{"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":"2026-07-27T12:08:50Z","heatmap_track_id":"full_freedom/intensive","models":[{"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-2026-07-25":11},"run_count":8,"token_priced_attempt_count":11,"total":12.660970000000002},"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-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0372}},"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-2026-07-25":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":82.05398116503684,"medium":82.13181183227302},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:46:35Z","match_totals_all":{"draws":80,"losses":101,"wins":327},"match_totals_tracks":{"highest":{"draws":39,"losses":50,"wins":191},"medium":{"draws":41,"losses":51,"wins":136}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":83.46508123439294,"min":51.25235536890574},"per_game":{"GB2-01":65.10607118012358,"GB2-02":64.12910881005666,"GB2-03":77.21712923444468,"GB2-04":100.0,"GB2-05":96.80004942946064,"GB2-06":86.63777139507742,"GB2-07":66.54171927113187,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":23,"wins":43},"GB2-02":{"draws":34,"losses":3,"wins":29},"GB2-03":{"draws":12,"losses":3,"wins":7},"GB2-04":{"draws":22,"losses":7,"wins":37},"GB2-05":{"draws":0,"losses":22,"wins":52},"GB2-06":{"draws":12,"losses":13,"wins":41},"GB2-07":{"draws":0,"losses":26,"wins":48},"GB2-08":{"draws":0,"losses":4,"wins":70}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":12,"wins":20},"GB2-02":{"draws":15,"losses":2,"wins":19},"GB2-03":{"draws":12,"losses":3,"wins":7},"GB2-04":{"draws":7,"losses":0,"wins":27},"GB2-05":{"draws":0,"losses":6,"wins":36},"GB2-06":{"draws":5,"losses":8,"wins":23},"GB2-07":{"draws":0,"losses":18,"wins":20},"GB2-08":{"draws":0,"losses":1,"wins":39}},"medium":{"GB2-01":{"draws":0,"losses":11,"wins":23},"GB2-02":{"draws":19,"losses":1,"wins":10},"GB2-04":{"draws":15,"losses":7,"wins":10},"GB2-05":{"draws":0,"losses":16,"wins":16},"GB2-06":{"draws":7,"losses":5,"wins":18},"GB2-07":{"draws":0,"losses":8,"wins":28},"GB2-08":{"draws":0,"losses":3,"wins":31}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1572.4733522869028,"GB2-02":1627.5900380283315,"GB2-03":1536.5271386172433,"GB2-04":1744.0680990562232,"GB2-05":1766.9249024534338,"GB2-06":1656.7301631786654,"GB2-07":1563.5727006176976,"GB2-08":1855.2871085339511},"medium":{"GB2-01":1627.4198381444287,"GB2-02":1598.1409013976136,"GB2-04":1574.371070117924,"GB2-05":1542.3063477043722,"GB2-06":1665.360654264961,"GB2-07":1685.2833742990706,"GB2-08":1762.12477009952}},"per_game_tracks":{"highest":{"GB2-01":65.10607118012358,"GB2-02":64.12910881005666,"GB2-03":77.21712923444468,"GB2-04":100.0,"GB2-05":96.80004942946064,"GB2-06":86.63777139507742,"GB2-07":66.54171927113187,"GB2-08":100.0},"medium":{"GB2-01":66.74457030567973,"GB2-02":86.09676158777394,"GB2-04":96.09094184721906,"GB2-05":51.25235536890574,"GB2-06":80.2809467186497,"GB2-07":94.45710699768296,"GB2-08":100.0}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":87.49488502391748,"medium":79.43527744486839},"reasoning_agg":{"highest":{"max":100.0,"mean":87.49488502391748,"min":66.54171927113187},"medium":{"max":100.0,"mean":79.43527744486839,"min":51.25235536890574}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":8.059607579049086},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":80.20987916527109,"reliability_score":59.42366365028197,"uncertainty_avg":40.57633634971803,"uncertainty_penalty":-7.285005858646386},"medium":{"ceiling_score":100.0,"expected_score":86.65858047863408,"reliability_score":57.33381391702074,"uncertainty_avg":42.66618608297926,"uncertainty_penalty":7.2233030337656885}}},{"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-2026-07-25":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":0.366615,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":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":0.121464375,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485}},"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-2026-07-25":27},"run_count":26,"token_priced_attempt_count":27,"total":85.66335500000001},"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":13803.555555555557,"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":67.45607375733147,"highest":69.63452833335168,"medium":66.59301849909089,"none":66.14067443955182},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:44Z","match_totals_all":{"draws":175,"losses":256,"wins":445},"match_totals_tracks":{"highest":{"draws":31,"losses":89,"wins":180},"medium":{"draws":61,"losses":73,"wins":128},"none":{"draws":83,"losses":94,"wins":137}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":67.45607375733145,"min":20.492149149769027},"per_game":{"GB2-01":71.86605925428235,"GB2-02":100.0,"GB2-03":80.1148367650945,"GB2-04":71.3122819774477,"GB2-05":80.30789756064816,"GB2-06":74.44633576629161,"GB2-07":58.5366661932801,"GB2-08":20.492149149769027},"per_game_all":{"GB2-01":67.69407867812004,"GB2-02":87.70972772874785,"GB2-03":75.14825947586047,"GB2-04":67.40398978683892,"GB2-05":66.7859182633925,"GB2-06":67.09922548541212,"GB2-07":62.99710961992566,"GB2-08":44.81028102035413},"per_game_match_totals_all":{"GB2-01":{"draws":9,"losses":34,"wins":63},"GB2-02":{"draws":50,"losses":7,"wins":45},"GB2-03":{"draws":19,"losses":25,"wins":38},"GB2-04":{"draws":70,"losses":6,"wins":26},"GB2-05":{"draws":0,"losses":36,"wins":80},"GB2-06":{"draws":8,"losses":56,"wins":64},"GB2-07":{"draws":0,"losses":55,"wins":75},"GB2-08":{"draws":19,"losses":37,"wins":54}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":11,"wins":23},"GB2-02":{"draws":4,"losses":3,"wins":29},"GB2-03":{"draws":2,"losses":8,"wins":16},"GB2-04":{"draws":14,"losses":2,"wins":20},"GB2-05":{"draws":0,"losses":10,"wins":30},"GB2-06":{"draws":2,"losses":15,"wins":19},"GB2-07":{"draws":0,"losses":22,"wins":32},"GB2-08":{"draws":9,"losses":18,"wins":11}},"medium":{"GB2-01":{"draws":0,"losses":17,"wins":15},"GB2-02":{"draws":16,"losses":2,"wins":12},"GB2-03":{"draws":5,"losses":5,"wins":12},"GB2-04":{"draws":30,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":14,"wins":24},"GB2-06":{"draws":5,"losses":6,"wins":19},"GB2-07":{"draws":0,"losses":18,"wins":20},"GB2-08":{"draws":5,"losses":8,"wins":23}},"none":{"GB2-01":{"draws":9,"losses":6,"wins":25},"GB2-02":{"draws":30,"losses":2,"wins":4},"GB2-03":{"draws":12,"losses":12,"wins":10},"GB2-04":{"draws":26,"losses":1,"wins":3},"GB2-05":{"draws":0,"losses":12,"wins":26},"GB2-06":{"draws":1,"losses":35,"wins":26},"GB2-07":{"draws":0,"losses":15,"wins":23},"GB2-08":{"draws":5,"losses":11,"wins":20}}},"per_game_raw_elo_all":{"GB2-01":1608.4187265629255,"GB2-02":1611.1355056793952,"GB2-03":1534.7963752384683,"GB2-04":1552.8467846120127,"GB2-05":1610.818116264959,"GB2-06":1577.5721149648855,"GB2-07":1549.5452538743732,"GB2-08":1529.2687400232837},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1605.509798264124,"GB2-02":1737.6584206742875,"GB2-03":1536.37884380157,"GB2-04":1639.7206482409697,"GB2-05":1667.1776298896546,"GB2-06":1590.2040403195467,"GB2-07":1503.443205499448,"GB2-08":1383.6520822330217},"medium":{"GB2-01":1525.6788902740416,"GB2-02":1578.7609133825872,"GB2-03":1572.4320080310492,"GB2-04":1498.922163263296,"GB2-05":1561.4870941390402,"GB2-06":1665.1856924018116,"GB2-07":1537.7297375035548,"GB2-08":1623.7505160206958},"none":{"GB2-01":1694.0674911506117,"GB2-02":1516.987182981311,"GB2-03":1495.5782738827854,"GB2-04":1519.8975423317725,"GB2-05":1603.7896247661818,"GB2-06":1477.3266121732986,"GB2-07":1607.4628186201166,"GB2-08":1580.4036218161336}},"per_game_tracks":{"highest":{"GB2-01":71.86605925428235,"GB2-02":100.0,"GB2-03":80.1148367650945,"GB2-04":71.3122819774477,"GB2-05":80.30789756064816,"GB2-06":74.44633576629161,"GB2-07":58.5366661932801,"GB2-08":20.492149149769027},"medium":{"GB2-01":50.39329262049877,"GB2-02":75.19558306360466,"GB2-03":84.82062838505718,"GB2-04":52.69406067196953,"GB2-05":55.82088096897083,"GB2-06":80.24079290785865,"GB2-07":65.13085976351364,"GB2-08":68.44804961125392},"none":{"GB2-01":80.82288415957899,"GB2-02":87.93360012263891,"GB2-03":60.509313277429726,"GB2-04":78.20562671109955,"GB2-05":64.22897626055851,"GB2-06":46.610547782086115,"GB2-07":65.32380290298325,"GB2-08":45.49064430003946}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":69.63452833335168,"medium":66.59301849909089,"none":66.14067443955182},"reasoning_agg":{"highest":{"max":100.0,"mean":69.63452833335168,"min":20.492149149769027},"medium":{"max":84.82062838505718,"mean":66.59301849909089,"min":50.39329262049877},"none":{"max":87.93360012263891,"mean":66.14067443955182,"min":45.49064430003946}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":64.37068412436538,"reasoning_variance":3.4938538937998658,"reliability_score":60.905643712147516,"uncertainty_avg":39.094356287852484,"uncertainty_penalty":-3.08538963296607},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":64.34734971820517,"reliability_score":62.1362630763755,"uncertainty_avg":37.8637369236245,"uncertainty_penalty":-5.287178615146516},"medium":{"ceiling_score":84.82062838505718,"expected_score":66.79269826232027,"reliability_score":56.82144023204929,"uncertainty_avg":43.17855976795071,"uncertainty_penalty":0.1996797632293834},"none":{"ceiling_score":87.93360012263891,"expected_score":61.97200439257074,"reliability_score":63.75922782801778,"uncertainty_avg":36.24077217198222,"uncertainty_penalty":-4.168670046981077}}},{"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-2026-07-25":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-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":3.989149999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.1598575,"mean":0.093565,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":8,"token_priced_attempt_count":10,"total":0.74852}},"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":1.078263125,"median":0.5065824999999999,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":28},"run_count":24,"token_priced_attempt_count":28,"total":25.878314999999997},"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":63.55415000427999,"highest":63.94527562797671,"medium":54.20640932807544,"none":72.51076505678779},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:53:35Z","match_totals_all":{"draws":268,"losses":193,"wins":423},"match_totals_tracks":{"highest":{"draws":54,"losses":64,"wins":176},"medium":{"draws":94,"losses":79,"wins":107},"none":{"draws":120,"losses":50,"wins":140}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":63.55415000427998,"min":6.510092243905561},"per_game":{"GB2-01":100.0,"GB2-02":36.870613069615246,"GB2-03":6.510092243905561,"GB2-04":28.518989543740652,"GB2-05":100.0,"GB2-06":100.0,"GB2-07":100.0,"GB2-08":39.66251016655223},"per_game_all":{"GB2-01":87.0043459828933,"GB2-02":43.325472858089974,"GB2-03":40.85856941821964,"GB2-04":61.60283909098692,"GB2-05":81.45375285632726,"GB2-06":96.8646229795678,"GB2-07":68.00399095310341,"GB2-08":29.319605895051538},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":10,"wins":81},"GB2-02":{"draws":92,"losses":8,"wins":12},"GB2-03":{"draws":32,"losses":23,"wins":17},"GB2-04":{"draws":70,"losses":18,"wins":28},"GB2-05":{"draws":0,"losses":29,"wins":95},"GB2-06":{"draws":10,"losses":14,"wins":78},"GB2-07":{"draws":0,"losses":43,"wins":77},"GB2-08":{"draws":49,"losses":48,"wins":35}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":32},"GB2-02":{"draws":21,"losses":4,"wins":11},"GB2-03":{"draws":2,"losses":12,"wins":4},"GB2-04":{"draws":20,"losses":11,"wins":15},"GB2-05":{"draws":0,"losses":4,"wins":36},"GB2-06":{"draws":4,"losses":6,"wins":26},"GB2-07":{"draws":0,"losses":4,"wins":36},"GB2-08":{"draws":7,"losses":21,"wins":16}},"medium":{"GB2-01":{"draws":13,"losses":6,"wins":13},"GB2-02":{"draws":34,"losses":3,"wins":1},"GB2-03":{"draws":12,"losses":8,"wins":4},"GB2-04":{"draws":21,"losses":4,"wins":9},"GB2-05":{"draws":0,"losses":18,"wins":22},"GB2-06":{"draws":4,"losses":3,"wins":25},"GB2-07":{"draws":0,"losses":19,"wins":21},"GB2-08":{"draws":10,"losses":18,"wins":12}},"none":{"GB2-01":{"draws":2,"losses":2,"wins":36},"GB2-02":{"draws":37,"losses":1,"wins":0},"GB2-03":{"draws":18,"losses":3,"wins":9},"GB2-04":{"draws":29,"losses":3,"wins":4},"GB2-05":{"draws":0,"losses":7,"wins":37},"GB2-06":{"draws":2,"losses":5,"wins":27},"GB2-07":{"draws":0,"losses":20,"wins":20},"GB2-08":{"draws":32,"losses":9,"wins":7}}},"per_game_raw_elo_all":{"GB2-01":1714.9330826791122,"GB2-02":1504.6611517861027,"GB2-03":1474.5955510866115,"GB2-04":1511.9393021441447,"GB2-05":1697.4920449755973,"GB2-06":1728.7486073579191,"GB2-07":1593.5317324966236,"GB2-08":1471.34415151564},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.4035495541411,"GB2-02":1543.9484434098736,"GB2-03":1391.7118135414669,"GB2-04":1479.416328673052,"GB2-05":1788.0340484254982,"GB2-06":1729.645059250773,"GB2-07":1771.0326433486096,"GB2-08":1493.3279265182478},"medium":{"GB2-01":1593.0681971292947,"GB2-02":1473.9971278996284,"GB2-03":1457.387709238609,"GB2-04":1543.219343682438,"GB2-05":1510.7986639936207,"GB2-06":1749.0712613941848,"GB2-07":1528.9830586828025,"GB2-08":1462.3769280323002},"none":{"GB2-01":1800.327501353901,"GB2-02":1496.0378840488054,"GB2-03":1574.6871304797592,"GB2-04":1513.1822340769445,"GB2-05":1793.6434225076723,"GB2-06":1707.5295014287992,"GB2-07":1480.5794954584585,"GB2-08":1458.3275999963723}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-02":36.870613069615246,"GB2-03":6.510092243905561,"GB2-04":28.518989543740652,"GB2-05":100.0,"GB2-06":100.0,"GB2-07":100.0,"GB2-08":39.66251016655223},"medium