4.1":{"draws":5,"losses":9,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":8,"losses":13,"wins":15},"gpt-5.4":{"draws":13,"losses":40,"wins":13},"gpt-5.4-mini":{"draws":14,"losses":15,"wins":29},"gpt-5.4-nano":{"draws":12,"losses":30,"wins":30},"gpt-5.5":{"draws":16,"losses":28,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":26,"wins":30},"gpt-5.6-sol":{"draws":11,"losses":41,"wins":16},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":32},"inclusionai/ling-3.0-flash":{"draws":20,"losses":9,"wins":19},"meituan/longcat-2.0":{"draws":18,"losses":21,"wins":31},"minimax/minimax-m3":{"draws":14,"losses":18,"wins":30},"mistralai/mistral-medium-3-5":{"draws":5,"losses":13,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":16,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":15,"wins":17},"o3":{"draws":6,"losses":13,"wins":15},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":23},"poolside/laguna-s-2.1":{"draws":18,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":12,"losses":25,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":12,"losses":12,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":17,"wins":13},"x-ai/grok-4.5":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.5":{"draws":42,"losses":58,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":24,"wins":19},"z-ai/glm-5.2":{"draws":14,"losses":19,"wins":17}},"gpt-5.5":{"claude-fable-5":{"draws":8,"losses":24,"wins":22},"claude-opus-4-5":{"draws":31,"losses":24,"wins":33},"claude-opus-4-8":{"draws":19,"losses":22,"wins":35},"claude-opus-5":{"draws":21,"losses":94,"wins":33},"claude-sonnet-5":{"draws":9,"losses":5,"wins":10},"cohere/north-mini-code":{"draws":14,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":28,"losses":1,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":3,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":6,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":26,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":10,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":29,"losses":32,"wins":23},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":18,"wins":28},"gpt-5.5":{"draws":16,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":17,"losses":31,"wins":36},"gpt-5.6-terra":{"draws":28,"losses":16,"wins":26},"inclusionai/ling-3.0-flash":{"draws":27,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":5,"wins":23},"o3":{"draws":12,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":21,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.7-max":{"draws":17,"losses":11,"wins":16},"qwen/qwen3.7-plus":{"draws":13,"losses":4,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":5,"wins":17},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":22},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":16},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":37,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":10},"z-ai/glm-5.2":{"draws":22,"losses":13,"wins":21}},"gpt-5.6-luna":{"claude-fable-5":{"draws":6,"losses":33,"wins":7},"claude-opus-4-5":{"draws":37,"losses":27,"wins":30},"claude-opus-4-8":{"draws":17,"losses":26,"wins":19},"claude-opus-5":{"draws":16,"losses":68,"wins":14},"claude-sonnet-5":{"draws":10,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":16,"wins":7},"deepseek/deepseek-v4-flash":{"draws":32,"losses":25,"wins":21},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":15,"losses":15,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":25,"losses":6,"wins":13},"google/gemini-3.6-flash":{"draws":24,"losses":30,"wins":16},"google/gemma-4-31b-it":{"draws":8,"losses":12,"wins":8},"gpt-4.1":{"draws":12,"losses":4,"wins":10},"gpt-5":{"draws":19,"losses":17,"wins":16},"gpt-5.4":{"draws":33,"losses":43,"wins":10},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":30,"wins":26},"gpt-5.5":{"draws":17,"losses":29,"wins":18},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":16},"gpt-5.6-sol":{"draws":11,"losses":40,"wins":21},"gpt-5.6-terra":{"draws":21,"losses":34,"wins":23},"inclusionai/ling-3.0-flash":{"draws":30,"losses":11,"wins":5},"meituan/longcat-2.0":{"draws":26,"losses":11,"wins":15},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":12,"wins":11},"nex-agi/nex-n2-pro":{"draws":18,"losses":14,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":9,"wins":23},"o3":{"draws":7,"losses":16,"wins":23},"openai/gpt-oss-120b":{"draws":20,"losses":15,"wins":19},"poolside/laguna-s-2.1":{"draws":23,"losses":12,"wins":7},"qwen/qwen3.7-max":{"draws":22,"losses":11,"wins":15},"qwen/qwen3.7-plus":{"draws":11,"losses":11,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"tencent/hy3-preview":{"draws":13,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":13,"losses":20,"wins":13},"x-ai/grok-build-0.1":{"draws":19,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":37,"losses":37,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":14,"wins":5},"z-ai/glm-5.2":{"draws":24,"losses":26,"wins":14}},"gpt-5.6-sol":{"claude-fable-5":{"draws":13,"losses":41,"wins":20},"claude-opus-4-5":{"draws":27,"losses":15,"wins":54},"claude-opus-4-8":{"draws":15,"losses":23,"wins":40},"claude-opus-5":{"draws":29,"losses":122,"wins":35},"claude-sonnet-5":{"draws":4,"losses":6,"wins":20},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":20},"deepseek/deepseek-v4-flash":{"draws":5,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":20},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":12,"losses":11,"wins":21},"google/gemini-3.5-flash-lite":{"draws":11,"losses":6,"wins":13},"google/gemini-3.6-flash":{"draws":15,"losses":21,"wins":28},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":13},"gpt-5":{"draws":10,"losses":11,"wins":31},"gpt-5.4":{"draws":15,"losses":50,"wins":25},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":41},"gpt-5.5":{"draws":17,"losses":36,"wins":31},"gpt-5.6-luna":{"draws":11,"losses":21,"wins":40},"gpt-5.6-sol":{"draws":6,"losses":19,"wins":19},"gpt-5.6-terra":{"draws":16,"losses":27,"wins":41},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":9,"wins":8},"minimax/minimax-m3":{"draws":11,"losses":2,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":8,"wins":38},"o3":{"draws":4,"losses":10,"wins":28},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":0,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":23},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":25},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":16},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":31},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":27,"losses":14,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":17},"z-ai/glm-5.2":{"draws":11,"losses":13,"wins":28}},"gpt-5.6-terra":{"claude-fable-5":{"draws":7,"losses":48,"wins":5},"claude-opus-4-5":{"draws":42,"losses":29,"wins":37},"claude-opus-4-8":{"draws":22,"losses":27,"wins":17},"claude-opus-5":{"draws":37,"losses":107,"wins":18},"claude-sonnet-5":{"draws":9,"losses":11,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":22,"losses":7,"wins":37},"deepseek/deepseek-v4-pro":{"draws":17,"losses":10,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":17},"google/gemini-3.6-flash":{"draws":21,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":21},"gpt-4.1":{"draws":10,"losses":7,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":30,"losses":43,"wins":19},"gpt-5.4-mini":{"draws":26,"losses":11,"wins":23},"gpt-5.4-nano":{"draws":17,"losses":32,"wins":23},"gpt-5.5":{"draws":28,"losses":26,"wins":16},"gpt-5.6-luna":{"draws":21,"losses":23,"wins":34},"gpt-5.6-sol":{"draws":16,"losses":41,"wins":27},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":13},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":8,"wins":27},"o3":{"draws":5,"losses":16,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":12},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":12,"wins":13},"x-ai/grok-4.5":{"draws":17,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":12,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":45,"losses":16,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":32,"losses":25,"wins":17}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":18,"losses":13,"wins":7},"claude-opus-4-8":{"draws":18,"losses":4,"wins":0},"claude-opus-5":{"draws":12,"losses":22,"wins":2},"claude-sonnet-5":{"draws":9,"losses":15,"wins":2},"cohere/north-mini-code":{"draws":18,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":11},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":50,"losses":39,"wins":15},"google/gemini-3.6-flash":{"draws":67,"losses":46,"wins":19},"google/gemma-4-31b-it":{"draws":12,"losses":19,"wins":5},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":4,"wins":1},"gpt-5":{"draws":6,"losses":6,"wins":8},"gpt-5.4":{"draws":17,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":18,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":9},"gpt-5.5":{"draws":27,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":30,"losses":5,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":4},"inclusionai/ling-3.0-flash":{"draws":20,"losses":18,"wins":18},"meituan/longcat-2.0":{"draws":42,"losses":37,"wins":27},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":20,"losses":12,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":5},"o3":{"draws":7,"losses":27,"wins":8},"openai/gpt-oss-120b":{"draws":25,"losses":15,"wins":10},"poolside/laguna-s-2.1":{"draws":47,"losses":31,"wins":14},"qwen/qwen3.7-max":{"draws":21,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":14,"wins":6},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":33,"losses":32,"wins":27},"x-ai/grok-4.5":{"draws":19,"losses":44,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":30,"losses":24,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":8},"z-ai/glm-5.2":{"draws":18,"losses":2,"wins":4}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":28,"losses":30,"wins":17},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":10,"losses":48,"wins":10},"claude-sonnet-5":{"draws":7,"losses":17,"wins":6},"cohere/north-mini-code":{"draws":22,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":19,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":16,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":3},"google/gemini-3.5-flash-lite":{"draws":38,"losses":54,"wins":47},"google/gemini-3.6-flash":{"draws":45,"losses":59,"wins":28},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":13},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":8,"losses":16,"wins":6},"gpt-5.4":{"draws":13,"losses":11,"wins":10},"gpt-5.4-mini":{"draws":21,"losses":17,"wins":10},"gpt-5.4-nano":{"draws":18,"losses":31,"wins":21},"gpt-5.5":{"draws":16,"losses":12,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":9},"gpt-5.6-terra":{"draws":16,"losses":16,"wins":14},"inclusionai/ling-3.0-flash":{"draws":42,"losses":27,"wins":37},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":18,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":31,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":13,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":18,"wins":9},"o3":{"draws":12,"losses":45,"wins":25},"openai/gpt-oss-120b":{"draws":23,"losses":14,"wins":21},"poolside/laguna-s-2.1":{"draws":46,"losses":32,"wins":26},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":22,"wins":15},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":24,"losses":43,"wins":33},"x-ai/grok-4.5":{"draws":24,"losses":56,"wins":16},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":29,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":18,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":18,"wins":10}},"minimax/minimax-m3":{"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-opus-4-5":{"draws":11,"losses":28,"wins":7},"claude-opus-4-8":{"draws":11,"losses":19,"wins":4},"claude-opus-5":{"draws":3,"losses":33,"wins":4},"claude-sonnet-5":{"draws":6,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":9},"google/gemini-3.1-flash-lite":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":9,"losses":11,"wins":6},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":11,"wins":6},"gpt-5.4":{"draws":10,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":30,"wins":18},"gpt-5.5":{"draws":9,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":10},"gpt-5.6-sol":{"draws":11,"losses":23,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":18},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":9},"o3":{"draws":5,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.7-max":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":26,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":10,"wins":6}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":20,"wins":0},"claude-opus-4-8":{"draws":2,"losses":18,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":15,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":14,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":9,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":14,"wins":4},"gpt-5.4":{"draws":1,"losses":15,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":13},"gpt-5.5":{"draws":2,"losses":12,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":19,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":8},"o3":{"draws":3,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":22,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":6}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-sonnet-5":{"draws":5,"losses":6,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":25,"losses":19,"wins":26},"claude-opus-4-8":{"draws":8,"losses":9,"wins":13},"claude-opus-5":{"draws":14,"losses":61,"wins":11},"claude-sonnet-5":{"draws":10,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