":{"GB2-01":61.01303794867986,"GB2-02":20.64863599452821,"GB2-03":31.198505930588695,"GB2-04":78.42781304173958,"GB2-05":46.76029390709667,"GB2-06":100.0,"GB2-07":63.6901532705237,"GB2-08":31.912834531446784},"none":{"GB2-01":100.0,"GB2-02":72.45716951012649,"GB2-03":84.86711008016466,"GB2-04":77.86171468748051,"GB2-05":97.60096466188511,"GB2-06":90.59386893870337,"GB2-07":40.32181958878655,"GB2-08":16.383472987155603}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.94527562797671,"medium":54.20640932807544,"none":72.51076505678779},"reasoning_agg":{"highest":{"max":100.0,"mean":63.94527562797671,"min":6.510092243905561},"medium":{"max":100.0,"mean":54.20640932807544,"min":20.64863599452821},"none":{"max":100.0,"mean":72.51076505678779,"min":16.383472987155603}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":59.12999761866468,"reasoning_variance":18.304355728712352,"reliability_score":61.29577010943041,"uncertainty_avg":38.70422989056959,"uncertainty_penalty":-4.424152385615301},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":59.72245694690028,"reliability_score":60.34198292487048,"uncertainty_avg":39.65801707512952,"uncertainty_penalty":-4.222818681076433},"medium":{"ceiling_score":100.0,"expected_score":51.55893672841378,"reliability_score":59.63527485449972,"uncertainty_avg":40.36472514550028,"uncertainty_penalty":-2.6474725996616613},"none":{"ceiling_score":100.0,"expected_score":66.10859918067997,"reliability_score":63.910052548921016,"uncertainty_avg":36.089947451078984,"uncertainty_penalty":-6.402165876107816}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":20,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.14454373333333334,"mean":0.08818255,"median":0.07401653333333333,"min":0.052337466666666665,"recorded_attempt_count":37,"run_count":24,"total":2.1163811999999997},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12366493333333332,"mean":0.09185773333333332,"median":0.09170913333333332,"min":0.04980146666666666,"recorded_attempt_count":39,"run_count":24,"total":2.2045855999999997},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","max":0.116343,"mean":0.07787519999999999,"median":0.0843883,"min":0.041110400000000005,"recorded_attempt_count":28,"run_count":16,"total":1.2460032}},"codegen_cost_usd":{"admitted_cell_count":59,"cell_count":24,"cost_basis_counts":{"provider_reported":104},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.14454373333333334,"mean":0.08597182777777779,"median":0.08538879999999999,"min":0.041110400000000005,"recorded_attempt_count":104,"run_count":64,"total":5.56697},"codegen_latency_ms":{"attempt_count":104,"max_ms":194096,"mean_ms":104338.484375,"min_ms":45373,"run_count":64},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":37,"max_ms":194096,"mean_ms":109560.20833333331,"min_ms":52667,"run_count":24},"medium":{"attempt_count":39,"max_ms":151974,"mean_ms":106852.375,"min_ms":48934,"run_count":24},"none":{"attempt_count":28,"max_ms":139814,"mean_ms":92735.0625,"min_ms":45373,"run_count":16}},"codegen_output_tokens":{"attempt_count":104,"output_max":26179,"output_mean":9948.484375,"output_min":3846,"run_count":64},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":37,"output_max":26179,"output_mean":10515.25,"output_min":4776,"run_count":24},"medium":{"attempt_count":39,"output_max":19479,"output_mean":10751.083333333334,"output_min":5204,"run_count":24},"none":{"attempt_count":28,"output_max":14459,"output_mean":7894.4375,"output_min":3846,"run_count":16}},"display_name":"Grok 4.5","economics":{"all":63.36052754464899,"highest":52.50038311884343,"medium":68.22939959940362,"none":69.3517999156999},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":23,"evaluated_cells":24,"failed_game_aliases":["GB2-02"],"first_pass_admitted":10,"first_pass_rate":0.4166666666666667,"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":0.041666666666666664,"model_code_failures":1,"repaired_admitted":13,"repaired_rate":0.5416666666666666},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":11,"repaired_rate":0.6875},"intensive":{"admitted_plugins":20,"evaluated_cells":24,"failed_game_aliases":["GB2-02","GB2-03","GB2-05"],"first_pass_admitted":12,"first_pass_rate":0.5,"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":0.16666666666666666,"model_code_failures":4,"repaired_admitted":8,"repaired_rate":0.3333333333333333}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:53:35Z","match_totals_all":{"draws":501,"losses":609,"wins":1008},"match_totals_tracks":{"highest":{"draws":110,"losses":263,"wins":343},"medium":{"draws":198,"losses":217,"wins":409},"none":{"draws":193,"losses":129,"wins":256}},"model_slug":"x-ai-grok-4-5","overall":{"max":89.62057504440759,"mean":63.36052754464898,"min":15.003544455041151},"per_game":{"GB2-01":73.29749735278367,"GB2-02":24.210064903221465,"GB2-03":54.831529095952085,"GB2-04":15.003544455041151,"GB2-05":54.97905976692074,"GB2-06":61.63139425390002,"GB2-07":63.34872710882669,"GB2-08":72.7012480141017},"per_game_all":{"GB2-01":65.43581517424722,"GB2-02":54.05574262842305,"GB2-03":47.42342566962483,"GB2-04":55.71373914771971,"GB2-05":67.24970943568704,"GB2-06":59.36889519907904,"GB2-07":78.66837922170522,"GB2-08":78.9685138807058},"per_game_match_totals_all":{"GB2-01":{"draws":63,"losses":77,"wins":140},"GB2-02":{"draws":153,"losses":21,"wins":34},"GB2-03":{"draws":81,"losses":49,"wins":32},"GB2-04":{"draws":179,"losses":50,"wins":37},"GB2-05":{"draws":0,"losses":106,"wins":180},"GB2-06":{"draws":24,"losses":137,"wins":157},"GB2-07":{"draws":0,"losses":106,"wins":200},"GB2-08":{"draws":1,"losses":63,"wins":228}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":16,"losses":28,"wins":54},"GB2-02":{"draws":39,"losses":13,"wins":14},"GB2-03":{"draws":9,"losses":5,"wins":4},"GB2-04":{"draws":40,"losses":27,"wins":11},"GB2-05":{"draws":0,"losses":43,"wins":43},"GB2-06":{"draws":6,"losses":65,"wins":67},"GB2-07":{"draws":0,"losses":55,"wins":63},"GB2-08":{"draws":0,"losses":27,"wins":87}},"medium":{"GB2-01":{"draws":12,"losses":36,"wins":58},"GB2-02":{"draws":45,"losses":5,"wins":18},"GB2-03":{"draws":41,"losses":16,"wins":19},"GB2-04":{"draws":85,"losses":16,"wins":17},"GB2-05":{"draws":0,"losses":42,"wins":82},"GB2-06":{"draws":15,"losses":41,"wins":56},"GB2-07":{"draws":0,"losses":39,"wins":75},"GB2-08":{"draws":0,"losses":22,"wins":84}},"none":{"GB2-01":{"draws":35,"losses":13,"wins":28},"GB2-02":{"draws":69,"losses":3,"wins":2},"GB2-03":{"draws":31,"losses":28,"wins":9},"GB2-04":{"draws":54,"losses":7,"wins":9},"GB2-05":{"draws":0,"losses":21,"wins":55},"GB2-06":{"draws":3,"losses":31,"wins":34},"GB2-07":{"draws":0,"losses":12,"wins":62},"GB2-08":{"draws":1,"losses":14,"wins":57}}},"per_game_raw_elo_all":{"GB2-01":1598.4275301313994,"GB2-02":1521.5786020513408,"GB2-03":1470.6894246205004,"GB2-04":1500.109789103335,"GB2-05":1607.5941085413945,"GB2-06":1542.1270994574388,"GB2-07":1633.2836192368607,"GB2-08":1700.7371014593657},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1614.278599845149,"GB2-02":1507.962168524286,"GB2-03":1496.3927282437023,"GB2-04":1451.082546475501,"GB2-05":1509.8544076462035,"GB2-06":1513.0400252752788,"GB2-07":1542.6061458845336,"GB2-08":1694.3914815154003},"medium":{"GB2-01":1588.6690474216646,"GB2-02":1564.670534690998,"GB2-03":1502.8902128840152,"GB2-04":1518.8061196284582,"GB2-05":1632.8909452237556,"GB2-06":1560.8160138205174,"GB2-07":1627.1604423106364,"GB2-08":1695.695559200463},"none":{"GB2-01":1592.3349431273846,"GB2-02":1492.1031029387386,"GB2-03":1412.7853327337837,"GB2-04":1530.4407012060465,"GB2-05":1680.0369727542245,"GB2-06":1552.5252592765198,"GB2-07":1730.084269515412,"GB2-08":1712.1242636622335}},"per_game_tracks":{"highest":{"GB2-01":73.29749735278367,"GB2-02":24.210064903221465,"GB2-03":54.831529095952085,"GB2-04":15.003544455041151,"GB2-05":54.97905976692074,"GB2-06":61.63139425390002,"GB2-07":63.34872710882669,"GB2-08":72.7012480141017},"medium":{"GB2-01":60.83255808793939,"GB2-02":69.46095827835052,"GB2-03":53.97033563854308,"GB2-04":66.27912634393984,"GB2-05":69.4436534916628,"GB2-06":57.89107272340044,"GB2-07":83.03583551188142,"GB2-08":84.92165671951146},"none":{"GB2-01":62.17739008201862,"GB2-02":68.49620470369716,"GB2-03":33.46841227437931,"GB2-04":85.85854664417812,"GB2-05":77.32641504847757,"GB2-06":58.584218619936664,"GB2-07":89.62057504440759,"GB2-08":79.28263690850423}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.50038311884343,"medium":68.22939959940362,"none":69.3517999156999},"reasoning_agg":{"highest":{"max":73.29749735278367,"mean":52.50038311884343,"min":15.003544455041151},"medium":{"max":84.92165671951146,"mean":68.22939959940362,"min":53.97033563854308},"none":{"max":89.62057504440759,"mean":69.3517999156999,"min":33.46841227437931}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":89.62057504440759,"expected_score":60.67299857642796,"reasoning_variance":16.85141679685647,"reliability_score":59.66048765676397,"uncertainty_avg":40.33951234323603,"uncertainty_penalty":-2.6875289682210237},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.29749735278367,"expected_score":49.01938732446115,"reliability_score":57.21057326801569,"uncertainty_avg":42.78942673198431,"uncertainty_penalty":-3.480995794382281},"medium":{"ceiling_score":84.92165671951146,"expected_score":67.99998240022076,"reliability_score":60.46960188130581,"uncertainty_avg":39.53039811869419,"uncertainty_penalty":-0.22941719918286196},"none":{"ceiling_score":89.62057504440759,"expected_score":64.99962600460195,"reliability_score":61.30128782097041,"uncertainty_avg":38.69871217902959,"uncertainty_penalty":-4.35217391109795}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":18,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.9392418,"mean":0.7382814249999998,"median":0.7264120999999999,"min":0.4980382,"recorded_attempt_count":48,"run_count":23,"total":16.779512399999998},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.3926418,"mean":0.31750829999999997,"median":0.32150055,"min":0.2298153,"recorded_attempt_count":32,"run_count":16,"total":5.080132799999999},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.0820533,"mean":0.0699502125,"median":0.06609614999999999,"min":0.0587988,"recorded_attempt_count":17,"run_count":16,"total":1.1192034}},"codegen_cost_usd":{"admitted_cell_count":49,"cell_count":24,"cost_basis_counts":{"provider_reported":97},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.9392418,"mean":0.3752466458333333,"median":0.32150055,"min":0.0587988,"recorded_attempt_count":97,"run_count":55,"total":22.9788486},"codegen_latency_ms":{"attempt_count":97,"max_ms":2434665,"mean_ms":734905.7636363637,"min_ms":64944,"run_count":55},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":48,"max_ms":2434665,"mean_ms":1301919.2608695652,"min_ms":865404,"run_count":23},"medium":{"attempt_count":32,"max_ms":962148,"mean_ms":564713.375,"min_ms":119309,"run_count":16},"none":{"attempt_count":17,"max_ms":115016,"mean_ms":90016.25,"min_ms":64944,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":81171,"output_mean":25811.70909090909,"output_min":2237,"run_count":55},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":48,"output_max":81171,"output_mean":46501.95652173913,"output_min":28508,"run_count":23},"medium":{"attempt_count":32,"output_max":30004,"output_mean":18825.75,"output_min":4345,"run_count":16},"none":{"attempt_count":17,"output_max":4534,"output_mean":3055.4375,"output_min":2237,"run_count":16}},"display_name":"Kimi K3","economics":{"all":55.38549505233441,"highest":47.58893978381631,"medium":54.28440132761132,"none":70.61495470364622},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-05"],"first_pass_admitted":1,"first_pass_rate":0.0625,"model_code_failure_rate":0.0625,"model_code_failures":1,"repaired_admitted":14,"repaired_rate":0.875},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":15,"first_pass_rate":0.9375,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.0625},"intensive":{"admitted_plugins":18,"evaluated_cells":23,"failed_game_aliases":["GB2-03","GB2-05","GB2-06"],"infra_excluded_game_aliases":["GB2-02","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.21739130434782608,"model_code_failures":5,"repaired_admitted":18,"repaired_rate":0.782608695652174}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":569,"losses":513,"wins":703},"match_totals_tracks":{"highest":{"draws":200,"losses":248,"wins":277},"medium":{"draws":198,"losses":124,"wins":168},"none":{"draws":171,"losses":141,"wins":258}},"model_slug":"moonshotai-kimi-k3","overall":{"max":92.34979339934728,"mean":57.98729584074465,"min":27.533937664020943},"per_game":{"GB2-01":55.50931776256605,"GB2-02":16.467348481477572,"GB2-04":43.8212919129843,"GB2-05":54.296051128861706,"GB2-06":78.32108125131899,"GB2-07":59.424757600443634,"GB2-08":25.282730349061865},"per_game_all":{"GB2-01":55.870877738542134,"GB2-02":44.22217633411345,"GB2-04":55.07790273401138,"GB2-05":58.738912304126224,"GB2-06":73.26575039784579,"GB2-07":58.610251025055966,"GB2-08":41.91259483264593},"per_game_match_totals_all":{"GB2-01":{"draws":81,"losses":81,"wins":102},"GB2-02":{"draws":201,"losses":25,"wins":16},"GB2-03":{"draws":34,"losses":16,"wins":48},"GB2-04":{"draws":118,"losses":49,"wins":63},"GB2-05":{"draws":0,"losses":90,"wins":119},"GB2-06":{"draws":16,"losses":61,"wins":133},"GB2-07":{"draws":0,"losses":130,"wins":154},"GB2-08":{"draws":119,"losses":61,"wins":68}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":51,"wins":55},"GB2-02":{"draws":80,"losses":17,"wins":9},"GB2-04":{"draws":34,"losses":24,"wins":36},"GB2-05":{"draws":0,"losses":47,"wins":50},"GB2-06":{"draws":6,"losses":21,"wins":45},"GB2-07":{"draws":0,"losses":63,"wins":77},"GB2-08":{"draws":58,"losses":25,"wins":5}},"medium":{"GB2-01":{"draws":30,"losses":12,"wins":18},"GB2-02":{"draws":52,"losses":7,"wins":3},"GB2-03":{"draws":11,"losses":9,"wins":18},"GB2-04":{"draws":47,"losses":14,"wins":15},"GB2-05":{"draws":0,"losses":18,"wins":18},"GB2-06":{"draws":8,"losses":15,"wins":39},"GB2-07":{"draws":0,"losses":29,"wins":39},"GB2-08":{"draws":50,"losses":20,"wins":18}},"none":{"GB2-01":{"draws":29,"losses":18,"wins":29},"GB2-02":{"draws":69,"losses":1,"wins":4},"GB2-03":{"draws":23,"losses":7,"wins":30},"GB2-04":{"draws":37,"losses":11,"wins":12},"GB2-05":{"draws":0,"losses":25,"wins":51},"GB2-06":{"draws":2,"losses":25,"wins":49},"GB2-07":{"draws":0,"losses":38,"wins":38},"GB2-08":{"draws":11,"losses":16,"wins":45}}},"per_game_raw_elo_all":{"GB2-01":1544.4810023383277,"GB2-02":1497.5095777876447,"GB2-04":1515.5723840790563,"GB2-05":1560.3240623904267,"GB2-06":1614.437812713156,"GB2-07":1530.5145463100027,"GB2-08":1513.6827297658147},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1513.6815272547765,"GB2-02":1482.1532233038204,"GB2-04":1546.1100671958757,"GB2-05":1502.026020706588,"GB2-06":1611.3477187208096,"GB2-07":1513.1524120542344,"GB2-08":1408.1447522119745},"medium":{"GB2-01":1544.6574862294765,"GB2-02":1492.923066963177,"GB2-03":1562.00482090384,"GB2-04":1490.5606753787383,"GB2-05":1548.7600602936016,"GB2-06":1611.7283788155676,"GB2-07":1554.493132293216,"GB2-08":1490.5012117576744},"none":{"GB2-01":1575.10399353073,"GB2-02":1517.4524430959366,"GB2-03":1597.6898847399202,"GB2-04":1510.046409662555,"GB2-05":1630.1861061710906,"GB2-06":1620.2373406030915,"GB2-07":1523.8980945825583,"GB2-08":1642.4022253277956}},"per_game_tracks":{"highest":{"GB2-01":55.50931776256605,"GB2-02":16.467348481477572,"GB2-04":43.8212919129843,"GB2-05":54.296051128861706,"GB2-06":78.32108125131899,"GB2-07":59.424757600443634,"GB2-08":25.282730349061865},"medium":{"GB2-01":53.03565513507361,"GB2-02":27.533937664020943,"GB2-03":76.87223723840454,"GB2-04":48.621930226537806,"GB2-05":53.15743641654883,"GB2-06":68.22603948442678,"GB2-07":67.76886481085508,"GB2-08":39.059109645022986},"none":{"GB2-01":59.067660317986736,"GB2-02":88.66524285684184,"GB2-03":92.34979339934728,"GB2-04":72.79048606251203,"GB2-05":68.76324936696814,"GB2-06":73.25013045779164,"GB2-07":48.63713066386918,"GB2-08":61.39594450385294}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.772944020743815,"medium":53.57398879784393,"none":70.61495470364622},"reasoning_agg":{"highest":{"max":59.424757600443634,"mean":49.772944020743815,"min":43.8212919129843},"medium":{"max":76.87223723840454,"mean":53.57398879784393,"min":27.533937664020943},"none":{"max":92.34979339934728,"mean":70.61495470364622,"min":48.63713066386918}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"score_diagnostics":{"ceiling_score":92.34979339934728,"expected_score":51.71761626150685,"reasoning_variance":20.842010682902405,"reliability_score":62.29155982485376,"uncertainty_avg":37.70844017514624,"uncertainty_penalty":-6.269679579237803},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.424757600443634,"expected_score":42.83366817083904,"reliability_score":65.46573053310107,"uncertainty_avg":34.53426946689893,"uncertainty_penalty":-6.939275849904774},"medium":{"ceiling_score":76.87223723840454,"expected_score":52.86372397520098,"reliability_score":56.23684146808494,"uncertainty_avg":43.76315853191506,"uncertainty_penalty":-0.710264822642948},"none":{"ceiling_score":92.34979339934728,"expected_score":67.19037892163186,"reliability_score":60.71960672568948,"uncertainty_avg":39.28039327431052,"uncertainty_penalty":-3.424575782014358}}},{"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-2026-07-25":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":0.442856875,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"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-2026-07-25":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":58.55080079448652,"highest":65.84083340449097,"medium":52.22017032287155,"none":56.023761200399285},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-5.5","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:52:58Z","match_totals_all":{"draws":283,"losses":191,"wins":297},"match_totals_tracks":{"highest":{"draws":52,"losses":59,"wins":132},"medium":{"draws":81,"losses":77,"wins":94},"none":{"draws":150,"losses":55,"wins":71}},"model_slug":"gpt-5-5","overall":{"max":89.5488782879756,"mean":56.69457738852287,"min":13.03869548876527},"per_game":{"GB2-01":79.37438294325402,"GB2-03":56.8304765462084,"GB2-04":19.11061437892723,"GB2-05":82.07253898580366,"GB2-06":69.07396378501579,"GB2-07":89.5488782879756,"GB2-08":64.87497890425209},"per_game_all":{"GB2-01":61.18263348574789,"GB2-03":62.524226040781194,"GB2-04":42.72260491769827,"GB2-05":73.62534069737468,"GB2-07":73.02596928450458,"GB2-08":38.2240303408125},"per_game_match_totals_all":{"GB2-01":{"draws":63,"losses":15,"wins":34},"GB2-02":{"draws":59,"losses":7,"wins":8},"GB2-03":{"draws":32,"losses":16,"wins":19},"GB2-04":{"draws":67,"losses":21,"wins":14},"GB2-05":{"draws":0,"losses":37,"wins":79},"GB2-06":{"draws":6,"losses":33,"wins":31},"GB2-07":{"draws":0,"losses":38,"wins":78},"GB2-08":{"draws":56,"losses":24,"wins":34}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":7,"wins":18},"GB2-03":{"draws":10,"losses":4,"wins":3},"GB2-04":{"draws":20,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":12,"wins":28},"GB2-06":{"draws":6,"losses":14,"wins":18},"GB2-07":{"draws":0,"losses":6,"wins":34},"GB2-08":{"draws":7,"losses":9,"wins":26}},"medium":{"GB2-01":{"draws":16,"losses":3,"wins":11},"GB2-02":{"draws":16,"losses":6,"wins":8},"GB2-03":{"draws":10,"losses":5,"wins":5},"GB2-04":{"draws":24,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":13,"wins":25},"GB2-06":{"draws":0,"losses":19,"wins":13},"GB2-07":{"draws":0,"losses":14,"wins":20},"GB2-08":{"draws":15,"losses":10,"wins":7}},"none":{"GB2-01":{"draws":38,"losses":5,"wins":5},"GB2-02":{"draws":43,"losses":1,"wins":0},"GB2-03":{"draws":12,"losses":7,"wins":11},"GB2-04":{"draws":23,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":12,"wins":26},"GB2-07":{"draws":0,"losses":18,"wins":24},"GB2-08":{"draws":34,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1572.2938040428792,"GB2-03":1520.465547056365,"GB2-04":1477.42240877767,"GB2-05":1649.274383968412,"GB2-07":1615.4369245134067,"GB2-08":1528.6267215796997},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1644.4455989322375,"GB2-03":1503.2377491470545,"GB2-04":1457.0874053731973,"GB2-05":1678.0077707190103,"GB2-06":1559.1797929160575,"GB2-07":1705.7357961483333,"GB2-08":1644.7590670645436},"medium":{"GB2-01":1572.42847353646,"GB2-02":1531.6142012340692,"GB2-03":1519.9053207634795,"GB2-04":1492.1799267831789,"GB2-05":1624.0373796112651,"GB2-06":1415.3289968740492,"GB2-07":1604.3676330595297,"GB2-08":1490.5047387756592},"none":{"GB2-01":1500.0073396599396,"GB2-02":1495.700687820907,"GB2-03":1538.2535712585614,"GB2-04":1482.999894176634,"GB2-05":1645.7780015749606,"GB2-07":1536.2073443323568,"GB2-08":1450.6163588988966}},"per_game_tracks":{"highest":{"GB2-01":79.37438294325402,"GB2-03":56.8304765462084,"GB2-04":19.11061437892723,"GB2-05":82.07253898580366,"GB2-06":69.07396378501579,"GB2-07":89.5488782879756,"GB2-08":64.87497890425209},"medium":{"GB2-01":57.41202916939602,"GB2-02":48.67571496254503,"GB2-03":57.726749899984654,"GB2-04":48.606291706521056,"GB2-05":67.36192556171113,"GB2-06":23.40602974118218,"GB2-07":77.81420491221216,"GB2-08":36.75841662942015},"none":{"GB2-01":46.76148834459363,"GB2-02":75.74340202770378,"GB2-03":73.0154516761505,"GB2-04":60.45090866764652,"GB2-05":71.44155754460928,"GB2-07":51.714824653325984,"GB2-08":13.03869548876527}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.67916099754152,"medium":52.220170322871546,"none":54.18440084515555},"reasoning_agg":{"highest":{"max":89.5488782879756,"mean":63.67916099754152,"min":19.11061437892723},"medium":{"max":77.81420491221216,"mean":52.220170322871546,"min":23.40602974118218},"none":{"max":75.74340202770378,"mean":54.18440084515555,"min":13.03869548876527}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":89.5488782879756,"expected_score":55.50285566574078,"reasoning_variance":11.458990674669977,"reliability_score":58.48862545729818,"uncertainty_avg":41.51137454270182,"uncertainty_penalty":-1.1917217227820913},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.5488782879756,"expected_score":61.805942470945006,"reliability_score":57.7653560562985,"uncertainty_avg":42.2346439437015,"uncertainty_penalty":-1.873218526596517},"medium":{"ceiling_score":77.81420491221216,"expected_score":52.20643892966436,"reliability_score":55.053637608932135,"uncertainty_avg":44.946362391067865,"uncertainty_penalty":-0.013731393207187637},"none":{"ceiling_score":75.74340202770378,"expected_score":46.247943355654506,"reliability_score":64.5096442602925,"uncertainty_avg":35.490355739707496,"uncertainty_penalty":-7.936457489501045}}},{"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":0.4890770625000001,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.9126165},"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":2.790024}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.41891503125,"median":0.4031475,"min":0.254883,"recorded_attempt_count":37,"run_count":16,"total":6.702640499999999},"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":51.861197300859224,"medium":62.872826461559235},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-3.5-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:53:34Z","match_totals_all":{"draws":137,"losses":133,"wins":186},"match_totals_tracks":{"highest":{"draws":51,"losses":79,"wins":70},"medium":{"draws":86,"losses":54,"wins":116}},"model_slug":"google-gemini-3-5-flash","overall":{"max":100.0,"mean":55.56755433429576,"min":18.74472465795587},"per_game":{"GB2-03":71.6494706887085,"GB2-04":24.391172674552745,"GB2-05":50.4482489217218,"GB2-06":77.49112703166377,"GB2-07":68.44243983055263,"GB2-08":18.74472465795587},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":0,"wins":34},"GB2-02":{"draws":24,"losses":0,"wins":4},"GB2-03":{"draws":18,"losses":6,"wins":16},"GB2-04":{"draws":27,"losses":21,"wins":16},"GB2-05":{"draws":0,"losses":38,"wins":40},"GB2-06":{"draws":12,"losses":16,"wins":40},"GB2-07":{"draws":0,"losses":36,"wins":36},"GB2-08":{"draws":56,"losses":16,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":13,"losses":1,"wins":4},"GB2-04":{"draws":7,"losses":16,"wins":9},"GB2-05":{"draws":0,"losses":18,"wins":20},"GB2-06":{"draws":6,"losses":11,"wins":19},"GB2-07":{"draws":0,"losses":20,"wins":18},"GB2-08":{"draws":25,"losses":13,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":0,"wins":34},"GB2-02":{"draws":24,"losses":0,"wins":4},"GB2-03":{"draws":5,"losses":5,"wins":12},"GB2-04":{"draws":20,"losses":5,"wins":7},"GB2-05":{"draws":0,"losses":20,"wins":20},"GB2-06":{"draws":6,"losses":5,"wins":21},"GB2-07":{"draws":0,"losses":16,"wins":18},"GB2-08":{"draws":31,"losses":3,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1532.8261959555375,"GB2-04":1475.9536416564838,"GB2-05":1485.5016464350815,"GB2-06":1606.8188315523569,"GB2-07":1575.4480823574515,"GB2-08":1373.2517181453684},"medium":{"GB2-01":1838.4475310898383,"GB2-02":1538.4702659640886,"GB2-03":1562.162104844842,"GB2-04":1507.8544822327308,"GB2-05":1525.869550605163,"GB2-06":1695.234146268621,"GB2-07":1497.8972900669266,"GB2-08":1427.1362847514313}},"per_game_tracks":{"highest":{"GB2-03":71.6494706887085,"GB2-04":24.391172674552745,"GB2-05":50.4482489217218,"GB2-06":77.49112703166377,"GB2-07":68.44243983055263,"GB2-08":18.74472465795587},"medium":{"GB2-01":100.0,"GB2-02":51.1619784752323,"GB2-03":79.8877974832961,"GB2-04":55.76241815237855,"GB2-05":49.54099703455366,"GB2-06":87.64436263211375,"GB2-07":56.40538660256344,"GB2-08":22.57967131233604}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.262282207032285,"medium":62.87282646155923},"reasoning_agg":{"highest":{"max":77.49112703166377,"mean":48.262282207032285,"min":18.74472465795587},"medium":{"max":100.0,"mean":62.87282646155923,"min":22.57967131233604}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":14.610544254526943},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.49112703166377,"expected_score":45.65726614369576,"reliability_score":56.393596787760146,"uncertainty_avg":43.606403212239854,"uncertainty_penalty":-2.605016063336528},"medium":{"ceiling_score":100.0,"expected_score":63.99278388646701,"reliability_score":55.89803882054759,"uncertainty_avg":44.10196117945241,"uncertainty_penalty":1.1199574249077813}}},{"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":12.13752,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":11},"run_count":8,"token_priced_attempt_count":11,"total":65.3280125},"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":0.158095,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":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-2026-07-25":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063375}},"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":12.13752,"mean":2.8005991666666663,"median":0.158095,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":32},"run_count":25,"token_priced_attempt_count":32,"total":67.27387},"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":51.9614054920852,"highest":54.20040986507351,"medium":42.818484898804904,"none":58.865321712377195},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:44Z","match_totals_all":{"draws":321,"losses":268,"wins":305},"match_totals_tracks":{"highest":{"draws":52,"losses":107,"wins":137},"medium":{"draws":118,"losses":73,"wins":75},"none":{"draws":151,"losses":88,"wins":93}},"model_slug":"gpt-5-6-terra","overall":{"max":83.15246772729438,"mean":51.9614054920852,"min":15.58654015337014},"per_game":{"GB2-01":37.45010615839138,"GB2-02":15.600779261238808,"GB2-03":78.37602417367826,"GB2-04":39.83837333300842,"GB2-05":74.29245202837116,"GB2-06":71.35148531923815,"GB2-07":77.40512914785191,"GB2-08":39.28892949880998},"per_game_all":{"GB2-01":47.88278444899498,"GB2-02":39.72575245516226,"GB2-03":64.97076251970037,"GB2-04":64.27371074741399,"GB2-05":61.494236459158024,"GB2-06":52.762018481738046,"GB2-07":55.90862672345293,"GB2-08":28.673352101061003},"per_game_match_totals_all":{"GB2-01":{"draws":33,"losses":39,"wins":32},"GB2-02":{"draws":99,"losses":7,"wins":6},"GB2-03":{"draws":30,"losses":22,"wins":22},"GB2-04":{"draws":88,"losses":12,"wins":18},"GB2-05":{"draws":0,"losses":46,"wins":70},"GB2-06":{"draws":6,"losses":56,"wins":74},"GB2-07":{"draws":0,"losses":51,"wins":59},"GB2-08":{"draws":65,"losses":35,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":7,"losses":16,"wins":9},"GB2-02":{"draws":27,"losses":6,"wins":5},"GB2-03":{"draws":4,"losses":5,"wins":9},"GB2-04":{"draws":9,"losses":11,"wins":12},"GB2-05":{"draws":0,"losses":13,"wins":25},"GB2-06":{"draws":0,"losses":21,"wins":37},"GB2-07":{"draws":0,"losses":14,"wins":24},"GB2-08":{"draws":5,"losses":21,"wins":16}},"medium":{"GB2-01":{"draws":12,"losses":12,"wins":10},"GB2-02":{"draws":31,"losses":1,"wins":0},"GB2-03":{"draws":13,"losses":6,"wins":3},"GB2-04":{"draws":31,"losses":1,"wins":4},"GB2-05":{"draws":0,"losses":19,"wins":21},"GB2-06":{"draws":6,"losses":10,"wins":18},"GB2-07":{"draws":0,"losses":17,"wins":15},"GB2-08":{"draws":25,"losses":7,"wins":4}},"none":{"GB2-01":{"draws":14,"losses":11,"wins":13},"GB2-02":{"draws":41,"losses":0,"wins":1},"GB2-03":{"draws":13,"losses":11,"wins":10},"GB2-04":{"draws":48,"losses":0,"wins":2},"GB2-05":{"draws":0,"losses":14,"wins":24},"GB2-06":{"draws":0,"losses":25,"wins":19},"GB2-07":{"draws":0,"losses":20,"wins":20},"GB2-08":{"draws":35,"losses":7,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1501.6661388941618,"GB2-02":1488.516109544809,"GB2-03":1524.2449609176608,"GB2-04":1523.8325625593843,"GB2-05":1580.204597002409,"GB2-06":1510.7849747185037,"GB2-07":1526.815900915212,"GB2-08":1470.4141994812835},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1429.0582324843149,"GB2-02":1476.9744829574713,"GB2-03":1547.3982330776153,"GB2-04":1531.1429836204177,"GB2-05":1631.8407688922227,"GB2-06":1559.6320560375812,"GB2-07":1631.4454547908722,"GB2-08":1492.4753886406684},"medium":{"GB2-01":1486.2383524960562,"GB2-02":1489.5319497576706,"GB2-03":1476.2394657722348,"GB2-04":1527.186118357768,"GB2-05":1526.4991852727485,"GB2-06":1494.785846302627,"GB2-07":1420.5629574849504,"GB2-08":1462.3429016755483},"none":{"GB2-01":1589.7018317021136,"GB2-02":1499.041895919285,"GB2-03":1549.0971839031326,"GB2-04":1513.1685856999677,"GB2-05":1582.2738368422554,"GB2-06":1477.9370218153024,"GB2-07":1528.4392904698134,"GB2-08":1456.4243081276331}},"per_game_tracks":{"highest":{"GB2-01":37.45010615839138,"GB2-02":15.600779261238808,"GB2-03":78.37602417367826,"GB2-04":39.83837333300842,"GB2-05":74.29245202837116,"GB2-06":71.35148531923815,"GB2-07":77.40512914785191,"GB2-08":39.28892949880998},"medium":{"GB2-01":44.49606393863294,"GB2-02":26.248302053387786,"GB2-03":38.61751075386925,"GB2-04":69.83029118193915,"GB2-05":49.657169834100074,"GB2-06":42.10470281484796,"GB2-07":40.44925196265917,"GB2-08":31.14458665100289},"none":{"GB2-01":61.702183249960626,"GB2-02":77.32817605086018,"GB2-03":77.91875263155363,"GB2-04":83.15246772729438,"GB2-05":60.53308751500282,"GB2-06":44.82986731112803,"GB2-07":49.871499059847736,"GB2-08":15.58654015337014}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.20040986507351,"medium":42.8184848988049,"none":58.865321712377195},"reasoning_agg":{"highest":{"max":78.37602417367826,"mean":54.20040986507351,"min":15.600779261238808},"medium":{"max":69.83029118193915,"mean":42.8184848988049,"min":26.248302053387786},"none":{"max":83.15246772729438,"mean":58.865321712377195,"min":15.58654015337014}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":83.15246772729438,"expected_score":46.72874402408446,"reasoning_variance":16.0468368135723,"reliability_score":61.390211624008025,"uncertainty_avg":38.609788375991975,"uncertainty_penalty":-5.232661468000735},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.37602417367826,"expected_score":49.341118480649655,"reliability_score":59.95981321808454,"uncertainty_avg":40.04018678191546,"uncertainty_penalty":-4.859291384423855},"medium":{"ceiling_score":69.83029118193915,"expected_score":40.283232597539325,"reliability_score":57.51855222755013,"uncertainty_avg":42.48144777244987,"uncertainty_penalty":-2.5352523012655723},"none":{"ceiling_score":83.15246772729438,"expected_score":50.561880994064424,"reliability_score":66.69226942638939,"uncertainty_avg":33.30773057361061,"uncertainty_penalty":-8.303440718312771}}},{"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-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":7.44989},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":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-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825}},"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":0.203055,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":25},"run_count":24,"token_priced_attempt_count":25,"total":10.45624},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":57.667189040788834,"highest":63.90970952070681,"medium":43.073303252286614,"none":62.84032169813988},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:54:26Z","match_totals_all":{"draws":178,"losses":224,"wins":356},"match_totals_tracks":{"highest":{"draws":35,"losses":82,"wins":153},"medium":{"draws":85,"losses":71,"wins":86},"none":{"draws":58,"losses":71,"wins":117}},"model_slug":"claude-opus-4-8","overall":{"max":83.86927193530403,"mean":50.34085505447382,"min":15.302591868876998},"per_game":{"GB2-01":58.16403882324354,"GB2-02":82.34591745744908,"GB2-04":41.58717179249483,"GB2-05":48.77341909695622,"GB2-06":86.00594867914448,"GB2-07":73.80891927170455,"GB2-08":56.68255152395502},"per_game_all":{"GB2-01":55.34523094656137,"GB2-02":56.75261171111526,"GB2-04":41.5470577988966,"GB2-05":46.02166215973583,"GB2-06":67.83007095864828,"GB2-07":78.88354561572255,"GB2-08":57.2901440948419},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":40,"wins":48},"GB2-02":{"draws":60,"losses":8,"wins":26},"GB2-03":{"draws":9,"losses":7,"wins":4},"GB2-04":{"draws":60,"losses":15,"wins":21},"GB2-05":{"draws":0,"losses":55,"wins":57},"GB2-06":{"draws":4,"losses":39,"wins":61},"GB2-07":{"draws":0,"losses":36,"wins":76},"GB2-08":{"draws":27,"losses":24,"wins":63}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":15,"wins":19},"GB2-02":{"draws":11,"losses":2,"wins":23},"GB2-04":{"draws":21,"losses":8,"wins":17},"GB2-05":{"draws":0,"losses":21,"wins":17},"GB2-06":{"draws":1,"losses":11,"wins":24},"GB2-07":{"draws":0,"losses":13,"wins":25},"GB2-08":{"draws":0,"losses":12,"wins":28}},"medium":{"GB2-01":{"draws":5,"losses":15,"wins":12},"GB2-02":{"draws":22,"losses":3,"wins":1},"GB2-03":{"draws":9,"losses":7,"wins":4},"GB2-04":{"draws":21,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":16,"wins":18},"GB2-06":{"draws":1,"losses":11,"wins":22},"GB2-07":{"draws":0,"losses":11,"wins":23},"GB2-08":{"draws":27,"losses":4,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":10,"wins":17},"GB2-02":{"draws":27,"losses":3,"wins":2},"GB2-04":{"draws":18,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":18,"wins":22},"GB2-06":{"draws":2,"losses":17,"wins":15},"GB2-07":{"draws":0,"losses":12,"wins":28},"GB2-08":{"draws":0,"losses":8,"wins":32}}},"per_game_raw_elo_all":{"GB2-01":1540.072438929027,"GB2-02":1554.2387333629638,"GB2-04":1493.5400415353536,"GB2-05":1489.6929215636026,"GB2-06":1589.569376784911,"GB2-07":1639.2470413286985,"GB2-08":1596.8999978527884},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1532.6026925601775,"GB2-02":1683.4875805279585,"GB2-04":1526.10597781532,"GB2-05":1475.2227066976116,"GB2-06":1653.2824383244988,"GB2-07":1608.976941529492,"GB2-08":1597.4692528213088},"medium":{"GB2-01":1491.2805766319743,"GB2-02":1477.4217673860342,"GB2-03":1443.07915798124,"GB2-04":1475.8864065756195,"GB2-05":1488.6778580177793,"GB2-06":1613.483830603291,"GB2-07":1634.4806945777934,"GB2-08":1480.7805344503954},"none":{"GB2-01":1596.334047594929,"GB2-02":1501.806852174898,"GB2-04":1478.627740215121,"GB2-05":1505.1781999754169,"GB2-06":1501.9418614269432,"GB2-07":1674.28348787881,"GB2-08":1712.4502062866611}},"per_game_tracks":{"highest":{"GB2-01":58.16403882324354,"GB2-02":82.34591745744908,"GB2-04":41.58717179249483,"GB2-05":48.77341909695622,"GB2-06":86.00594867914448,"GB2-07":73.80891927170455,"GB2-08":56.68255152395502},"medium":{"GB2-01":44.972531558476135,"GB2-02":15.302591868876998,"GB2-03":20.82567469365443,"GB2-04":33.56291976165975,"GB2-05":41.7299267221127,"GB2-06":69.34593308689266,"GB2-07":83.86927193530403,"GB2-08":34.97757639131614},"none":{"GB2-01":62.89912245796443,"GB2-02":72.60932580701969,"GB2-04":49.49108184253522,"GB2-05":47.561640660138586,"GB2-06":48.13833110990768,"GB2-07":78.97244564015908,"GB2-08":80.21030436925452}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.172100450110534,"medium":43.07330325228661,"none":60.77716146102433},"reasoning_agg":{"highest":{"max":48.77341909695622,"mean":47.172100450110534,"min":48.77341909695622},"medium":{"max":83.86927193530403,"mean":43.07330325228661,"min":15.302591868876998},"none":{"max":80.21030436925452,"mean":60.77716146102433,"min":47.561640660138586}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":83.86927193530403,"expected_score":54.67704769482217,"reasoning_variance":17.70385820873772,"reliability_score":59.84259830981985,"uncertainty_avg":40.15740169018015,"uncertainty_penalty":4.336192640348351},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.77341909695622,"expected_score":60.42116234962906,"reliability_score":64.07199836337523,"uncertainty_avg":35.92800163662477,"uncertainty_penalty":13.249061899518523},"medium":{"ceiling_score":83.86927193530403,"expected_score":40.47392018646306,"reliability_score":53.339726382410575,"uncertainty_avg":46.660273617589425,"uncertainty_penalty":-2.5993830658235453},"none":{"ceiling_score":80.21030436925452,"expected_score":58.47428075455131,"reliability_score":59.44483139790133,"uncertainty_avg":40.55516860209867,"uncertainty_penalty":-2.302880706473019}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.73533,"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},"medium":{"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":0.1968175,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"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-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.29615479166666664,"median":0.1968175,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-07-25":8},"run_count":24,"token_priced_attempt_count":24,"total":7.107714999999999},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333331,"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":50.26099362898371,"highest":39.176288778201155,"medium":47.370024176358925,"none":64.23666793239106},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-4-5","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:44Z","match_totals_all":{"draws":273,"losses":294,"wins":311},"match_totals_tracks":{"highest":{"draws":91,"losses":119,"wins":102},"medium":{"draws":85,"losses":96,"wins":101},"none":{"draws":97,"losses":79,"wins":108}},"model_slug":"claude-opus-4-5","overall":{"max":100.0,"mean":50.26099362898372,"min":9.009338261613248},"per_game":{"GB2-01":56.044272021155734,"GB2-02":9.009338261613248,"GB2-03":45.87894601202358,"GB2-04":9.92411109290124,"GB2-05":51.850038077950096,"GB2-06":55.03423685545403,"GB2-07":53.2512454384642,"GB2-08":32.41812246604711},"per_game_all":{"GB2-01":48.070472186939206,"GB2-02":36.037665378120046,"GB2-03":56.28275952976552,"GB2-04":51.435125507733915,"GB2-05":55.287679408253986,"GB2-06":45.69809211960549,"GB2-07":51.53735395191155,"GB2-08":57.738800949540014},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":33,"wins":37},"GB2-02":{"draws":93,"losses":10,"wins":3},"GB2-03":{"draws":36,"losses":20,"wins":18},"GB2-04":{"draws":69,"losses":18,"wins":13},"GB2-05":{"draws":0,"losses":52,"wins":68},"GB2-06":{"draws":9,"losses":58,"wins":55},"GB2-07":{"draws":0,"losses":61,"wins":57},"GB2-08":{"draws":30,"losses":42,"wins":60}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":14,"wins":15},"GB2-02":{"draws":31,"losses":3,"wins":0},"GB2-03":{"draws":4,"losses":8,"wins":8},"GB2-04":{"draws":17,"losses":11,"wins":4},"GB2-05":{"draws":0,"losses":20,"wins":22},"GB2-06":{"draws":6,"losses":19,"wins":21},"GB2-07":{"draws":0,"losses":20,"wins":20},"GB2-08":{"draws":28,"losses":24,"wins":12}},"medium":{"GB2-01":{"draws":6,"losses":12,"wins":14},"GB2-02":{"draws":31,"losses":4,"wins":1},"GB2-03":{"draws":11,"losses":6,"wins":5},"GB2-04":{"draws":34,"losses":5,"wins":3},"GB2-05":{"draws":0,"losses":20,"wins":20},"GB2-06":{"draws":3,"losses":17,"wins":20},"GB2-07":{"draws":0,"losses":22,"wins":18},"GB2-08":{"draws":0,"losses":10,"wins":20}},"none":{"GB2-01":{"draws":25,"losses":7,"wins":8},"GB2-02":{"draws":31,"losses":3,"wins":2},"GB2-03":{"draws":21,"losses":6,"wins":5},"GB2-04":{"draws":18,"losses":2,"wins":6},"GB2-05":{"draws":0,"losses":12,"wins":26},"GB2-06":{"draws":0,"losses":22,"wins":14},"GB2-07":{"draws":0,"losses":19,"wins":19},"GB2-08":{"draws":2,"losses":8,"wins":28}}},"per_game_raw_elo_all":{"GB2-01":1501.9696533700844,"GB2-02":1481.115388667844,"GB2-03":1501.8823989484608,"GB2-04":1489.9511185050194,"GB2-05":1541.3309241292554,"GB2-06":1475.8940796970098,"GB2-07":1492.4178687239262,"GB2-08":1584.3463532224448},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1523.4629953502915,"GB2-02":1460.3099909938203,"GB2-03":1472.519205042554,"GB2-04":1424.2661141557646,"GB2-05":1491.0530192037809,"GB2-06":1476.8626647915107,"GB2-07":1478.954303097749,"GB2-08":1440.1960159820344},"medium":{"GB2-01":1535.4053826715624,"GB2-02":1482.7817827664023,"GB2-03":1505.6237128606474,"GB2-04":1480.4511356589542,"GB2-05":1500.6982138755695,"GB2-06":1483.239411261727,"GB2-07":1471.8744937004997,"GB2-08":1625.963923900997},"none":{"GB2-01":1447.0405820883989,"GB2-02":1500.254392243309,"GB2-03":1527.5042789421814,"GB2-04":1565.136105700339,"GB2-05":1632.241539308416,"GB2-06":1467.5801630377923,"GB2-07":1526.4248093735291,"GB2-08":1686.8791197843032}},"per_game_tracks":{"highest":{"GB2-01":56.044272021155734,"GB2-02":9.009338261613248,"GB2-03":45.87894601202358,"GB2-04":9.92411109290124,"GB2-05":51.850038077950096,"GB2-06":55.03423685545403,"GB2-07":53.2512454384642,"GB2-08":32.41812246604711},"medium":{"GB2-01":51.92607099467059,"GB2-02":24.629043182743423,"GB2-03":52.73132657419512,"GB2-04":44.38126543030049,"GB2-05":44.896677388976386,"GB2-06":40.635074435351015,"GB2-07":52.20689082141307,"GB2-08":67.55384458322129},"none":{"GB2-01":36.24107354499127,"GB2-02":74.47461469000346,"GB2-03":70.23800600307787,"GB2-04":100.0,"GB2-05":69.11632275783549,"GB2-06":41.424965068011424,"GB2-07":49.15392559585737,"GB2-08":73.24443579935165}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.176288778201155,"medium":47.370024176358925,"none":64.23666793239107},"reasoning_agg":{"highest":{"max":56.044272021155734,"mean":39.176288778201155,"min":9.009338261613248},"medium":{"max":67.55384458322129,"mean":47.370024176358925,"min":24.629043182743423},"none":{"max":100.0,"mean":64.23666793239107,"min":36.24107354499127}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":45.80331145839829,"reasoning_variance":25.060379154189917,"reliability_score":60.65771947218972,"uncertainty_avg":39.34228052781028,"uncertainty_penalty":-4.457682170585429},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.044272021155734,"expected_score":33.17876493404705,"reliability_score":61.94191835053683,"uncertainty_avg":38.05808164946317,"uncertainty_penalty":-5.997523844154102},"medium":{"ceiling_score":67.55384458322129,"expected_score":43.311594219342126,"reliability_score":59.523986541042014,"uncertainty_avg":40.476013458957986,"uncertainty_penalty":-4.0584299570167985},"none":{"ceiling_score":100.0,"expected_score":60.91957522180571,"reliability_score":60.50725352499031,"uncertainty_avg":39.49274647500969,"uncertainty_penalty":-3.3170927105853636}}},{"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":0.121855,"mean":0.09110296875,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"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":0.0216425,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.121855,"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":46.699595392837736,"none":55.36439448914248},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:32Z","match_totals_all":{"draws":170,"losses":154,"wins":166},"match_totals_tracks":{"medium":{"draws":69,"losses":74,"wins":73},"none":{"draws":101,"losses":80,"wins":93}},"model_slug":"qwen-qwen3-7-max","overall":{"max":100.0,"mean":49.35652320663631,"min":14.50861546885052},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":23,"wins":29},"GB2-02":{"draws":56,"losses":3,"wins":5},"GB2-03":{"draws":29,"losses":5,"wins":2},"GB2-04":{"draws":14,"losses":6,"wins":4},"GB2-05":{"draws":0,"losses":38,"wins":34},"GB2-06":{"draws":2,"losses":38,"wins":28},"GB2-07":{"draws":0,"losses":13,"wins":57},"GB2-08":{"draws":51,"losses":28,"wins":7}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":14,"wins":9},"GB2-02":{"draws":26,"losses":2,"wins":2},"GB2-04":{"draws":14,"losses":6,"wins":4},"GB2-05":{"draws":0,"losses":19,"wins":15},"GB2-06":{"draws":2,"losses":17,"wins":15},"GB2-07":{"draws":0,"losses":7,"wins":25},"GB2-08":{"draws":20,"losses":9,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":9,"wins":20},"GB2-02":{"draws":30,"losses":1,"wins":3},"GB2-03":{"draws":29,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":19,"wins":19},"GB2-06":{"draws":0,"losses":21,"wins":13},"GB2-07":{"draws":0,"losses":6,"wins":32},"GB2-08":{"draws":31,"losses":19,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1446.6575769432316,"GB2-02":1497.5628702309473,"GB2-04":1491.1336780974766,"GB2-05":1515.607178277588,"GB2-06":1499.722397285423,"GB2-07":1703.7276305907535,"GB2-08":1474.7679718264287},"none":{"GB2-01":1595.6889672545,"GB2-02":1518.9303935289158,"GB2-03":1441.8092821040834,"GB2-05":1546.251890698747,"GB2-06":1385.0587432954344,"GB2-07":1781.24830428649,"GB2-08":1447.8125675010338}},"per_game_tracks":{"medium":{"GB2-01":37.59204653645451,"GB2-02":29.52195501373589,"GB2-04":39.3381046554568,"GB2-05":46.69860885720293,"GB2-06":43.23764304853719,"GB2-07":97.38737076494762,"GB2-08":33.121438873529215},"none":{"GB2-01":63.06816772998318,"GB2-02":88.00636553082899,"GB2-03":43.62121257614854,"GB2-05":54.345393816983226,"GB2-06":24.001006301202903,"GB2-07":100.0,"GB2-08":14.50861546885052}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":45.166364090065144,"none":53.54668232320747},"reasoning_agg":{"medium":{"max":97.38737076494762,"mean":45.166364090065144,"min":29.52195501373589},"none":{"max":100.0,"mean":53.54668232320747,"min":14.50861546885052}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":8.380318233142326},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":97.38737076494762,"expected_score":46.78456858896301,"reliability_score":54.79088443883199,"uncertainty_avg":45.20911556116801,"uncertainty_penalty":1.6182044988978674},"none":{"ceiling_score":100.0,"expected_score":50.86109247436088,"reliability_score":64.1978049151291,"uncertainty_avg":35.80219508487091,"uncertainty_penalty":-2.6855898488465897}}},{"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":0.0276132876,"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_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":1.2846227784000002},"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":42.544113461527544,"none":58.85466348231919},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:52:51Z","match_totals_all":{"draws":111,"losses":154,"wins":145},"match_totals_tracks":{"medium":{"draws":40,"losses":71,"wins":57},"none":{"draws":71,"losses":83,"wins":88}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":85.87939617310066,"mean":48.11072430490802,"min":29.45033436961341},"per_game_match_totals_all":{"GB2-01":{"draws":13,"losses":16,"wins":17},"GB2-02":{"draws":38,"losses":0,"wins":2},"GB2-03":{"draws":20,"losses":5,"wins":7},"GB2-04":{"draws":13,"losses":8,"wins":9},"GB2-05":{"draws":0,"losses":51,"wins":33},"GB2-06":{"draws":0,"losses":37,"wins":35},"GB2-07":{"draws":0,"losses":34,"wins":40},"GB2-08":{"draws":27,"losses":3,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":13,"losses":8,"wins":9},"GB2-05":{"draws":0,"losses":22,"wins":14},"GB2-06":{"draws":0,"losses":17,"wins":17},"GB2-07":{"draws":0,"losses":21,"wins":15},"GB2-08":{"draws":27,"losses":3,"wins":2}},"none":{"GB2-01":{"draws":13,"losses":16,"wins":17},"GB2-02":{"draws":38,"losses":0,"wins":2},"GB2-03":{"draws":20,"losses":5,"wins":7},"GB2-05":{"draws":0,"losses":29,"wins":19},"GB2-06":{"draws":0,"losses":20,"wins":18},"GB2-07":{"draws":0,"losses":13,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1487.003603440828,"GB2-05":1441.13880021793,"GB2-06":1534.6026025709218,"GB2-07":1498.738158105106,"GB2-08":1458.8835425277289},"none":{"GB2-01":1472.4144412982305,"GB2-02":1511.1432179335625,"GB2-03":1472.4772013795491,"GB2-05":1501.8393688414926,"GB2-06":1487.4595191351682,"GB2-07":1678.809626562992}},"per_game_tracks":{"medium":{"GB2-04":41.780133263616506,"GB2-05":33.300424537494195,"GB2-06":51.24266276068025,"GB2-07":56.94701237623334,"GB2-08":29.45033436961341},"none":{"GB2-01":41.56456664352618,"GB2-02":85.87939617310066,"GB2-03":52.33796713275897,"GB2-05":47.90309915460271,"GB2-06":45.8830004250419,"GB2-07":79.55995136488475}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.59175871348858,"none":56.629689896327456},"reasoning_agg":{"medium":{"max":56.94701237623334,"mean":39.59175871348858,"min":29.45033436961341},"none":{"max":85.87939617310066,"mean":56.629689896327456,"min":41.56456664352618}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":85.87939617310066,"reasoning_variance":17.037931182838875},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":56.94701237623334,"expected_score":42.292165204607805,"reliability_score":58.59882164611092,"uncertainty_avg":41.40117835388908,"uncertainty_penalty":2.7004064911192245},"none":{"ceiling_score":85.87939617310066,"expected_score":51.51210799045932,"reliability_score":65.48084501587371,"uncertainty_avg":34.519154984126295,"uncertainty_penalty":-5.1175819058681356}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.055222,"mean":0.046879,"median":0.046959,"min":0.039474,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.375032},"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":0.03731,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"evidence_basis":"Standard list-price estimate","max":0.136952,"mean":0.07424775,"median":0.070604,"min":0.041758,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13},"run_count":8,"token_priced_attempt_count":13,"total":0.593982}},"codegen_cost_usd":{"admitted_cell_count":18,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":29},"evidence_basis":"Standard list-price estimate","failed_cell_count":6,"max":0.136952,"mean":0.056666249999999994,"median":0.050531999999999994,"min":0.03731,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-25":16},"run_count":24,"token_priced_attempt_count":29,"total":1.35999},"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":29,"output_max":12043,"output_mean":4816.25,"output_min":2653,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":5073,"output_mean":3923.0,"output_min":3125,"run_count":8},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":13,"output_max":12043,"output_mean":6353.625,"output_min":3209,"run_count":8}},"display_name":"O3","economics":{"all":50.60726150614951,"highest":46.89856707080784,"medium":44.56024921209652,"none":52.550526564157146},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":8,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":4,"repaired_rate":0.5},"intensive":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":24,"model_code_failure_rate":0.5,"model_code_failures":4}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":156,"losses":239,"wins":263},"match_totals_tracks":{"highest":{"draws":5,"losses":82,"wins":71},"medium":{"draws":64,"losses":79,"wins":81},"none":{"draws":87,"losses":78,"wins":111}},"model_slug":"o3","overall":{"max":100.0,"mean":46.97235935818083,"min":23.13958048787723},"per_game":{"GB2-05":47.584800109539664,"GB2-06":52.03307063558969,"GB2-07":28.99415327623317,"GB2-08":58.98224426186886},"per_game_all":{"GB2-05":53.58905425023709,"GB2-06":65.30053384733783,"GB2-07":44.35046476371803,"GB2-08":39.18899316330509},"per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":26,"wins":32},"GB2-02":{"draws":30,"losses":1,"wins":1},"GB2-03":{"draws":19,"losses":9,"wins":2},"GB2-04":{"draws":42,"losses":12,"wins":6},"GB2-05":{"draws":0,"losses":55,"wins":67},"GB2-06":{"draws":13,"losses":32,"wins":61},"GB2-07":{"draws":0,"losses":62,"wins":58},"GB2-08":{"draws":40,"losses":42,"wins":36}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":25,"wins":21},"GB2-06":{"draws":4,"losses":15,"wins":17},"GB2-07":{"draws":0,"losses":27,"wins":11},"GB2-08":{"draws":1,"losses":15,"wins":22}},"medium":{"GB2-01":{"draws":5,"losses":11,"wins":16},"GB2-04":{"draws":27,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":18,"wins":20},"GB2-06":{"draws":8,"losses":13,"wins":15},"GB2-07":{"draws":0,"losses":19,"wins":23},"GB2-08":{"draws":24,"losses":14,"wins":6}},"none":{"GB2-01":{"draws":7,"losses":15,"wins":16},"GB2-02":{"draws":30,"losses":1,"wins":1},"GB2-03":{"draws":19,"losses":9,"wins":2},"GB2-04":{"draws":15,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":12,"wins":26},"GB2-06":{"draws":1,"losses":4,"wins":29},"GB2-07":{"draws":0,"losses":16,"wins":24},"GB2-08":{"draws":15,"losses":13,"wins":8}}},"per_game_raw_elo_all":{"GB2-05":1530.1855712486765,"GB2-06":1573.8653661354012,"GB2-07":1445.7713788421388,"GB2-08":1526.9459140513425},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1462.2225257409953,"GB2-06":1467.8995246611578,"GB2-07":1328.9818359174642,"GB2-08":1612.738377411857},"medium":{"GB2-01":1515.0490522046796,"GB2-04":1461.593763442168,"GB2-05":1520.5161372234036,"GB2-06":1500.61861420371,"GB2-07":1525.838093057079,"GB2-08":1474.819828960065},"none":{"GB2-01":1483.6732105344224,"GB2-02":1484.755244181817,"GB2-03":1439.5041846509685,"GB2-04":1469.123343440049,"GB2-05":1607.8180507816303,"GB2-06":1753.0779595413362,"GB2-07":1482.4942075518725,"GB2-08":1493.2795357821049}},"per_game_tracks":{"highest":{"GB2-05":47.584800109539664,"GB2-06":52.03307063558969,"GB2-07":28.99415327623317,"GB2-08":58.98224426186886},"medium":{"GB2-01":48.71815781878759,"GB2-04":27.71488064029795,"GB2-05":48.261400829098896,"GB2-06":43.8685309064238,"GB2-07":63.35337033780171,"GB2-08":35.445154740169194},"none":{"GB2-01":42.56682699841392,"GB2-02":58.89390037827312,"GB2-03":40.892759776255375,"GB2-04":49.28631238324553,"GB2-05":64.9209618120727,"GB2-06":100.0,"GB2-07":40.703870677119205,"GB2-08":23.13958048787723}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.89856707080784,"medium":41.46798443957753,"none":52.55052656415714},"reasoning_agg":{"highest":{"max":58.98224426186886,"mean":46.89856707080784,"min":28.99415327623317},"medium":{"max":63.35337033780171,"mean":41.46798443957753,"min":27.71488064029795},"none":{"max":100.0,"mean":52.55052656415714,"min":23.13958048787723}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":50.369118675932626,"reasoning_variance":11.08254212457961,"reliability_score":64.31879373744937,"uncertainty_avg":35.681206262550624,"uncertainty_penalty":3.396759317751794},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.98224426186886,"expected_score":42.99274207982221,"reliability_score":64.93496419832174,"uncertainty_avg":35.06503580167826,"uncertainty_penalty":-3.9058249909856357},"medium":{"ceiling_score":63.35337033780171,"expected_score":41.73011402470882,"reliability_score":62.562314845464094,"uncertainty_avg":37.437685154535906,"uncertainty_penalty":0.2621295851312908},"none":{"ceiling_score":100.0,"expected_score":44.55096236947962,"reliability_score":59.42261225566465,"uncertainty_avg":40.57738774433535,"uncertainty_penalty":-7.999564194677518}}},{"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":1.320515,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.07445},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.4461796875,"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":7.138874999999999},"none":{"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":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}},"codegen_cost_usd":{"admitted_cell_count":40,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":8,"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":45.0747111813484,"highest":49.57763008758633,"medium":51.58990767023265,"none":34.05659578622625},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":13,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07","GB2-08"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.1875,"model_code_failures":3},"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":"2026-07-27T11:10:13Z","match_totals_all":{"draws":77,"losses":105,"wins":222},"match_totals_tracks":{"highest":{"draws":15,"losses":33,"wins":72},"medium":{"draws":25,"losses":58,"wins":105},"none":{"draws":37,"losses":14,"wins":45}},"model_slug":"claude-opus-5","overall":{"max":94.79672549017546,"mean":45.658693241612745,"min":15.323711218544618},"per_game":{"GB2-01":33.41074838053438,"GB2-02":15.323711218544618,"GB2-03":94.79672549017546,"GB2-04":35.66511216430216,"GB2-05":63.25104721138389,"GB2-07":69.13276490537369,"GB2-08":35.46330124279012},"per_game_all":{"GB2-01":42.89129416963152,"GB2-02":28.89357977996606,"GB2-03":82.4132852647775,"GB2-04":26.86559577596636,"GB2-05":57.615517561175665,"GB2-07":51.56517870772185,"GB2-08":25.278527010199877},"per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":18,"wins":25},"GB2-02":{"draws":27,"losses":15,"wins":20},"GB2-03":{"draws":2,"losses":9,"wins":49},"GB2-04":{"draws":23,"losses":17,"wins":20},"GB2-05":{"draws":0,"losses":16,"wins":54},"GB2-07":{"draws":0,"losses":6,"wins":28},"GB2-08":{"draws":0,"losses":24,"wins":26}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":5,"wins":5},"GB2-02":{"draws":7,"losses":10,"wins":7},"GB2-03":{"draws":0,"losses":3,"wins":17},"GB2-04":{"draws":8,"losses":4,"wins":10},"GB2-05":{"draws":0,"losses":4,"wins":16},"GB2-07":{"draws":0,"losses":0,"wins":8},"GB2-08":{"draws":0,"losses":7,"wins":9}},"medium":{"GB2-01":{"draws":0,"losses":13,"wins":13},"GB2-02":{"draws":13,"losses":5,"wins":6},"GB2-03":{"draws":0,"losses":4,"wins":18},"GB2-04":{"draws":12,"losses":8,"wins":6},"GB2-05":{"draws":0,"losses":8,"wins":28},"GB2-07":{"draws":0,"losses":5,"wins":19},"GB2-08":{"draws":0,"losses":15,"wins":15}},"none":{"GB2-01":{"draws":25,"losses":0,"wins":7},"GB2-02":{"draws":7,"losses":0,"wins":7},"GB2-03":{"draws":2,"losses":2,"wins":14},"GB2-04":{"draws":3,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":4,"wins":10},"GB2-07":{"draws":0,"losses":1,"wins":1},"GB2-08":{"draws":0,"losses":2,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1537.3345901717723,"GB2-02":1533.5763915679893,"GB2-03":1597.255519409373,"GB2-04":1517.0167116655373,"GB2-05":1609.184245834232,"GB2-07":1594.2274850944302,"GB2-08":1532.4888851973137},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1520.6170540315286,"GB2-02":1523.0130885679262,"GB2-03":1611.809385490821,"GB2-04":1562.3740948086547,"GB2-05":1622.161736009653,"GB2-07":1649.0431889004428,"GB2-08":1544.601655637103},"medium":{"GB2-01":1525.6877457529356,"GB2-02":1527.995084709691,"GB2-03":1608.246347686773,"GB2-04":1493.161667330759,"GB2-05":1655.9631399611644,"GB2-07":1629.5851031397242,"GB2-08":1536.6573322056245},"none":{"GB2-01":1565.698970730853,"GB2-02":1549.721001426351,"GB2-03":1571.7108250505244,"GB2-04":1495.5143728571977,"GB2-05":1549.4278615318788,"GB2-07":1504.0541632431232,"GB2-08":1516.2076677492134}},"per_game_tracks":{"highest":{"GB2-01":33.41074838053438,"GB2-02":15.323711218544618,"GB2-03":94.79672549017546,"GB2-04":35.66511216430216,"GB2-05":63.25104721138389,"GB2-07":69.13276490537369,"GB2-08":35.46330124279012},"medium":{"GB2-01":44.220653668944664,"GB2-02":24.647525484457113,"GB2-03":86.47668070148819,"GB2-04":23.100733678652347,"GB2-05":68.13883973540305,"GB2-07":74.17264063487363,"GB2-08":40.372279787809504},"none":{"GB2-01":51.042480459415515,"GB2-02":46.70950263689645,"GB2-03":65.96644960266886,"GB2-04":21.830941484944567,"GB2-05":41.45666573674007,"GB2-07":11.390130582918244,"GB2-08":0.0}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.97539765281296,"medium":49.896118662388695,"none":43.10456340963656},"reasoning_agg":{"highest":{"max":94.79672549017546,"mean":43.97539765281296,"min":15.323711218544618},"medium":{"max":86.47668070148819,"mean":49.896118662388695,"min":23.100733678652347},"none":{"max":65.96644960266886,"mean":43.10456340963656,"min":21.830941484944567}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":94.79672549017546,"expected_score":61.64893009882978,"reasoning_variance":6.791555252752133,"reliability_score":5.370760667149753,"uncertainty_avg":94.62923933285025,"uncertainty_penalty":15.990236857217035},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":94.79672549017546,"expected_score":59.10996927632402,"reliability_score":1.4499859839122138,"uncertainty_avg":98.55001401608779,"uncertainty_penalty":15.134571623511064},"medium":{"ceiling_score":86.47668070148819,"expected_score":65.35105856704172,"reliability_score":11.825438458558693,"uncertainty_avg":88.1745615414413,"uncertainty_penalty":15.454939904653024},"none":{"ceiling_score":65.96644960266886,"expected_score":60.4857624531236,"reliability_score":2.8368575589783234,"uncertainty_avg":97.16314244102168,"uncertainty_penalty":17.381199043487037}}},{"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":0.015562441375,"median":0.0131167185,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.124499531}},"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":0.7872815620000001},"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":46.43120724907973,"none":48.80225329126459},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:44Z","match_totals_all":{"draws":153,"losses":183,"wins":186},"match_totals_tracks":{"highest":{"draws":46,"losses":94,"wins":90},"none":{"draws":107,"losses":89,"wins":96}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":95.81361600239788,"mean":45.204547523090326,"min":3.9277758714214266},"per_game":{"GB2-01":43.94251497461655,"GB2-04":22.266164983908823,"GB2-05":84.45578447414862,"GB2-06":40.14696516362653,"GB2-07":59.059631393829065,"GB2-08":28.716182504348794},"per_game_match_totals_all":{"GB2-01":{"draws":30,"losses":27,"wins":27},"GB2-02":{"draws":33,"losses":0,"wins":1},"GB2-03":{"draws":9,"losses":21,"wins":4},"GB2-04":{"draws":9,"losses":12,"wins":5},"GB2-05":{"draws":0,"losses":38,"wins":56},"GB2-06":{"draws":3,"losses":26,"wins":41},"GB2-07":{"draws":0,"losses":43,"wins":43},"GB2-08":{"draws":69,"losses":16,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":14,"wins":14},"GB2-04":{"draws":9,"losses":12,"wins":5},"GB2-05":{"draws":0,"losses":10,"wins":30},"GB2-06":{"draws":1,"losses":22,"wins":13},"GB2-07":{"draws":0,"losses":26,"wins":22},"GB2-08":{"draws":28,"losses":10,"wins":6}},"none":{"GB2-01":{"draws":22,"losses":13,"wins":13},"GB2-02":{"draws":33,"losses":0,"wins":1},"GB2-03":{"draws":9,"losses":21,"wins":4},"GB2-05":{"draws":0,"losses":28,"wins":26},"GB2-06":{"draws":2,"losses":4,"wins":28},"GB2-07":{"draws":0,"losses":17,"wins":21},"GB2-08":{"draws":41,"losses":6,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1458.854351291902,"GB2-04":1475.7104449918947,"GB2-05":1692.6344727230326,"GB2-06":1403.0395248201862,"GB2-07":1509.9174720865078,"GB2-08":1428.1773041920517},"none":{"GB2-01":1488.2361642359106,"GB2-02":1512.0031542827776,"GB2-03":1321.6391740847348,"GB2-05":1489.3932651481157,"GB2-06":1732.8057206244898,"GB2-07":1546.7400799427755,"GB2-08":1452.8918082141306}},"per_game_tracks":{"highest":{"GB2-01":43.94251497461655,"GB2-04":22.266164983908823,"GB2-05":84.45578447414862,"GB2-06":40.14696516362653,"GB2-07":59.059631393829065,"GB2-08":28.716182504348794},"none":{"GB2-01":44.637103129001645,"GB2-02":82.43445504906987,"GB2-03":3.9277758714214266,"GB2-05":46.31602333852887,"GB2-06":95.81361600239788,"GB2-07":53.20752261310657,"GB2-08":15.279277035325885}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.20910707997023,"none":47.199987966210415},"reasoning_agg":{"highest":{"max":84.45578447414862,"mean":43.20910707997023,"min":22.266164983908823},"none":{"max":95.81361600239788,"mean":47.199987966210415,"min":3.9277758714214266}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":95.81361600239788,"reasoning_variance":3.990880886240184},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":84.45578447414862,"expected_score":40.838246706399,"reliability_score":62.97081936780627,"uncertainty_avg":37.02918063219373,"uncertainty_penalty":-2.370860373571233},"none":{"ceiling_score":95.81361600239788,"expected_score":41.872037450675286,"reliability_score":66.25386925751505,"uncertainty_avg":33.74613074248496,"uncertainty_penalty":-5.327950515535129}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":15},"evidence_basis":"Standard list-price estimate","max":1.5164726249999998,"mean":1.0182428035714286,"median":0.9670455,"min":0.8356068750000001,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":15},"run_count":12,"token_priced_attempt_count":15,"total":12.214044},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.29749325000000004,"mean":0.24155631250000004,"median":0.24021375,"min":0.17873725,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":26},"run_count":24,"token_priced_attempt_count":26,"total":5.7973514999999995},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":29},"evidence_basis":"Standard list-price estimate","max":0.021615250000000003,"mean":0.017288937500000004,"median":0.01830825,"min":0.01259225,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":29},"run_count":24,"token_priced_attempt_count":29,"total":0.4149345}},"codegen_cost_usd":{"admitted_cell_count":59,"cell_count":23,"cost_basis_counts":{"local_standard_estimate":70},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.5164726249999998,"mean":0.3999331141304348,"median":0.2331955,"min":0.01259225,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":70},"run_count":60,"token_priced_attempt_count":70,"total":18.426329999999997},"codegen_latency_ms":{"attempt_count":70,"max_ms":2003150,"mean_ms":252256.05,"min_ms":9399,"run_count":60},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":2003150,"mean_ms":889166.0,"min_ms":660984,"run_count":12},"medium":{"attempt_count":26,"max_ms":308347,"mean_ms":170741.83333333334,"min_ms":75782,"run_count":24},"none":{"attempt_count":29,"max_ms":30363,"mean_ms":15315.291666666666,"min_ms":9399,"run_count":24}},"codegen_output_tokens":{"attempt_count":70,"output_max":440805,"output_mean":65843.35,"output_min":1473,"run_count":60},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":440805,"output_mean":219612.66666666663,"output_min":114521,"run_count":12},"medium":{"attempt_count":26,"output_max":83384,"output_mean":52370.75,"output_min":25033,"run_count":24},"none":{"attempt_count":29,"output_max":4573,"output_mean":2431.2916666666665,"output_min":1473,"run_count":24}},"display_name":"GPT-5.4 