":10,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":45,"losses":26,"wins":63},"google/gemini-3.6-flash":{"draws":40,"losses":58,"wins":42},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":3,"wins":5},"gpt-5.4":{"draws":11,"losses":14,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":19},"gpt-5.5":{"draws":15,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":21,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":20},"meituan/longcat-2.0":{"draws":25,"losses":8,"wins":31},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":20,"losses":14,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":4},"o3":{"draws":6,"losses":32,"wins":26},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":29},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":14},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":11},"thinkingmachines/inkling":{"draws":25,"losses":7,"wins":40},"x-ai/grok-4.5":{"draws":31,"losses":34,"wins":35},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":2,"losses":3,"wins":1}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":9,"losses":20,"wins":7},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":0,"losses":15,"wins":1},"claude-sonnet-5":{"draws":2,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":8},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":4,"losses":10,"wins":2},"gpt-5.4":{"draws":10,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":16},"gpt-5.5":{"draws":8,"losses":15,"wins":3},"gpt-5.6-luna":{"draws":18,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":16,"wins":9},"o3":{"draws":2,"losses":11,"wins":3},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":7},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":29,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":14,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":4,"losses":27,"wins":1},"claude-opus-4-5":{"draws":35,"losses":29,"wins":16},"claude-opus-4-8":{"draws":14,"losses":31,"wins":11},"claude-opus-5":{"draws":11,"losses":43,"wins":0},"claude-sonnet-5":{"draws":9,"losses":4,"wins":9},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":36,"losses":24,"wins":22},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":13,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-5":{"draws":17,"losses":15,"wins":6},"gpt-5.4":{"draws":16,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":18,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":17,"wins":15},"gpt-5.5":{"draws":22,"losses":23,"wins":5},"gpt-5.6-luna":{"draws":32,"losses":23,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":8},"gpt-5.6-terra":{"draws":25,"losses":27,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":18},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":3},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":7},"o3":{"draws":18,"losses":30,"wins":10},"openai/gpt-oss-120b":{"draws":21,"losses":11,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":18,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":24},"x-ai/grok-4.5":{"draws":10,"losses":15,"wins":1},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":23,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":3},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":11}},"o3":{"claude-fable-5":{"draws":1,"losses":31,"wins":2},"claude-opus-4-5":{"draws":18,"losses":58,"wins":30},"claude-opus-4-8":{"draws":4,"losses":34,"wins":6},"claude-opus-5":{"draws":2,"losses":68,"wins":6},"claude-sonnet-5":{"draws":6,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":11,"losses":20,"wins":15},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":15},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":8,"losses":10,"wins":18},"google/gemini-3.5-flash-lite":{"draws":27,"losses":50,"wins":105},"google/gemini-3.6-flash":{"draws":30,"losses":76,"wins":56},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":7},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":6,"losses":20,"wins":16},"gpt-5.4":{"draws":7,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":13},"gpt-5.5":{"draws":12,"losses":34,"wins":6},"gpt-5.6-luna":{"draws":7,"losses":23,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":10},"gpt-5.6-terra":{"draws":5,"losses":27,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":27},"meituan/longcat-2.0":{"draws":12,"losses":25,"wins":45},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":26,"wins":32},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":30},"o3":{"draws":10,"losses":61,"wins":61},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":29},"poolside/laguna-s-2.1":{"draws":20,"losses":18,"wins":26},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":36},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":21,"wins":43},"x-ai/grok-4.5":{"draws":8,"losses":34,"wins":20},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":5,"losses":11,"wins":8}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":4,"losses":19,"wins":1},"claude-opus-4-5":{"draws":27,"losses":44,"wins":9},"claude-opus-4-8":{"draws":13,"losses":23,"wins":6},"claude-opus-5":{"draws":4,"losses":21,"wins":3},"claude-sonnet-5":{"draws":7,"losses":7,"wins":0},"cohere/north-mini-code":{"draws":16,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":22},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":22,"losses":38,"wins":18},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":6,"wins":2},"gpt-5.4":{"draws":12,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":23,"wins":13},"gpt-5.5":{"draws":21,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":19,"wins":15},"gpt-5.6-sol":{"draws":14,"losses":28,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":5},"inclusionai/ling-3.0-flash":{"draws":25,"losses":10,"wins":15},"meituan/longcat-2.0":{"draws":23,"losses":21,"wins":14},"minimax/minimax-m3":{"draws":9,"losses":13,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":19,"wins":3},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":8,"wins":11},"o3":{"draws":14,"losses":29,"wins":11},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":13},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":5},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":22,"wins":21},"x-ai/grok-4.5":{"draws":11,"losses":21,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":36,"losses":26,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":8,"wins":9}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":4,"wins":6},"claude-opus-4-5":{"draws":29,"losses":24,"wins":5},"claude-opus-4-8":{"draws":12,"losses":23,"wins":5},"claude-opus-5":{"draws":8,"losses":66,"wins":8},"claude-sonnet-5":{"draws":14,"losses":11,"wins":5},"cohere/north-mini-code":{"draws":21,"losses":15,"wins":2},"deepseek/deepseek-v4-flash":{"draws":23,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":60,"losses":38,"wins":44},"google/gemini-3.6-flash":{"draws":63,"losses":49,"wins":26},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":11,"losses":6,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":18,"losses":14,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":14},"gpt-5.6-luna":{"draws":23,"losses":7,"wins":12},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":12},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"inclusionai/ling-3.0-flash":{"draws":47,"losses":14,"wins":31},"meituan/longcat-2.0":{"draws":46,"losses":26,"wins":32},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":14},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":31,"losses":29,"wins":10},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":9},"o3":{"draws":20,"losses":26,"wins":18},"openai/gpt-oss-120b":{"draws":17,"losses":14,"wins":13},"poolside/laguna-s-2.1":{"draws":42,"losses":23,"wins":23},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":15,"losses":3,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":16,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":34,"losses":25,"wins":41},"x-ai/grok-4.5":{"draws":25,"losses":54,"wins":15},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":19,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":22,"losses":13,"wins":13}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":3,"losses":17,"wins":4},"claude-opus-4-5":{"draws":22,"losses":28,"wins":14},"claude-opus-4-8":{"draws":12,"losses":17,"wins":11},"claude-opus-5":{"draws":12,"losses":55,"wins":7},"claude-sonnet-5":{"draws":7,"losses":6,"wins":7},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":11,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":9},"google/gemini-3.5-flash-lite":{"draws":7,"losses":7,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":14},"gpt-4.1":{"draws":7,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":10,"wins":4},"gpt-5.4":{"draws":9,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":17,"losses":15,"wins":22},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":18,"losses":4,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"o3":{"draws":10,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":9}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":23,"losses":18,"wins":11},"claude-opus-4-8":{"draws":12,"losses":20,"wins":6},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"claude-sonnet-5":{"draws":6,"losses":3,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":12,"losses":16,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":13,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":12,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":12,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":10,"losses":19,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":25},"gpt-5.5":{"draws":13,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":10,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":13},"o3":{"draws":3,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":8,"wins":13},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":25,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":6}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":3,"losses":19,"wins":0},"claude-opus-4-5":{"draws":14,"losses":36,"wins":10},"claude-opus-4-8":{"draws":7,"losses":21,"wins":8},"claude-opus-5":{"draws":5,"losses":26,"wins":1},"claude-sonnet-5":{"draws":3,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":8,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":3},"google/gemini-3.5-flash-lite":{"draws":11,"losses":18,"wins":25},"google/gemini-3.6-flash":{"draws":5,"losses":22,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":13},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":8,"losses":14,"wins":0},"gpt-5.4":{"draws":5,"losses":15,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":10},"gpt-5.5":{"draws":6,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":4},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":5,"losses":15,"wins":22},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":14,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":10},"o3":{"draws":9,"losses":36,"wins":19},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":10},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":16,"wins":28},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":4}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":20,"wins":5},"claude-opus-4-5":{"draws":17,"losses":19,"wins":8},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":48,"wins":7},"claude-sonnet-5":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":11,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":3},"gpt-5":{"draws":5,"losses":9,"wins":8},"gpt-5.4":{"draws":17,"losses":23,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":12},"gpt-5.5":{"draws":24,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":13,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":13,"losses":25,"wins":10},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":11,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":14},"o3":{"draws":10,"losses":12,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":11,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":20,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":19,"losses":8,"wins":9}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":4,"losses":10,"wins":0},"claude-opus-4-5":{"draws":28,"losses":43,"wins":11},"claude-opus-4-8":{"draws":8,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":52,"wins":11},"claude-sonnet-5":{"draws":17,"losses":11,"wins":4},"cohere/north-mini-code":{"draws":9,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":21,"losses":20,"wins":17},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":4},"google/gemini-3.1-flash-lite":{"draws":11,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":18,"wins":4},"google/gemini-3.5-flash-lite":{"draws":48,"losses":63,"wins":43},"google/gemini-3.6-flash":{"draws":64,"losses":67,"wins":23},"google/gemma-4-31b-it":{"draws":4,"losses":14,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":12,"losses":13,"wins":5},"gpt-5.4":{"draws":16,"losses":15,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":17},"gpt-5.5":{"draws":15,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":18,"losses":14,"wins":10},"gpt-5.6-sol":{"draws":10,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":21,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":33,"losses":27,"wins":32},"meituan/longcat-2.0":{"draws":24,"losses":33,"wins":43},"minimax/minimax-m3":{"draws":6,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":14,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":40,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":24,"wins":15},"o3":{"draws":19,"losses":43,"wins":21},"openai/gpt-oss-120b":{"draws":17,"losses":21,"wins":22},"poolside/laguna-s-2.1":{"draws":34,"losses":41,"wins":25},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":13,"wins":8},"stepfun/step-3.7-flash":{"draws":10,"losses":28,"wins":16},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":14,"losses":21,"wins":21},"x-ai/grok-4.5":{"draws":25,"losses":33,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":42,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":18,"wins":10}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":7,"losses":30,"wins":7},"claude-opus-4-5":{"draws":31,"losses":26,"wins":37},"claude-opus-4-8":{"draws":15,"losses":19,"wins":20},"claude-opus-5":{"draws":16,"losses":83,"wins":21},"claude-sonnet-5":{"draws":11,"losses":6,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":6,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":17},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash-lite":{"draws":29,"losses":32,"wins":67},"google/gemini-3.6-flash":{"draws":31,"losses":64,"wins":57},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":10},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":6,"wins":18},"gpt-5.4":{"draws":12,"losses":30,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":14},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":23},"gpt-5.5":{"draws":14,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":13,"losses":13,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":17,"losses":16,"wins":23},"inclusionai/ling-3.0-flash":{"draws":19,"losses":9,"wins":44},"meituan/longcat-2.0":{"draws":24,"losses":16,"wins":56},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":31,"losses":35,"wins":34},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":15},"o3":{"draws":8,"losses":20,"wins":34},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":54},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":13},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":20},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":33},"x-ai/grok-4.5":{"draws":18,"losses":23,"wins":23},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":10},"z-ai/glm-5.2":{"draws":5,"losses":5,"wins":4}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":5,"losses":41,"wins":2},"claude-opus-4-5":{"draws":62,"losses":55,"wins":33},"claude-opus-4-8":{"draws":38,"losses":46,"wins":12},"claude-opus-5":{"draws":9,"losses":50,"wins":3},"claude-sonnet-5":{"draws":30,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":27,"losses":15,"wins":24},"deepseek/deepseek-v4-flash":{"draws":48,"losses":31,"wins":49},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":11},"google/gemini-3.1-flash-lite":{"draws":35,"losses":25,"wins":42},"google/gemini-3.5-flash":{"draws":28,"losses":25,"wins":9},"google/gemini-3.5-flash-lite":{"draws":11,"losses":12,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":17,"losses":27,"wins":26},"gpt-4.1":{"draws":13,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":31,"losses":23,"wins":18},"gpt-5.4":{"draws":36,"losses":45,"wins":9},"gpt-5.4-mini":{"draws":39,"losses":28,"wins":27},"gpt-5.4-nano":{"draws":42,"losses":60,"wins":58},"gpt-5.5":{"draws":37,"losses":33,"wins":10},"gpt-5.6-luna":{"draws":37,"losses":30,"wins":37},"gpt-5.6-sol":{"draws":27,"losses":53,"wins":14},"gpt-5.6-terra":{"draws":45,"losses":35,"wins":16},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":24},"meituan/longcat-2.0":{"draws":23,"losses":32,"wins":29},"minimax/minimax-m3":{"draws":28,"losses":30,"wins":26},"mistralai/mistral-medium-3-5":{"draws":10,"losses":14,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":22,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":18,"losses":19,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":31,"wins":23},"o3":{"draws":12,"losses":24,"wins":4},"openai/gpt-oss-120b":{"draws":36,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":23,"losses":24,"wins":19},"qwen/qwen3.7-max":{"draws":28,"losses":31,"wins":19},"qwen/qwen3.7-plus":{"draws":23,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":28,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":42},"x-ai/grok-4.5":{"draws":16,"losses":23,"wins":5},"x-ai/grok-build-0.1":{"draws":24,"losses":18,"wins":10},"xiaomi/mimo-v2.5":{"draws":76,"losses":56,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":32,"losses":46,"wins":26}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":7,"losses":21,"wins":18},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":8,"losses":35,"wins":1},"claude-sonnet-5":{"draws":6,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":18},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":2,"losses":11,"wins":5},"gpt-5":{"draws":5,"losses":8,"wins":5},"gpt-5.4":{"draws":6,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":24},"gpt-5.5":{"draws":8,"losses":10,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":11},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":10},"o3":{"draws":4,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":16},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":30},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":10}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":22,"losses":44,"wins":38},"claude-opus-4-8":{"draws":23,"losses":25,"wins":16},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-sonnet-5":{"draws":12,"losses":18,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":32,"losses":12,"wins":34},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":21},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":11},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":7},"google/gemini-3.6-flash":{"draws":11,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":3},"gpt-4.1":{"draws":12,"losses":8,"wins":12},"gpt-5":{"draws":14,"losses":19,"wins":17},"gpt-5.4":{"draws":32,"losses":17,"wins":13},"gpt-5.4-mini":{"draws":30,"losses":7,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":19},"gpt-5.5":{"draws":22,"losses":21,"wins":13},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":26},"gpt-5.6-sol":{"draws":11,"losses":28,"wins":13},"gpt-5.6-terra":{"draws":32,"losses":17,"wins":25},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":18},"minimax/minimax-m3":{"draws":14,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":11},"o3":{"draws":5,"losses":8,"wins":11},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":8},"poolside/laguna-s-2.1":{"draws":22,"losses":13,"wins":13},"qwen/qwen3.7-max":{"draws":14,"losses":9,"wins":17},"qwen/qwen3.7-plus":{"draws":13,"losses":6,"wins":15},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":19,"losses":9,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":26,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":12},"z-ai/glm-5.2":{"draws":28,"losses":22,"wins":22}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":2,"wins":10},"claude-opus-4-5":{"draws":4,"losses":4,"wins":24},"claude-opus-4-8":{"draws":3,"losses":10,"wins":17},"claude-opus-5":{"draws":17,"losses":30,"wins":43},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":19},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":19},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":21},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":7,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":21},"gpt-5.4":{"draws":3,"losses":14,"wins":19},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":16},"gpt-5.5":{"draws":5,"losses":11,"wins":14},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":11,"losses":8,"wins":25},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":16},"o3":{"draws":0,"losses":2,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":11},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":15},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":20},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":13}},"claude-opus-4-5":{"claude-fable-5":{"draws":0,"losses":15,"wins":1},"claude-opus-4-5":{"draws":2,"losses":5,"wins":3},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":7,"losses":68,"wins":3},"claude-sonnet-5":{"draws":1,"losses":3,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":3},"google/gemini-3.5-flash-lite":{"draws":23,"losses":10,"wins":17},"google/gemini-3.6-flash":{"draws":12,"losses":21,"wins":15},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":7,"losses":5,"wins":4},"gpt-5.4":{"draws":4,"losses":11,"wins":1},"gpt-5.5":{"draws":2,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":9,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":8},"o3":{"draws":6,"losses":8,"wins":26},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":11,"losses":0,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":13},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":8}},"claude-opus-4-8":{"claude-fable-5":{"draws":4,"losses":12,"wins":18},"claude-opus-4-5":{"draws":3,"losses":8,"wins":25},"claude-opus-4-8":{"draws":0,"losses":3,"wins":5},"claude-opus-5":{"draws":14,"losses":33,"wins":23},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":5,"wins":16},"gpt-5.4":{"draws":6,"losses":13,"wins":11},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":8},"gpt-5.5":{"draws":4,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":16,"wins":16},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":15},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":18},"o3":{"draws":0,"losses":5,"wins":25},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":6,"wins":11}},"claude-opus-5":{"claude-fable-5":{"draws":7,"losses":19,"wins":26},"claude-opus-4-5":{"draws":3,"losses":6,"wins":53},"claude-opus-4-8":{"draws":2,"losses":12,"wins":16},"claude-opus-5":{"draws":14,"losses":51,"wins":81},"claude-sonnet-5":{"draws":0,"losses":0,"wins":14},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":13},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":23},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":34},"google/gemini-3.6-flash":{"draws":4,"losses":8,"wins":34},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":0,"losses":2,"wins":16},"gpt-5.4":{"draws":0,"losses":9,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":3},"gpt-5.5":{"draws":0,"losses":7,"wins":23},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":15},"o3":{"draws":0,"losses":3,"wins":41},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":19},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":23},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"claude-sonnet-5":{"claude-fable-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-5":{"draws":4,"losses":1,"wins":5},"claude-opus-5":{"draws":2,"losses":20,"wins":2},"claude-sonnet-5":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":3,"losses":4,"wins":3},"google/gemini-3.6-flash":{"draws":4,"losses":4,"wins":2},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":0,"wins":4},"gpt-5.4":{"draws":5,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":1},"gpt-5.5":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":4},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":1,"wins":1},"o3":{"draws":1,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":5,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":7}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":0,"losses":12,"wins":2},"claude-opus-4-5":{"draws":9,"losses":11,"wins":8},"claude-opus-4-8":{"draws":0,"losses":9,"wins":5},"claude-opus-5":{"draws":3,"losses":15,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":11,"wins":3},"gpt-5.4":{"draws":8,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":3},"gpt-5.5":{"draws":3,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":8},"o3":{"draws":5,"losses":11,"wins":18},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":6}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":2},"claude-opus-4-5":{"draws":9,"losses":12,"wins":3},"claude-opus-4-8":{"draws":5,"losses":13,"wins":6},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"claude-sonnet-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":18},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":3,"losses":4,"wins":11},"gpt-5.4":{"draws":1,"losses":19,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":0},"gpt-5.5":{"draws":8,"losses":10,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":5},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":12},"o3":{"draws":7,"losses":13,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":7},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":8}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":6,"losses":14,"wins":2},"claude-opus-4-8":{"draws":3,"losses":13,"wins":2},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":8,"wins":0},"gpt-5.4":{"draws":1,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":3},"gpt-5.5":{"draws":4,"losses":12,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":3},"o3":{"draws":4,"losses":16,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":3}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":2,"losses":16,"wins":4},"claude-opus-4-5":{"draws":8,"losses":5,"wins":11},"claude-opus-4-8":{"draws":1,"losses":6,"wins":7},"claude-opus-5":{"draws":4,"losses":32,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":5,"wins":7},"gpt-5.4":{"draws":3,"losses":7,"wins":6},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":8,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":9,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"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":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":12},"o3":{"draws":7,"losses":12,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":9}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":11,"losses":14,"wins":9},"claude-opus-4-8":{"draws":0,"losses":12,"wins":2},"claude-opus-5":{"draws":3,"losses":30,"wins":1},"claude-sonnet-5":{"draws":5,"losses":3,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":8,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":18,"losses":26,"wins":30},"google/gemini-3.6-flash":{"draws":20,"losses":30,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":10,"losses":6,"wins":2},"gpt-5.4":{"draws":2,"losses":8,"wins":0},"gpt-5.5":{"draws":6,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":9},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":9},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":6},"o3":{"draws":4,"losses":42,"wins":26},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":20},"poolside/laguna-s-2.1":{"draws":11,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":10,"wins":16},"x-ai/grok-4.5":{"draws":4,"losses":9,"wins":11},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":3}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":15,"wins":5},"claude-opus-4-5":{"draws":4,"losses":10,"wins":18},"claude-opus-4-8":{"draws":2,"losses":10,"wins":10},"claude-opus-5":{"draws":8,"losses":35,"wins":11},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":7},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":30},"google/gemini-3.6-flash":{"draws":13,"losses":22,"wins":31},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":12},"gpt-5.4":{"draws":4,"losses":12,"wins":4},"gpt-5.5":{"draws":4,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":3,"losses":11,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":2,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":11},"o3":{"draws":7,"losses":13,"wins":34},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":17},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":12},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":19},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":23},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":20,"wins":1},"claude-opus-4-5":{"draws":19,"losses":9,"wins":10},"claude-opus-4-8":{"draws":4,"losses":15,"wins":5},"claude-opus-5":{"draws":3,"losses":37,"wins":2},"claude-sonnet-5":{"draws":6,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":7,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":7},"gpt-5.5":{"draws":8,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":10},"o3":{"draws":3,"losses":12,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":5,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":11,"wins":13}},"gpt-5.4":{"claude-fable-5":{"draws":4,"losses":11,"wins":19},"claude-opus-4-5":{"draws":11,"losses":7,"wins":16},"claude-opus-4-8":{"draws":5,"losses":8,"wins":15},"claude-opus-5":{"draws":7,"losses":39,"wins":34},"claude-sonnet-5":{"draws":3,"losses":1,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":18},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":11},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":8},"google/gemini-3.6-flash":{"draws":4,"losses":4,"wins":14},"gpt-5":{"draws":4,"losses":3,"wins":15},"gpt-5.4":{"draws":4,"losses":2,"wins":12},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":9},"gpt-5.5":{"draws":12,"losses":6,"wins":14},"gpt-5.6-luna":{"draws":9,"losses":2,"wins":23},"gpt-5.6-sol":{"draws":7,"losses":5,"wins":24},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":21},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":17},"o3":{"draws":2,"losses":2,"wins":22},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":15},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":9}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":11,"wins":16},"claude-opus-4-5":{"draws":6,"losses":5,"wins":17},"claude-opus-4-8":{"draws":2,"losses":3,"wins":19},"claude-opus-5":{"draws":1,"losses":38,"wins":27},"claude-sonnet-5":{"draws":3,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":11},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":3,"wins":14},"gpt-5.4":{"draws":11,"losses":10,"wins":13},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":10},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":20},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":11},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":11},"o3":{"draws":1,"losses":2,"wins":27},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":12}},"gpt-5.6-luna":{"claude-fable-5":{"draws":4,"losses":19,"wins":5},"claude-opus-4-5":{"draws":7,"losses":7,"wins":18},"claude-opus-4-8":{"draws":3,"losses":10,"wins":13},"claude-opus-5":{"draws":10,"losses":45,"wins":9},"claude-sonnet-5":{"draws":3,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":8,"wins":13},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":10},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":11},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":9,"wins":8},"gpt-5.4":{"draws":10,"losses":16,"wins":6},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":3},"gpt-5.5":{"draws":2,"losses":10,"wins":12},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":14},"gpt-5.6-terra":{"draws":5,"losses":15,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":16},"o3":{"draws":1,"losses":10,"wins":17},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":8}},"gpt-5.6-sol":{"claude-fable-5":{"draws":9,"losses":15,"wins":14},"claude-opus-4-5":{"draws":5,"losses":5,"wins":22},"claude-opus-4-8":{"draws":3,"losses":7,"wins":16},"claude-opus-5":{"draws":14,"losses":48,"wins":24},"claude-sonnet-5":{"draws":0,"losses":2,"wins":8},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":5,"wins":17},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":13},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":16},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":5,"wins":18},"gpt-5.4":{"draws":5,"losses":19,"wins":10},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":7},"gpt-5.5":{"draws":3,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":0,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":8},"gpt-5.6-terra":{"draws":3,"losses":11,"wins":16},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":17},"o3":{"draws":1,"losses":6,"wins":17},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":13},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":18},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":3,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":13}},"gpt-5.6-terra":{"claude-fable-5":{"draws":4,"losses":30,"wins":4},"claude-opus-4-5":{"draws":11,"losses":8,"wins":17},"claude-opus-4-8":{"draws":1,"losses":16,"wins":5},"claude-opus-5":{"draws":12,"losses":52,"wins":10},"claude-sonnet-5":{"draws":2,"losses":5,"wins":1},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":5,"wins":16},"gpt-5.4":{"draws":8,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":6},"gpt-5.5":{"draws":5,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":10,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":19},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":13},"o3":{"draws":1,"losses":9,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":11}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":8,"wins":0},"claude-opus-4-8":{"draws":0,"losses":10,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":15,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":12,"wins":0},"gpt-5.4":{"draws":0,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":7},"gpt-5.5":{"draws":0,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":9,"wins":5},"o3":{"draws":0,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":6,"losses":2,"wins":6},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":5,"losses":20,"wins":1},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":3},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":18},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":13},"gpt-5":{"draws":2,"losses":1,"wins":5},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":3},"o3":{"draws":0,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":9},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":3,"losses":15,"wins":0},"claude-opus-4-5":{"draws":25,"losses":18,"wins":5},"claude-opus-4-8":{"draws":8,"losses":18,"wins":4},"claude-opus-5":{"draws":1,"losses":13,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":22,"losses":9,"wins":13},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":9,"wins":1},"gpt-5.4":{"draws":4,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":4},"gpt-5.5":{"draws":7,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":17,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":21},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":21,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":5,"losses":6,"wins":5}},"o3":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":8,"losses":38,"wins":18},"claude-opus-4-8":{"draws":0,"losses":25,"wins":3},"claude-opus-5":{"draws":0,"losses":43,"wins":3},"claude-sonnet-5":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":4,"losses":15,"wins":9},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":13},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":11},"google/gemini-3.5-flash-lite":{"draws":16,"losses":31,"wins":85},"google/gemini-3.6-flash":{"draws":16,"losses":54,"wins":46},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":3,"losses":13,"wins":12},"gpt-5.4":{"draws":1,"losses":19,"wins":2},"gpt-5.5":{"draws":1,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":1,"losses":16,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":0,"losses":19,"wins":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":11},"meituan/longcat-2.0":{"draws":2,"losses":9,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":20},"moonshotai/kimi-k3":{"draws":5,"losses":16,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"o3":{"draws":7,"losses":49,"wins":58},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":21},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":33},"tencent/hy3-preview":{"draws":3,"losses":13,"wins":10},"thinkingmachines/inkling":{"draws":7,"losses":11,"wins":35},"x-ai/grok-4.5":{"draws":3,"losses":23,"wins":14},"z-ai/glm-5.2":{"draws":1,"losses":3,"wins":0}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":10,"wins":1},"claude-opus-4-5":{"draws":9,"losses":4,"wins":5},"claude-opus-4-8":{"draws":6,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":13,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":11,"losses":3,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":7,"losses":2,"wins":1},"gpt-5.4":{"draws":3,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":2},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":5},"o3":{"draws":4,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":3}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":3,"losses":15,"wins":4},"claude-opus-4-8":{"draws":2,"losses":10,"wins":4},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":4,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":6},"gpt-5.5":{"draws":0,"losses":10,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":9},"o3":{"draws":5,"losses":19,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":17},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":17,"wins":1},"claude-opus-4-5":{"draws":11,"losses":12,"wins":5},"claude-opus-4-8":{"draws":3,"losses":10,"wins":7},"claude-opus-5":{"draws":3,"losses":35,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":9,"wins":8},"gpt-5.4":{"draws":6,"losses":14,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":12,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":7},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":12},"o3":{"draws":5,"losses":12,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":8,"wins":8},"z-ai/glm-5.2":{"draws":7,"losses":3,"wins":6}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-8":{"draws":2,"losses":8,"wins":0},"claude-opus-5":{"draws":1,"losses":15,"wins":2},"claude-sonnet-5":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":5,"losses":7,"wins":0},"deepseek/deepseek-v4-pro":{"draws":6,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":20,"losses":30,"wins":22},"google/gemini-3.6-flash":{"draws":18,"losses":29,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":0,"losses":5,"wins":1},"gpt-5.5":{"draws":1,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":9,"wins":0},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":3},"o3":{"draws":8,"losses":30,"wins":12},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":14,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":13,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":0}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":2,"losses":12,"wins":4},"claude-opus-4-5":{"draws":9,"losses":4,"wins":13},"claude-opus-4-8":{"draws":6,"losses":7,"wins":3},"claude-opus-5":{"draws":5,"losses":28,"wins":9},"claude-sonnet-5":{"draws":3,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":2},"google/gemini-3.5-flash-lite":{"draws":4,"losses":15,"wins":25},"google/gemini-3.6-flash":{"draws":7,"losses":24,"wins":25},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4":{"draws":4,"losses":8,"wins":4},"gpt-5.5":{"draws":3,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":4},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":18},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":10,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":8},"o3":{"draws":3,"losses":4,"wins":19},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":22},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":13},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":6,"wins":13},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":0}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":12,"losses":5,"wins":3},"claude-opus-4-8":{"draws":7,"losses":2,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":5,"losses":0,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":3,"wins":2},"gpt-5.4":{"draws":5,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":3},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":2},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":4}},"z-ai/glm-5.2":{"claude-opus-4-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":5,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":3},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"o3":{"draws":1,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":5,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":1}}},"medium":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":3,"losses":4,"wins":21},"claude-opus-4-8":{"draws":3,"losses":16,"wins":11},"claude-opus-5":{"draws":8,"losses":28,"wins":14},"claude-sonnet-5":{"draws":2,"losses":0,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":1,"losses":2,"wins":13},"gpt-5.4":{"draws":5,"losses":14,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":9},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":21},"gpt-5.5":{"draws":3,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":16},"gpt-5.6-sol":{"draws":2,"losses":12,"wins":16},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":11},"o3":{"draws":1,"losses":0,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":12},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":8}},"claude-opus-4-5":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":4,"losses":3,"wins":5},"claude-opus-4-8":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":6,"losses":22,"wins":6},"claude-sonnet-5":{"draws":6,"losses":3,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":7,"wins":25},"google/gemini-3.6-flash":{"draws":9,"losses":19,"wins":12},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":4,"wins":7},"gpt-5.4":{"draws":6,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":12},"gpt-5.5":{"draws":6,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":12,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":9,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":4},"o3":{"draws":6,"losses":16,"wins":20},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":15},"poolside/laguna-s-2.1":{"draws":6,"losses":1,"wins":7},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":15,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":2}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":10,"wins":6},"claude-opus-4-5":{"draws":6,"losses":11,"wins":13},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":3,"losses":14,"wins":1},"claude-sonnet-5":{"draws":6,"losses":3,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":9},"gpt-5.4":{"draws":6,"losses":10,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":14},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":4,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":10}},"claude-opus-5":{"claude-fable-5":{"draws":10,"losses":21,"wins":17},"claude-opus-4-5":{"draws":15,"losses":6,"wins":73},"claude-opus-4-8":{"draws":8,"losses":9,"wins":25},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"claude-sonnet-5":{"draws":3,"losses":2,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":21},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":19},"google/gemini-3.6-flash":{"draws":3,"losses":11,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":19},"gpt-5":{"draws":3,"losses":2,"wins":17},"gpt-5.4":{"draws":4,"losses":18,"wins":34},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":19},"gpt-5.5":{"draws":7,"losses":16,"wins":35},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":48},"gpt-5.6-terra":{"draws":17,"losses":5,"wins":44},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":5,"losses":1,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":16},"o3":{"draws":0,"losses":0,"wins":14},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":31},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":24},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":13},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":32}},"claude-sonnet-5":{"claude-fable-5":{"draws":2,"losses":12,"wins":0},"claude-opus-4-5":{"draws":13,"losses":13,"wins":14},"claude-opus-4-8":{"draws":6,"losses":5,"wins":7},"claude-opus-5":{"draws":5,"losses":20,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":4},"google/gemini-3.5-flash-lite":{"draws":8,"losses":0,"wins":14},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":3},"gpt-5.4":{"draws":5,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":11},"gpt-5.5":{"draws":4,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":14,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":17},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":4},"o3":{"draws":3,"losses":1,"wins":8},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":11,"losses":4,"wins":11}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":4,"losses":11,"wins":3},"claude-opus-4-8":{"draws":5,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":4,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":13,"wins":2},"gpt-5.4":{"draws":4,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":5},"gpt-5.5":{"draws":7,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":2,"losses":7,"wins":1},"claude-opus-4-5":{"draws":9,"losses":6,"wins":3},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":21,"wins":0},"claude-sonnet-5":{"draws":5,"losses":10,"wins":1},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":13},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":19,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":8},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-5":{"draws":7,"losses":6,"wins":1},"gpt-5.4":{"draws":10,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":13},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":3,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":3},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":15,"wins":3},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":20,"wins":4}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":13,"wins":0},"claude-opus-4-5":{"draws":6,"losses":20,"wins":0},"claude-opus-4-8":{"draws":6,"losses":10,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":1},"claude-sonnet-5":{"draws":5,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":8,"wins":9},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":13,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":9},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":6,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":1},"xiaomi/mimo-v2.5":{"draws":17,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":4}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-5":{"draws":10,"losses":11,"wins":11},"claude-opus-4-8":{"draws":12,"losses":5,"wins":11},"claude-opus-5":{"draws":7,"losses":28,"wins":11},"claude-sonnet-5":{"draws":6,"losses":5,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":4,"losses":6,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4":{"draws":12,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":15},"gpt-5.5":{"draws":3,"losses":9,"wins":14},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":8},"o3":{"draws":1,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":7}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":17,"losses":18,"wins":3},"claude-opus-4-8":{"draws":11,"losses":7,"wins":0},"claude-opus-5":{"draws":6,"losses":14,"wins":2},"claude-sonnet-5":{"draws":12,"losses":14,"wins":0},"cohere/north-mini-code":{"draws":12,"losses":10,"wins":0},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash-lite":{"draws":29,"losses":23,"wins":30},"google/gemini-3.6-flash":{"draws":34,"losses":27,"wins":12},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":1},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":5},"gpt-5.4":{"draws":2,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":13,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":10},"gpt-5.5":{"draws":13,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":8},"meituan/longcat-2.0":{"draws":14,"losses":21,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":2},"o3":{"draws":15,"losses":48,"wins":9},"openai/gpt-oss-120b":{"draws":13,"losses":11,"wins":14},"poolside/laguna-s-2.1":{"draws":19,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":2},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":4},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":15,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":5}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":0,"losses":7,"wins":9},"claude-opus-4-5":{"draws":11,"losses":10,"wins":19},"claude-opus-4-8":{"draws":10,"losses":4,"wins":14},"claude-opus-5":{"draws":3,"losses":27,"wins":14},"claude-sonnet-5":{"draws":6,"losses":4,"wins":14},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":34},"google/gemini-3.6-flash":{"draws":16,"losses":20,"wins":22},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":6},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":9},"gpt-5.4":{"draws":10,"losses":10,"wins":12},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":14},"gpt-5.5":{"draws":9,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":7,"wins":12},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":14},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":10,"losses":15,"wins":25},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":10},"o3":{"draws":10,"losses":11,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":12,"losses":4,"wins":16},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":14},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":4,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":9,"losses":3,"wins":4}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":4,"losses":5,"wins":11},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":1,"losses":4,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":6,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":5,"wins":2},"gpt-5.4":{"draws":1,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":10,"wins":5},"gpt-5.5":{"draws":2,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":4,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":6,"losses":12,"wins":10},"claude-opus-4-8":{"draws":7,"losses":11,"wins":8},"claude-opus-5":{"draws":7,"losses":14,"wins":3},"claude-sonnet-5":{"draws":3,"losses":3,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":4,"losses":14,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":6},"gpt-5.5":{"draws":3,"losses":9,"wins":6},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":5},"o3":{"draws":3,"losses":4,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":6}},"gpt-5.4":{"claude-fable-5":{"draws":3,"losses":12,"wins":5},"claude-opus-4-5":{"draws":9,"losses":8,"wins":15},"claude-opus-4-8":{"draws":7,"losses":9,"wins":10},"claude-opus-5":{"draws":6,"losses":24,"wins":6},"claude-sonnet-5":{"draws":5,"losses":2,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-4.1":{"draws":3,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":4,"wins":7},"gpt-5.4":{"draws":6,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":14},"gpt-5.5":{"draws":9,"losses":9,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":9},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":2,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":6},"o3":{"draws":3,"losses":3,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":15,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":9},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":5}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-opus-4-5":{"draws":11,"losses":16,"wins":13},"claude-opus-4-8":{"draws":8,"losses":8,"wins":12},"claude-opus-5":{"draws":6,"losses":25,"wins":5},"claude-sonnet-5":{"draws":5,"losses":3,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":9},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":7,"losses":2,"wins":5},"gpt-5":{"draws":3,"losses":4,"wins":9},"gpt-5.4":{"draws":10,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":8,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":14},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":5},"o3":{"draws":2,"losses":3,"wins":7},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":9},"xiaomi/mimo-v2.5":{"draws":17,"losses":7,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":10,"wins":5}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":27,"wins":5},"claude-opus-4-5":{"draws":14,"losses":17,"wins":21},"claude-opus-4-8":{"draws":6,"losses":20,"wins":8},"claude-opus-5":{"draws":3,"losses":22,"wins":11},"claude-sonnet-5":{"draws":5,"losses":11,"wins":8},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":10,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":8,"wins":9},"gpt-4.1":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":4,"losses":10,"wins":14},"gpt-5.4":{"draws":5,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":18},"gpt-5.4-nano":{"draws":2,"losses":13,"wins":21},"gpt-5.5":{"draws":7,"losses":17,"wins":10},"gpt-5.6-luna":{"draws":7,"losses":18,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":19},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":8,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":9},"o3":{"draws":3,"losses":11,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":11},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.5":{"draws":24,"losses":27,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"z-ai/glm-5.2":{"draws":5,"losses":10,"wins":13}},"gpt-5.5":{"claude-fable-5":{"draws":5,"losses":13,"wins":6},"claude-opus-4-5":{"draws":11,"losses":9,"wins":10},"claude-opus-4-8":{"draws":8,"losses":10,"wins":12},"claude-opus-5":{"draws":10,"losses":28,"wins