Mini","economics":{"all":41.77305123864498,"highest":40.16499565504982,"medium":45.38057987792682,"none":44.048968963059195},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":23,"evaluated_cells":24,"failed_game_aliases":["GB2-06"],"first_pass_admitted":22,"first_pass_rate":0.9166666666666666,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.041666666666666664},"baseline":{"admitted_plugins":24,"evaluated_cells":24,"first_pass_admitted":19,"first_pass_rate":0.7916666666666666,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":5,"repaired_rate":0.20833333333333337},"intensive":{"admitted_plugins":12,"evaluated_cells":12,"first_pass_admitted":10,"first_pass_rate":0.8333333333333334,"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-04"],"infra_failures_excluded":6,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":2,"repaired_rate":0.16666666666666666}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":787,"losses":762,"wins":642},"match_totals_tracks":{"highest":{"draws":116,"losses":175,"wins":165},"medium":{"draws":280,"losses":259,"wins":238},"none":{"draws":391,"losses":328,"wins":239}},"model_slug":"gpt-5-4-mini","overall":{"max":85.87723327609608,"mean":44.014249846563274,"min":9.447047375848612},"per_game":{"GB2-01":43.619794669436544,"GB2-02":9.447047375848612,"GB2-04":22.217961676257413,"GB2-05":43.3619156117431,"GB2-06":52.596077624755,"GB2-07":75.3566803021369,"GB2-08":34.55549232517113},"per_game_all":{"GB2-01":39.42519918359083,"GB2-02":36.48305547609812,"GB2-04":60.38766489922034,"GB2-05":35.83516271330739,"GB2-06":46.73758563472749,"GB2-07":47.308744921420974,"GB2-08":26.233945842149684},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":130,"wins":97},"GB2-02":{"draws":250,"losses":13,"wins":5},"GB2-03":{"draws":106,"losses":26,"wins":34},"GB2-04":{"draws":167,"losses":27,"wins":48},"GB2-05":{"draws":0,"losses":171,"wins":139},"GB2-06":{"draws":9,"losses":131,"wins":134},"GB2-07":{"draws":0,"losses":180,"wins":139},"GB2-08":{"draws":190,"losses":84,"wins":46}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":15,"wins":18},"GB2-02":{"draws":60,"losses":7,"wins":1},"GB2-04":{"draws":18,"losses":8,"wins":6},"GB2-05":{"draws":0,"losses":46,"wins":34},"GB2-06":{"draws":4,"losses":38,"wins":32},"GB2-07":{"draws":0,"losses":28,"wins":48},"GB2-08":{"draws":33,"losses":33,"wins":26}},"medium":{"GB2-01":{"draws":18,"losses":57,"wins":45},"GB2-02":{"draws":79,"losses":5,"wins":2},"GB2-03":{"draws":42,"losses":16,"wins":14},"GB2-04":{"draws":74,"losses":7,"wins":21},"GB2-05":{"draws":0,"losses":56,"wins":50},"GB2-06":{"draws":2,"losses":32,"wins":40},"GB2-07":{"draws":0,"losses":62,"wins":55},"GB2-08":{"draws":65,"losses":24,"wins":11}},"none":{"GB2-01":{"draws":46,"losses":58,"wins":34},"GB2-02":{"draws":111,"losses":1,"wins":2},"GB2-03":{"draws":64,"losses":10,"wins":20},"GB2-04":{"draws":75,"losses":12,"wins":21},"GB2-05":{"draws":0,"losses":69,"wins":55},"GB2-06":{"draws":3,"losses":61,"wins":62},"GB2-07":{"draws":0,"losses":90,"wins":36},"GB2-08":{"draws":92,"losses":27,"wins":9}}},"per_game_raw_elo_all":{"GB2-01":1448.7783331768435,"GB2-02":1484.3872142299251,"GB2-04":1509.7044730945825,"GB2-05":1429.5422769145237,"GB2-06":1481.2340598176208,"GB2-07":1480.213130483516,"GB2-08":1458.7080596926007},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1459.0335709392773,"GB2-02":1461.6530837544149,"GB2-04":1468.1892520044953,"GB2-05":1440.484748163939,"GB2-06":1470.1175697392898,"GB2-07":1618.647091613995,"GB2-08":1462.2969979257418},"medium":{"GB2-01":1450.432627439268,"GB2-02":1493.5272826677456,"GB2-03":1482.3068172946444,"GB2-04":1556.1217306840972,"GB2-05":1449.7983600929383,"GB2-06":1505.562222566737,"GB2-07":1496.9254891201217,"GB2-08":1465.996057457745},"none":{"GB2-01":1436.8688011519853,"GB2-02":1497.9812762676147,"GB2-03":1546.7914481309515,"GB2-04":1504.8024365951542,"GB2-05":1398.3437224866937,"GB2-06":1468.022387146836,"GB2-07":1325.0668107164308,"GB2-08":1447.831123694316}},"per_game_tracks":{"highest":{"GB2-01":43.619794669436544,"GB2-02":9.447047375848612,"GB2-04":22.217961676257413,"GB2-05":43.3619156117431,"GB2-06":52.596077624755,"GB2-07":75.3566803021369,"GB2-08":34.55549232517113},"medium":{"GB2-01":39.56023516892669,"GB2-02":26.118322896780953,"GB2-03":43.10586080056333,"GB2-04":85.87723327609608,"GB2-05":34.76514619458994,"GB2-06":45.16802637655485,"GB2-07":57.04464660609373,"GB2-08":31.405167703809017},"none":{"GB2-01":35.09556771240927,"GB2-02":73.88379615566481,"GB2-03":76.251423501129,"GB2-04":73.06779974530754,"GB2-05":29.37842633358912,"GB2-06":42.44865290287262,"GB2-07":9.524907856032284,"GB2-08":12.741177497468906}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.06344264793095,"medium":44.93033792869969,"none":44.04896896305919},"reasoning_agg":{"highest":{"max":75.3566803021369,"mean":43.06344264793095,"min":9.447047375848612},"medium":{"max":85.87723327609608,"mean":44.93033792869969,"min":26.118322896780953},"none":{"max":76.251423501129,"mean":44.04896896305919,"min":9.524907856032284}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":85.87723327609608,"expected_score":36.32468676301111,"reasoning_variance":1.8668952807687447,"reliability_score":62.93108583044924,"uncertainty_avg":37.06891416955076,"uncertainty_penalty":-7.689563083552166},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.3566803021369,"expected_score":35.30820972018611,"reliability_score":62.440820898205175,"uncertainty_avg":37.559179101794825,"uncertainty_penalty":-7.755232927744835},"medium":{"ceiling_score":85.87723327609608,"expected_score":43.07342690440516,"reliability_score":58.02971011415995,"uncertainty_avg":41.97028988584005,"uncertainty_penalty":-1.8569110242945328},"none":{"ceiling_score":76.251423501129,"expected_score":35.29560380925055,"reliability_score":64.94104776346052,"uncertainty_avg":35.05895223653948,"uncertainty_penalty":-8.753365153808637}}},{"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":0.454645,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561124999999995},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477375,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":1.4205012499999998}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"local_standard_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.454645,"mean":0.22978835937499997,"median":0.1997375,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":19},"run_count":16,"token_priced_attempt_count":19,"total":3.67661375},"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":44.523757881326794,"medium":44.54953876893639},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:53:48Z","match_totals_all":{"draws":174,"losses":177,"wins":178},"match_totals_tracks":{"highest":{"draws":90,"losses":100,"wins":103},"medium":{"draws":84,"losses":77,"wins":75}},"model_slug":"gpt-5","overall":{"max":75.94317153419365,"mean":43.80532777738345,"min":14.075498618933429},"per_game":{"GB2-01":52.732460780161915,"GB2-02":17.34035959387384,"GB2-03":37.73752316391911,"GB2-04":19.68475427518831,"GB2-05":70.47175218131694,"GB2-06":72.0351665557328,"GB2-07":58.55339190681908,"GB2-08":27.6346545936024},"per_game_match_totals_all":{"GB2-01":{"draws":16,"losses":30,"wins":22},"GB2-02":{"draws":25,"losses":9,"wins":4},"GB2-03":{"draws":20,"losses":15,"wins":6},"GB2-04":{"draws":47,"losses":11,"wins":12},"GB2-05":{"draws":0,"losses":31,"wins":39},"GB2-06":{"draws":9,"losses":29,"wins":36},"GB2-07":{"draws":0,"losses":36,"wins":50},"GB2-08":{"draws":57,"losses":16,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":7,"losses":17,"wins":14},"GB2-02":{"draws":25,"losses":9,"wins":4},"GB2-03":{"draws":7,"losses":9,"wins":5},"GB2-04":{"draws":21,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":14,"wins":24},"GB2-06":{"draws":3,"losses":15,"wins":24},"GB2-07":{"draws":0,"losses":21,"wins":25},"GB2-08":{"draws":27,"losses":10,"wins":5}},"medium":{"GB2-01":{"draws":9,"losses":13,"wins":8},"GB2-03":{"draws":13,"losses":6,"wins":1},"GB2-04":{"draws":26,"losses":6,"wins":10},"GB2-05":{"draws":0,"losses":17,"wins":15},"GB2-06":{"draws":6,"losses":14,"wins":12},"GB2-07":{"draws":0,"losses":15,"wins":25},"GB2-08":{"draws":30,"losses":6,"wins":4}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1502.7279069985364,"GB2-02":1482.3123150364672,"GB2-03":1452.8752028586307,"GB2-04":1463.7857498008668,"GB2-05":1608.3919725416276,"GB2-06":1572.2866257689911,"GB2-07":1507.9577125410674,"GB2-08":1423.1111884937484},"medium":{"GB2-01":1421.548867722602,"GB2-03":1429.025634526283,"GB2-04":1515.2487684925604,"GB2-05":1545.773258237218,"GB2-06":1499.1451109264806,"GB2-07":1589.9197735616242,"GB2-08":1446.2261844028271}},"per_game_tracks":{"highest":{"GB2-01":52.732460780161915,"GB2-02":17.34035959387384,"GB2-03":37.73752316391911,"GB2-04":19.68475427518831,"GB2-05":70.47175218131694,"GB2-06":72.0351665557328,"GB2-07":58.55339190681908,"GB2-08":27.6346545936024},"medium":{"GB2-01":33.635215551159206,"GB2-03":14.075498618933429,"GB2-04":65.47881725717096,"GB2-05":51.892029013183205,"GB2-06":42.64185819153504,"GB2-07":75.94317153419365,"GB2-08":28.18018121637925}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.5237578813268,"medium":43.08689767344009},"reasoning_agg":{"highest":{"max":72.0351665557328,"mean":44.5237578813268,"min":17.34035959387384},"medium":{"max":75.94317153419365,"mean":43.08689767344009,"min":14.075498618933429}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":75.94317153419365,"reasoning_variance":1.4368602078867099},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.0351665557328,"expected_score":38.97420889449545,"reliability_score":60.61608449306078,"uncertainty_avg":39.38391550693922,"uncertainty_penalty":-5.549548986831354},"medium":{"ceiling_score":75.94317153419365,"expected_score":41.136296672601574,"reliability_score":57.26252869400143,"uncertainty_avg":42.73747130599857,"uncertainty_penalty":-1.9506010008385175}}},{"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-2026-07-25":10},"run_count":9,"token_priced_attempt_count":10,"total":28.806541},"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":0.046574,"mean":0.036155625,"median":0.035338,"min":0.025803,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":9,"token_priced_attempt_count":9,"total":0.315048},"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-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":0.17574199999999998}},"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-2026-07-25":28},"run_count":26,"token_priced_attempt_count":28,"total":29.297331000000003},"codegen_latency_ms":{"attempt_count":28,"max_ms":220389,"mean_ms":65068.84615384616,"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":42.14870445026389,"highest":50.439969484988076,"medium":45.01088869780857,"none":30.995255167995055},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:32Z","match_totals_all":{"draws":296,"losses":309,"wins":224},"match_totals_tracks":{"highest":{"draws":67,"losses":101,"wins":110},"medium":{"draws":112,"losses":74,"wins":70},"none":{"draws":117,"losses":134,"wins":44}},"model_slug":"gpt-5-6-luna","overall":{"max":81.23280156110413,"mean":42.1487044502639,"min":0.0},"per_game":{"GB2-01":69.32309231802564,"GB2-02":15.045468569876284,"GB2-03":44.83538593718423,"GB2-04":33.20708835457535,"GB2-05":45.189665043930695,"GB2-06":76.86614736671234,"GB2-07":73.52687028032364,"GB2-08":45.52603800927643},"per_game_all":{"GB2-01":47.940653884182744,"GB2-02":37.98767565275601,"GB2-03":44.251266699218455,"GB2-04":54.978156015126935,"GB2-05":32.29582613539589,"GB2-06":43.89208589294183,"GB2-07":48.00470570344151,"GB2-08":27.839265619047804},"per_game_match_totals_all":{"GB2-01":{"draws":17,"losses":47,"wins":39},"GB2-02":{"draws":94,"losses":4,"wins":0},"GB2-03":{"draws":34,"losses":23,"wins":17},"GB2-04":{"draws":77,"losses":17,"wins":16},"GB2-05":{"draws":0,"losses":73,"wins":39},"GB2-06":{"draws":12,"losses":54,"wins":38},"GB2-07":{"draws":0,"losses":65,"wins":51},"GB2-08":{"draws":62,"losses":26,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":12,"wins":20},"GB2-02":{"draws":34,"losses":4,"wins":0},"GB2-03":{"draws":6,"losses":9,"wins":5},"GB2-04":{"draws":15,"losses":11,"wins":8},"GB2-05":{"draws":0,"losses":21,"wins":21},"GB2-06":{"draws":9,"losses":11,"wins":16},"GB2-07":{"draws":0,"losses":16,"wins":22},"GB2-08":{"draws":3,"losses":17,"wins":18}},"medium":{"GB2-01":{"draws":5,"losses":14,"wins":13},"GB2-02":{"draws":28,"losses":0,"wins":0},"GB2-03":{"draws":15,"losses":3,"wins":2},"GB2-04":{"draws":36,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":18,"wins":14},"GB2-06":{"draws":3,"losses":13,"wins":16},"GB2-07":{"draws":0,"losses":21,"wins":19},"GB2-08":{"draws":25,"losses":4,"wins":5}},"none":{"GB2-01":{"draws":12,"losses":21,"wins":6},"GB2-02":{"draws":32,"losses":0,"wins":0},"GB2-03":{"draws":13,"losses":11,"wins":10},"GB2-04":{"draws":26,"losses":5,"wins":7},"GB2-05":{"draws":0,"losses":34,"wins":4},"GB2-06":{"draws":0,"losses":30,"wins":6},"GB2-07":{"draws":0,"losses":28,"wins":10},"GB2-08":{"draws":34,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1500.5137418227011,"GB2-02":1490.5866783149643,"GB2-03":1471.3320346991638,"GB2-04":1505.564934884232,"GB2-05":1408.2581962709753,"GB2-06":1474.185724388023,"GB2-07":1483.503165292621,"GB2-08":1474.1304923951857},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1594.3414950628655,"GB2-02":1475.2705345013087,"GB2-03":1470.2584936420342,"GB2-04":1505.4321854644402,"GB2-05":1450.1762853210785,"GB2-06":1603.4084478009274,"GB2-07":1607.214746963142,"GB2-08":1532.649397933092},"medium":{"GB2-01":1533.14490561491,"GB2-02":1495.6061795407566,"GB2-03":1474.8862866013676,"GB2-04":1493.5860731188106,"GB2-05":1544.720646031192,"GB2-06":1552.1657338848022,"GB2-07":1507.6321565014584,"GB2-08":1454.7582569289596},"none":{"GB2-01":1374.0548247903282,"GB2-02":1500.8833209028282,"GB2-03":1468.8513238540895,"GB2-04":1517.6765460694453,"GB2-05":1229.8776574606557,"GB2-06":1266.9829914783388,"GB2-07":1335.662592413262,"GB2-08":1434.9838223235058}},"per_game_tracks":{"highest":{"GB2-01":69.32309231802564,"GB2-02":15.045468569876284,"GB2-03":44.83538593718423,"GB2-04":33.20708835457535,"GB2-05":45.189665043930695,"GB2-06":76.86614736671234,"GB2-07":73.52687028032364,"GB2-08":45.52603800927643},"medium":{"GB2-01":51.569846961777536,"GB2-02":27.051073039487715,"GB2-03":36.10324684880155,"GB2-04":50.49457812