":6},"claude-sonnet-5":{"draws":4,"losses":3,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":7,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":6,"wins":7},"gpt-5.4":{"draws":8,"losses":15,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":5,"losses":7,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":10,"losses":9,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":4,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":14,"wins":2},"claude-opus-4-5":{"draws":13,"losses":11,"wins":12},"claude-opus-4-8":{"draws":7,"losses":7,"wins":4},"claude-opus-5":{"draws":2,"losses":18,"wins":4},"claude-sonnet-5":{"draws":5,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":3},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":7,"losses":5,"wins":8},"gpt-5.4":{"draws":15,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":17},"gpt-5.5":{"draws":7,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":3,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":6},"o3":{"draws":4,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":13,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":6,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":12,"losses":13,"wins":3}},"gpt-5.6-sol":{"claude-fable-5":{"draws":3,"losses":19,"wins":6},"claude-opus-4-5":{"draws":8,"losses":2,"wins":18},"claude-opus-4-8":{"draws":3,"losses":8,"wins":17},"claude-opus-5":{"draws":8,"losses":36,"wins":10},"claude-sonnet-5":{"draws":4,"losses":3,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4":{"draws":3,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":21},"gpt-5.5":{"draws":6,"losses":13,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":8},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":17},"o3":{"draws":2,"losses":2,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":8},"z-ai/glm-5.2":{"draws":4,"losses":3,"wins":9}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":17,"losses":10,"wins":13},"claude-opus-4-8":{"draws":9,"losses":4,"wins":7},"claude-opus-5":{"draws":11,"losses":32,"wins":3},"claude-sonnet-5":{"draws":5,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":5,"losses":6,"wins":7},"gpt-5.4":{"draws":10,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":10},"gpt-5.5":{"draws":11,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":4,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":5,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":9,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":4,"losses":7,"wins":5},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":5,"wins":1},"claude-sonnet-5":{"draws":1,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":17,"losses":24,"wins":11},"google/gemini-3.6-flash":{"draws":20,"losses":26,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":2},"gpt-5.5":{"draws":1,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":14,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":2,"losses":22,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":7,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":20,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":12,"losses":18,"wins":9},"claude-opus-4-8":{"draws":4,"losses":4,"wins":2},"claude-opus-5":{"draws":3,"losses":17,"wins":4},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":18,"losses":27,"wins":38},"google/gemini-3.6-flash":{"draws":19,"losses":34,"wins":11},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":1,"losses":7,"wins":0},"gpt-5.4":{"draws":2,"losses":3,"wins":5},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":5},"gpt-5.5":{"draws":3,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":3},"o3":{"draws":5,"losses":41,"wins":12},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":14},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":14},"qwen/qwen3.7-max":{"draws":1,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":8,"losses":16,"wins":16},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"minimax/minimax-m3":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-8":{"draws":10,"losses":8,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":5,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":13,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":5,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":4},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":2},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":24,"wins":8},"gpt-5.5":{"draws":5,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":3},"o3":{"draws":4,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":17,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":1}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-sonnet-5":{"draws":5,"losses":6,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":7,"losses":11,"wins":6},"claude-opus-4-8":{"draws":2,"losses":2,"wins":4},"claude-opus-5":{"draws":3,"losses":18,"wins":1},"claude-sonnet-5":{"draws":4,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":18,"losses":12,"wins":26},"google/gemini-3.6-flash":{"draws":14,"losses":23,"wins":13},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":5,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":3},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":12},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":1},"o3":{"draws":3,"losses":16,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":1,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":10,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":0}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-8":{"draws":3,"losses":9,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":1,"losses":7,"wins":14},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":12},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":1,"losses":6,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":7,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":10,"wins":2},"gpt-5.4":{"draws":0,"losses":12,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":0,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":14,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":12,"wins":4},"o3":{"draws":0,"losses":8,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":16,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":0}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":8,"losses":4,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":0},"claude-opus-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":4,"wins":4},"gpt-5.4":{"draws":5,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":8},"gpt-5.5":{"draws":3,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":3,"losses":5,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":1}},"o3":{"claude-fable-5":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":7,"losses":16,"wins":9},"claude-opus-4-8":{"draws":4,"losses":7,"wins":3},"claude-opus-5":{"draws":2,"losses":19,"wins":3},"claude-sonnet-5":{"draws":3,"losses":8,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":15},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":4,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":12},"gpt-5.5":{"draws":7,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":8}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":3,"losses":9,"wins":0},"claude-opus-4-5":{"draws":13,"losses":14,"wins":3},"claude-opus-4-8":{"draws":7,"losses":6,"wins":3},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":5,"losses":7,"wins":0},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.6-flash":{"draws":9,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":2},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":4,"wins":1},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":5},"gpt-5.5":{"draws":10,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":9},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":6},"o3":{"draws":4,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":12,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":3,"wins":6}},"poolside/laguna-s-2.1":{"claude-opus-4-5":{"draws":15,"losses":14,"wins":1},"claude-opus-4-8":{"draws":8,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":25,"wins":3},"claude-sonnet-5":{"draws":8,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":45,"losses":23,"wins":28},"google/gemini-3.6-flash":{"draws":42,"losses":27,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":6,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":27,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":13,"losses":19,"wins":12},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":11},"poolside/laguna-s-2.1":{"draws":22,"losses":13,"wins":7},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":0},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":3},"thinkingmachines/inkling":{"draws":23,"losses":13,"wins":20},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":6},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":14,"losses":16,"wins":8},"claude-opus-4-8":{"draws":8,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":6},"claude-sonnet-5":{"draws":7,"losses":5,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":11,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":7,"wins":3},"gpt-5.4":{"draws":3,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":11},"gpt-5.5":{"draws":7,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":11,"losses":1,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":7},"o3":{"draws":7,"losses":2,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":8,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":6}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":12,"wins":1},"claude-opus-4-5":{"draws":7,"losses":11,"wins":8},"claude-opus-4-8":{"draws":6,"losses":11,"wins":3},"claude-opus-5":{"draws":4,"losses":18,"wins":0},"claude-sonnet-5":{"draws":6,"losses":3,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":6,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":8,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":3}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-5":{"draws":9,"losses":8,"wins":1},"claude-opus-4-8":{"draws":5,"losses":4,"wins":3},"claude-opus-5":{"draws":5,"losses":18,"wins":1},"claude-sonnet-5":{"draws":3,"losses":5,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":0},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":7,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":1},"o3":{"draws":2,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":1}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":3,"losses":8,"wins":1},"claude-opus-4-8":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":4,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":15,"losses":16,"wins":11},"google/gemini-3.6-flash":{"draws":21,"losses":14,"wins":7},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":5},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":9,"wins":9},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":5,"wins":1},"o3":{"draws":6,"losses":8,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":9,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":1}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":5,"losses":18,"wins":3},"claude-opus-4-5":{"draws":9,"losses":10,"wins":13},"claude-opus-4-8":{"draws":4,"losses":10,"wins":12},"claude-opus-5":{"draws":6,"losses":39,"wins":7},"claude-sonnet-5":{"draws":6,"losses":5,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":5,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4":{"draws":5,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":12},"gpt-5.5":{"draws":6,"losses":9,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":11,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":27},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":7},"o3":{"draws":2,"losses":5,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":5,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":4}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":25,"wins":12},"claude-opus-4-8":{"draws":18,"losses":19,"wins":5},"claude-opus-5":{"draws":2,"losses":17,"wins":1},"claude-sonnet-5":{"draws":19,"losses":18,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":17},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":9},"gpt-4.1":{"draws":3,"losses":3,"wins":4},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":19,"losses":20,"wins":5},"gpt-5.4-mini":{"draws":19,"losses":20,"wins":5},"gpt-5.4-nano":{"draws":19,"losses":28,"wins":25},"gpt-5.5":{"draws":20,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":16,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":18,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":19,"losses":11,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":17,"wins":9},"o3":{"draws":8,"losses":20,"wins":0},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":7},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":22},"x-ai/grok-4.5":{"draws":11,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":14,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":6,"losses":20,"wins":8}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":2,"losses":12,"wins":8},"claude-opus-4-8":{"draws":3,"losses":12,"wins":1},"claude-opus-5":{"draws":5,"losses":9,"wins":0},"claude-sonnet-5":{"draws":4,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":7},"gpt-4.1":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4":{"draws":2,"losses":16,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":13},"gpt-5.5":{"draws":1,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":6},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":17},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":4,"losses":12,"wins":16},"claude-opus-4-8":{"draws":12,"losses":10,"wins":4},"claude-opus-5":{"draws":1,"losses":17,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":7,"losses":6,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":5},"gpt-5.4":{"draws":14,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":4},"gpt-5.5":{"draws":10,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":4},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":4}}},"none":{"claude-opus-4-5":{"claude-fable-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-5":{"draws":13,"losses":4,"wins":9},"claude-opus-4-8":{"draws":3,"losses":12,"wins":9},"claude-opus-5":{"draws":10,"losses":38,"wins":6},"claude-sonnet-5":{"draws":3,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":5,"losses":5,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":7,"losses":8,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":14,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":8},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":11,"wins":15}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":6,"wins":2},"claude-opus-4-5":{"draws":8,"losses":6,"wins":14},"claude-opus-4-8":{"draws":4,"losses":1,"wins":3},"claude-opus-5":{"draws":4,"losses":19,"wins":7},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":12},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":14},"gpt-5.5":{"draws":5,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":6},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":11,"losses":7,"wins":4}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":17,"wins":15},"claude-opus-4-5":{"draws":17,"losses":15,"wins":44},"claude-opus-4-8":{"draws":11,"losses":10,"wins":25},"claude-opus-5":{"draws":19,"losses":62,"wins":37},"claude-sonnet-5":{"draws":6,"losses":3,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":20},"deepseek/deepseek-v4-pro":{"draws":5,"losses":0,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":16},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":31},"google/gemini-3.6-flash":{"draws":7,"losses":14,"wins":29},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":16},"gpt-4.1":{"draws":7,"losses":1,"wins":15},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":1,"wins":18},"gpt-5.4":{"draws":19,"losses":21,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":32},"gpt-5.5":{"draws":14,"losses":10,"wins":36},"gpt-5.6-luna":{"draws":9,"losses":7,"wins":30},"gpt-5.6-sol":{"draws":16,"losses":8,"wins":46},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":36},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":25},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":7,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":12},"o3":{"draws":2,"losses":3,"wins":13},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":22},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"thinkingmachines/inkling":{"draws":2,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":6,"wins":31},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":18},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":26}},"claude-sonnet-5":{"claude-opus-4-5":{"draws":4,"losses":0,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":0},"o3":{"draws":2,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":5,"losses":11,"wins":0},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":2},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":14,"wins":6},"gpt-5.5":{"draws":7,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":8,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":16,"wins":0},"claude-opus-4-8":{"draws":3,"losses":11,"wins":2},"claude-opus-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":3,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":8,"wins":3},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":5},"google/gemini-3.5-flash":{"draws":9,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":5},"gpt-4.1":{"draws":5,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":4},"gpt-5.5":{"draws":10,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":4},"o3":{"draws":3,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":13,"losses":13,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":9,"losses":5,"wins":2}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":10,"losses":7,"wins":9},"claude-opus-4-8":{"draws":6,"losses":10,"wins":6},"claude-opus-5":{"draws":3,"losses":23,"wins":2},"claude-sonnet-5":{"draws":5,"losses":3,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":9,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":3},"gpt-5.4":{"draws":8,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":12},"gpt-5.5":{"draws":7,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":12},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":1},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":8}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":16,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":7},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":10,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":21,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":12,"wins":1}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":19,"losses":10,"wins":11},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":40,"wins":6},"claude-sonnet-5":{"draws":4,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":35,"losses":32,"wins":21},"google/gemini-3.6-flash":{"draws":39,"losses":36,"wins":23},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":11,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":9},"gpt-5.5":{"draws":11,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":5,"losses":2,"wins":5},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":37,"losses":3,"wins":22},"meituan/longcat-2.0":{"draws":17,"losses":18,"wins":34},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":28,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":1},"o3":{"draws":8,"losses":15,"wins":15},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":30,"losses":22,"wins":18},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":26,"losses":23,"wins":29},"x-ai/grok-4.5":{"draws":13,"losses":35,"wins":18},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"google/gemini-3.6-flash":{"claude-opus-4-5":{"draws":14,"losses":14,"wins":12},"claude-opus-4-8":{"draws":7,"losses":2,"wins":3},"claude-opus-5":{"draws":3,"losses":37,"wins":8},"claude-sonnet-5":{"draws":5,"losses":3,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-pro":{"draws":9,"losses":0,"wins":5},"google/gemini-3.5-flash-lite":{"draws":57,"losses":30,"wins":29},"google/gemini-3.6-flash":{"draws":29,"losses":29,"wins":18},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5.4":{"draws":11,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":5},"gpt-5.5":{"draws":12,"losses":4,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":5,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":47,"losses":16,"wins":23},"meituan/longcat-2.0":{"draws":22,"losses":19,"wins":25},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":23,"losses":25,"wins":6},"nex-agi/nex-n2-pro":{"draws":12,"losses":3,"wins":7},"o3":{"draws":13,"losses":32,"wins":13},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":42,"losses":21,"wins":23},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":40,"losses":14,"wins":34},"x-ai/grok-4.5":{"draws":16,"losses":31,"wins":19},"xiaomi/mimo-v2.5":{"draws":2,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":1}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":7,"losses":8,"wins":3},"claude-opus-4-8":{"draws":6,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":12,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":3,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":5},"o3":{"draws":4,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":22,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":3}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"claude-sonnet-5":{"draws":6,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5.4":{"claude-fable-5":{"draws":1,"losses":7,"wins":4},"claude-opus-4-5":{"draws":8,"losses":10,"wins":6},"claude-opus-4-8":{"draws":3,"losses":6,"wins":7},"claude-opus-5":{"draws":10,"losses":20,"wins":8},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":5,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":15,"losses":3,"wins":6},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":7},"gpt-4.1":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":2,"losses":0,"wins":6},"gpt-5.4":{"draws":4,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":9,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":10,"losses":2,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":17},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":10},"inclusionai/ling-3.0-flash":{"draws":12,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":4},"o3":{"draws":2,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":8},"z-ai/glm-5.2":{"draws":18,"losses":1,"wins":3}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":14,"losses":11,"wins":5},"claude-opus-4-8":{"draws":10,"losses":9,"wins":3},"claude-opus-5":{"draws":4,"losses":7,"wins":1},"claude-sonnet-5":{"draws":8,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":11,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":8,"wins":3},"gpt-4.1":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":12,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":3},"gpt-5.5":{"draws":9,"losses":4,"wins":3},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":8,"wins":1},"gpt-5.6-terra":{"draws":11,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":4},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":7,"wins":2}},"gpt-5.4-nano":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":10,"losses":16,"wins":12},"claude-opus-4-8":{"draws":7,"losses":16,"wins":9},"claude-opus-5":{"draws":11,"losses":32,"wins":1},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":19,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":8},"google/gemini-3.6-flash":{"draws":16,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":8,"losses":16,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":9},"gpt-5.5":{"draws":9,"losses":11,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":18,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":14},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":12,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":3,"losses":2,"wins":7},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":31,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":4}},"gpt-5.5":{"claude-opus-4-5":{"draws":14,"losses":10,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":4},"claude-opus-5":{"draws":10,"losses":28,"wins":0},"claude-sonnet-5":{"draws":2,"losses":1,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":8},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":15,"losses":4,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":11,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":10,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":2,"wins":9},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":22,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":1},"o3":{"draws":7,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":19,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":7}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":17,"losses":9,"wins":0},"claude-opus-4-8":{"draws":7,"losses":9,"wins":2},"claude-opus-5":{"draws":4,"losses":5,"wins":1},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":15,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":4},"google/gemini-3.5-flash-lite":{"draws":13,"losses":2,"wins":1},"google/gemini-3.6-flash":{"draws":15,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":1},"gpt-4.1":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":3,"losses":3,"wins":0},"gpt-5.4":{"draws":8,"losses":15,"wins":1},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":17,"wins":6},"gpt-5.5":{"draws":8,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":13,"wins":0},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":1},"o3":{"draws":2,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":10,"wins":4},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":31,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":7,"wins":3}},"gpt-5.6-sol":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":14,"losses":8,"wins":14},"claude-opus-4-8":{"draws":9,"losses":8,"wins":7},"claude-opus-5":{"draws":7,"losses":38,"wins":1},"claude-sonnet-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":5,"wins":4},"google/gemini-3.6-flash":{"draws":7,"losses":6,"wins":5},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":8},"gpt-4.1":{"draws":3,"losses":2,"wins":5},"gpt-5":{"draws":3,"losses":3,"wins":2},"gpt-5.4":{"draws":7,"losses":10,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":13},"gpt-5.5":{"draws":8,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":13},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":7},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":4},"o3":{"draws":1,"losses":2,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":6}},"gpt-5.6-terra":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":14,"losses":11,"wins":7},"claude-opus-4-8":{"draws":12,"losses":7,"wins":5},"claude-opus-5":{"draws":14,"losses":23,"wins":5},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":15,"losses":5,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":1},"google/gemini-3.6-flash":{"draws":11,"losses":6,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":12,"losses":15,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":7},"gpt-5.5":{"draws":12,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":15},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":6},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":4,"wins":11},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":14,"losses":6,"wins":2},"claude-opus-4-8":{"draws":14,"losses":4,"wins":0},"claude-opus-5":{"draws":8,"losses":17,"wins":1},"claude-sonnet-5":{"draws":8,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":16,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":9},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":33,"losses":15,"wins":4},"google/gemini-3.6-flash":{"draws":47,"losses":20,"wins":9},"google/gemma-4-31b-it":{"draws":12,"losses":17,"wins":3},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":8},"gpt-5.4":{"draws":16,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":18,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":14,"wins":7},"gpt-5.5":{"draws":26,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":26,"losses":3,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":11},"meituan/longcat-2.0":{"draws":35,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":5,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":39,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":17,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":16},"x-ai/grok-4.5":{"draws":10,"losses":24,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":2,"wins":4}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":16,"losses":12,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":7,"losses":31,"wins":6},"claude-sonnet-5":{"draws":7,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":18,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":19,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":17},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":25,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":7,"losses":9,"wins":6},"gpt-5.4":{"draws":11,"losses":8,"wins":5},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":16,"losses":22,"wins":16},"gpt-5.5":{"draws":13,"losses":4,"wins":9},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":7},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":9},"inclusionai/ling-3.0-flash":{"draws":33,"losses":19,"wins":24},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":6},"o3":{"draws":7,"losses":4,"wins":13},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":12},"qwen/qwen3.7-max":{"draws":17,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":11,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":17},"x-ai/grok-4.5":{"draws":14,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":17,"wins":9}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":15,"wins":5},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":3,"losses":29,"wins":4},"claude-sonnet-5":{"draws":1,"losses":3,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":8},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4":{"draws":4,"losses":9,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":10},"gpt-5.5":{"draws":4,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":9,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":1,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":9,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":5}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-8":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":1,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":3},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":5}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":12,"losses":6,"wins":14},"claude-opus-4-8":{"draws":4,"losses":3,"wins":7},"claude-opus-5":{"draws":6,"losses":23,"wins":9},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":7},"google/gemini-3.5-flash-lite":{"draws":16,"losses":11,"wins":19},"google/gemini-3.6-flash":{"draws":19,"losses":23,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":8},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":4,"losses":5,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":16},"gpt-5.5":{"draws":5,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":15,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"o3":{"draws":3,"losses":10,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":13},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":7},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":21},"x-ai/grok-4.5":{"draws":14,"losses":13,"wins":17},"xiaomi/mimo-v2.5":{"draws":8,"losses":8,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":0}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":7,"losses":9,"wins":6},"claude-opus-4-8":{"draws":11,"losses":12,"wins":3},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":9,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":12,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":15,"losses":8,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":10,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":8},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":5},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":2,"losses":7,"wins":3},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-sonnet-5":{"draws":3,"losses":2,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":14,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4":{"draws":7,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":3},"gpt-5.5":{"draws":12,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":12,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":5}},"o3":{"claude-opus-4-5":{"draws":3,"losses":4,"wins":3},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":18,"wins":5},"google/gemini-3.6-flash":{"draws":10,"losses":12,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":0},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":1},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":5,"losses":10,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"o3":{"draws":3,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":5,"losses":26,"wins":1},"claude-opus-4-8":{"draws":0,"losses":9,"wins":3},"claude-opus-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":5,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":28,"wins":8},"google/gemini-3.6-flash":{"draws":5,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":3,"losses":10,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":6},"gpt-5.5":{"draws":6,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":8,"wins":1},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"o3":{"draws":6,"losses":19,"wins":3},"poolside/laguna-s-2.1":{"draws":3,"losses":8,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":17,"wins":6},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":13,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":4,"wins":6},"claude-opus-4-5":{"draws":14,"losses":10,"wins":4},"claude-opus-4-8":{"draws":4,"losses":18,"wins":4},"claude-opus-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":6,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":17,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":23,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":4},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":15,"losses":15,"wins":16},"google/gemini-3.6-flash":{"draws":21,"losses":22,"wins":17},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":8},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":4,"wins":9},"gpt-5.4":{"draws":6,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":16,"losses":10,"wins":14},"gpt-5.5":{"draws":13,"losses":9,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":13},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":21},"meituan/longcat-2.0":{"draws":19,"losses":7,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":14,"losses":10,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":9},"o3":{"draws":7,"losses":7,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":12,"wins":21},"x-ai/grok-4.5":{"draws":9,"losses":34,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":20,"losses":11,"wins":13}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-8":{"draws":4,"losses":9,"wins":5},"claude-opus-5":{"draws":7,"losses":30,"wins":1},"claude-sonnet-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":12,"losses":8,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":9},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":6,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":11},"gpt-5.5":{"draws":10,"losses":4,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":3},"o3":{"draws":3,"losses":4,"wins":1},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":8},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":11,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":3}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":16,"losses":7,"wins":3},"claude-opus-4-8":{"draws":6,"losses":9,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":10,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":9,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":6,"wins":6},"o3":{"draws":1,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":12,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":23,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":2,"losses":13,"wins":5},"claude-opus-4-8":{"draws":0,"losses":7,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":14},"google/gemini-3.6-flash":{"draws":1,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":2,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":4},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":7,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":0},"o3":{"draws":2,"losses":15,"wins":7},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":3,"wins":4},"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-opus-4-8":{"draws":8,"losses":7,"wins":3},"claude-opus-5":{"draws":8,"losses":13,"wins":5},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":11,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":10},"gpt-5.5":{"draws":12,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":5,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":3}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":20,"losses":22,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":6,"losses":29,"wins":7},"claude-sonnet-5":{"draws":9,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":17,"wins":10},"google/gemini-3.6-flash":{"draws":25,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":6,"wins":0},"gpt-5.4":{"draws":13,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":12},"gpt-5.5":{"draws":11,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":11},"o3":{"draws":5,"losses":5,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":14,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":33,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":9,"losses":14,"wins":9}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":13,"losses":12,"wins":11},"claude-opus-4-8":{"draws":5,"losses":2,"wins":5},"claude-opus-5":{"draws":5,"losses":16,"wins":5},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash-lite":{"draws":20,"losses":8,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":22,"wins":12},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":11},"gpt-5.5":{"draws":5,"losses":0,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":11},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":14,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"o3":{"draws":3,"losses":11,"wins":10},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":5}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":19,"losses":25,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":2},"claude-sonnet-5":{"draws":6,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":14},"deepseek/deepseek-v4-flash":{"draws":19,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":11,"losses":20,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":15,"wins":17},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":5},"gpt-5.4":{"draws":12,"losses":25,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":30},"gpt-5.5":{"draws":16,"losses":15,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":25},"gpt-5.6-sol":{"draws":8,"losses":24,"wins":10},"gpt-5.6-terra":{"draws":19,"losses":17,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":12},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":16,"wins":17},"poolside/laguna-s-2.1":{"draws":6,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":9,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":21,"wins":14}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":5,"losses":9,"wins":10},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":3,"losses":26,"wins":1},"claude-sonnet-5":{"draws":2,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":8,"losses":7,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":10,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":11},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":7}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":31,"wins":20},"claude-opus-4-8":{"draws":11,"losses":15,"wins":12},"claude-opus-5":{"draws":12,"losses":43,"wins":9},"claude-sonnet-5":{"draws":8,"losses":12,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":10,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":11,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-5":{"draws":9,"losses":13,"wins":12},"gpt-5.4":{"draws":18,"losses":10,"wins":10},"gpt-5.4-mini":{"draws":18,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":15},"gpt-5.5":{"draws":12,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":19,"wins":11},"gpt-5.6-terra":{"draws":27,"losses":11,"wins":18},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":6},"z-ai/glm-5.2":{"draws":16,"losses":13,"wins":17}}}}}