970133,"GB2-05":51.697813362256994,"GB2-06":54.81011031211314,"GB2-07":59.39696163894203,"GB2-08":28.963479289388196},"none":{"GB2-01":22.929022372745035,"GB2-02":71.86648534890404,"GB2-03":51.81516731166958,"GB2-04":81.23280156110413,"GB2-05":0.0,"GB2-06":0.0,"GB2-07":11.090285191058866,"GB2-08":9.028279558478792}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.43996948498808,"medium":45.01088869780856,"none":30.995255167995055},"reasoning_agg":{"highest":{"max":76.86614736671234,"mean":50.43996948498808,"min":15.045468569876284},"medium":{"max":59.39696163894203,"mean":45.01088869780856,"min":27.051073039487715},"none":{"max":81.23280156110413,"mean":30.995255167995055,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":81.23280156110413,"expected_score":37.13856906511581,"reasoning_variance":19.44471431699303,"reliability_score":58.91110459105842,"uncertainty_avg":41.08889540894158,"uncertainty_penalty":-5.010135385148089},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.86614736671234,"expected_score":45.936315611073724,"reliability_score":58.83697398808645,"uncertainty_avg":41.16302601191355,"uncertainty_penalty":-4.5036538739143595},"medium":{"ceiling_score":59.39696163894203,"expected_score":42.888749874343006,"reliability_score":55.53256481752909,"uncertainty_avg":44.46743518247091,"uncertainty_penalty":-2.122138823465555},"none":{"ceiling_score":81.23280156110413,"expected_score":22.59064170993072,"reliability_score":62.36377496755969,"uncertainty_avg":37.63622503244031,"uncertainty_penalty":-8.404613458064336}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.4567,"mean":0.3660333333333334,"median":0.355077,"min":0.234622,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-25":8},"run_count":10,"token_priced_attempt_count":10,"total":3.544308},"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-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":0.624428}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.4567,"mean":0.2220434166666667,"median":0.183367,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-25":17},"run_count":18,"token_priced_attempt_count":19,"total":4.168736},"codegen_latency_ms":{"attempt_count":19,"max_ms":417022,"mean_ms":186639.61111111112,"min_ms":23645,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":417022,"mean_ms":302024.2,"min_ms":185272,"run_count":10},"medium":{"attempt_count":9,"max_ms":95118,"mean_ms":42408.875,"min_ms":23645,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43177,"output_mean":20523.777777777777,"output_min":3136,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43177,"output_mean":32906.3,"output_min":21120,"run_count":10},"medium":{"attempt_count":9,"output_max":10845,"output_mean":5045.625,"output_min":3136,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"highest":44.66700109741266,"medium":37.61119006859883},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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},"intensive":{"admitted_plugins":10,"evaluated_cells":10,"first_pass_admitted":10,"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":18,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:58Z","match_totals_all":{"draws":178,"losses":232,"wins":210},"match_totals_tracks":{"highest":{"draws":105,"losses":144,"wins":119},"medium":{"draws":73,"losses":88,"wins":91}},"model_slug":"claude-sonnet-5","overall":{"max":64.19011345565015,"mean":40.52167423853142,"min":13.67413531950196},"per_game":{"GB2-01":64.19011345565015,"GB2-02":22.63149514807357,"GB2-03":47.79147907099729,"GB2-04":26.89600191666384,"GB2-05":58.554481452434786,"GB2-06":62.351569828557906,"GB2-07":44.02062671279558,"GB2-08":30.900241194128142},"per_game_match_totals_all":{"GB2-01":{"draws":11,"losses":33,"wins":40},"GB2-02":{"draws":45,"losses":11,"wins":6},"GB2-03":{"draws":25,"losses":21,"wins":14},"GB2-04":{"draws":43,"losses":12,"wins":9},"GB2-05":{"draws":0,"losses":43,"wins":45},"GB2-06":{"draws":6,"losses":44,"wins":46},"GB2-07":{"draws":0,"losses":42,"wins":40},"GB2-08":{"draws":48,"losses":26,"wins":10}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":7,"losses":15,"wins":24},"GB2-02":{"draws":20,"losses":8,"wins":6},"GB2-03":{"draws":25,"losses":21,"wins":14},"GB2-04":{"draws":24,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":26,"wins":24},"GB2-06":{"draws":4,"losses":21,"wins":25},"GB2-07":{"draws":0,"losses":25,"wins":15},"GB2-08":{"draws":25,"losses":21,"wins":6}},"medium":{"GB2-01":{"draws":4,"losses":18,"wins":16},"GB2-02":{"draws":25,"losses":3,"wins":0},"GB2-04":{"draws":19,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":17,"wins":21},"GB2-06":{"draws":2,"losses":23,"wins":21},"GB2-07":{"draws":0,"losses":17,"wins":25},"GB2-08":{"draws":23,"losses":5,"wins":4}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1556.4384183763725,"GB2-02":1502.109029905419,"GB2-03":1477.2194515351428,"GB2-04":1481.0313605674366,"GB2-05":1527.212001390186,"GB2-06":1514.457032252185,"GB2-07":1421.2829528731577,"GB2-08":1436.4921846225002},"medium":{"GB2-01":1456.48810791184,"GB2-02":1471.8248157078187,"GB2-04":1468.3975010402958,"GB2-05":1517.505095150019,"GB2-06":1492.1341808124089,"GB2-07":1492.900041183424,"GB2-08":1470.581569854736}},"per_game_tracks":{"highest":{"GB2-01":64.19011345565015,"GB2-02":22.63149514807357,"GB2-03":47.79147907099729,"GB2-04":26.89600191666384,"GB2-05":58.554481452434786,"GB2-06":62.351569828557906,"GB2-07":44.02062671279558,"GB2-08":30.900241194128142},"medium":{"GB2-01":40.368965985452455,"GB2-02":13.67413531950196,"GB2-04":29.02245077592327,"GB2-05":47.70583868294409,"GB2-06":43.62277387144765,"GB2-07":56.730260575810455,"GB2-08":32.1539052691119}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.66700109741265,"medium":36.37634737965019},"reasoning_agg":{"highest":{"max":64.19011345565015,"mean":44.66700109741265,"min":22.63149514807357},"medium":{"max":56.730260575810455,"mean":36.37634737965019,"min":13.67413531950196}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":64.19011345565015,"reasoning_variance":8.29065371776246},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.19011345565015,"expected_score":38.67523228617417,"reliability_score":64.21902114756915,"uncertainty_avg":35.78097885243084,"uncertainty_penalty":-5.9917688112384795},"medium":{"ceiling_score":56.730260575810455,"expected_score":35.12036316723008,"reliability_score":60.60084273210892,"uncertainty_avg":39.39915726789108,"uncertainty_penalty":-1.2559842124201097}}},{"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":0.08145696}},"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":422352.6470588235,"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":43.55210022885904,"none":38.2189369139256},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:44:24Z","match_totals_all":{"draws":125,"losses":166,"wins":139},"match_totals_tracks":{"medium":{"draws":62,"losses":74,"wins":84},"none":{"draws":63,"losses":92,"wins":55}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":72.54611424825131,"mean":38.06634569299311,"min":9.32585669310106},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":36,"wins":27},"GB2-02":{"draws":59,"losses":2,"wins":1},"GB2-04":{"draws":17,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":44,"wins":48},"GB2-06":{"draws":5,"losses":37,"wins":26},"GB2-07":{"draws":0,"losses":43,"wins":37},"GB2-08":{"draws":29,"losses":3,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":3,"losses":18,"wins":19},"GB2-02":{"draws":25,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":20,"wins":24},"GB2-06":{"draws":5,"losses":12,"wins":15},"GB2-07":{"draws":0,"losses":19,"wins":25},"GB2-08":{"draws":29,"losses":3,"wins":0}},"none":{"GB2-01":{"draws":12,"losses":18,"wins":8},"GB2-02":{"draws":34,"losses":0,"wins":0},"GB2-04":{"draws":17,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":24,"wins":24},"GB2-06":{"draws":0,"losses":25,"wins":11},"GB2-07":{"draws":0,"losses":24,"wins":12}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1492.228339405642,"GB2-02":1495.2058690166305,"GB2-05":1494.0902199224313,"GB2-06":1550.09007303238,"GB2-07":1503.7618985400777,"GB2-08":1463.472252814386},"none":{"GB2-01":1426.8304712938525,"GB2-02":1499.709542836781,"GB2-04":1491.1344575032592,"GB2-05":1458.4286081272326,"GB2-06":1378.0814396949431,"GB2-07":1328.5282011459767}},"per_game_tracks":{"medium":{"GB2-01":46.250463050232824,"GB2-02":26.825899706809754,"GB2-05":44.201640552019015,"GB2-06":54.33374539673026,"GB2-07":59.19000584975746,"GB2-08":30.51084681760492},"none":{"GB2-01":32.30821895746051,"GB2-02":72.54611424825131,"GB2-04":51.74450173865824,"GB2-05":40.4461869314892,"GB2-06":22.942742914593307,"GB2-07":9.32585669310106}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.529796097077885,"none":35.60289528890834},"reasoning_agg":{"medium":{"max":59.19000584975746,"mean":40.529796097077885,"min":26.825899706809754},"none":{"max":72.54611424825131,"mean":35.60289528890834,"min":9.32585669310106}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":72.54611424825131,"reasoning_variance":4.926900808169542},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.19000584975746,"expected_score":43.51532205103273,"reliability_score":61.402765918581196,"uncertainty_avg":38.597234081418804,"uncertainty_penalty":2.9855259539548484},"none":{"ceiling_score":72.54611424825131,"expected_score":28.446350239842303,"reliability_score":57.89751199256586,"uncertainty_avg":42.10248800743414,"uncertainty_penalty":-7.15654504906604}}},{"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_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":37.95666581573108},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:30:10Z","match_totals_all":{"draws":80,"losses":90,"wins":76},"match_totals_tracks":{"medium":{"draws":80,"losses":90,"wins":76}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":60.78618619226293,"mean":37.95666581573108,"min":21.629334144240534},"per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":16,"wins":19},"GB2-02":{"draws":23,"losses":2,"wins":1},"GB2-03":{"draws":10,"losses":5,"wins":5},"GB2-04":{"draws":18,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":17,"wins":21},"GB2-06":{"draws":0,"losses":21,"wins":15},"GB2-07":{"draws":0,"losses":21,"wins":11},"GB2-08":{"draws":24,"losses":5,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":5,"losses":16,"wins":19},"GB2-02":{"draws":23,"losses":2,"wins":1},"GB2-03":{"draws":10,"losses":5,"wins":5},"GB2-04":{"draws":18,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":17,"wins":21},"GB2-06":{"draws":0,"losses":21,"wins":15},"GB2-07":{"draws":0,"losses":21,"wins":11},"GB2-08":{"draws":24,"losses":5,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1511.3454441519766,"GB2-02":1496.3130508470942,"GB2-03":1523.7332408807254,"GB2-04":1476.5809913195983,"GB2-05":1588.3981121736656,"GB2-06":1403.7159485834295,"GB2-07":1356.028657307499,"GB2-08":1463.6745628998226}},"per_game_tracks":{"medium":{"GB2-01":49.26308913725138,"GB2-02":25.928875713842658,"GB2-03":59.5653731373665,"GB2-04":28.450025513233655,"GB2-05":60.78618619226293,"GB2-06":21.629334144240534,"GB2-07":27.472839297816236,"GB2-08":30.557603389834696}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.95666581573108},"reasoning_agg":{"medium":{"max":60.78618619226293,"mean":37.95666581573108,"min":21.629334144240534}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":60.78618619226293},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":60.78618619226293,"expected_score":37.433331356280064,"reliability_score":53.24758694166321,"uncertainty_avg":46.75241305833679,"uncertainty_penalty":-0.5233344594510143}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":40.69412087581795},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:03:48Z","match_totals_all":{"draws":44,"losses":71,"wins":65},"match_totals_tracks":{"medium":{"draws":44,"losses":71,"wins":65}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":57.239809739997824,"mean":37.87014662392437,"min":6.341962033451487},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":14,"wins":16},"GB2-02":{"draws":25,"losses":5,"wins":2},"GB2-04":{"draws":17,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":17,"wins":15},"GB2-07":{"draws":0,"losses":18,"wins":16},"GB2-08":{"draws":2,"losses":14,"wins":14}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":14,"wins":16},"GB2-02":{"draws":25,"losses":5,"wins":2},"GB2-04":{"draws":17,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":17,"wins":15},"GB2-07":{"draws":0,"losses":18,"wins":16},"GB2-08":{"draws":2,"losses":14,"wins":14}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1509.3347154731714,"GB2-02":1454.142690683152,"GB2-04":1476.253267864668,"GB2-05":1543.62195036127,"GB2-07":1502.0470435170537,"GB2-08":1564.5805260844868}},"per_game_tracks":{"medium":{"GB2-01":47.46921073576547,"GB2-02":6.341962033451487,"GB2-04":28.251329164883348,"GB2-05":51.49509493140263,"GB2-07":57.239809739997824,"GB2-08":53.367318649406904}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.87014662392437},"reasoning_agg":{"medium":{"max":57.239809739997824,"mean":37.87014662392437,"min":6.341962033451487}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":57.239809739997824},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":57.239809739997824,"expected_score":39.98732305499231,"reliability_score":53.34073491935636,"uncertainty_avg":46.65926508064364,"uncertainty_penalty":2.1171764310679393}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":22},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00596013,"mean":0.0023956312500000004,"median":0.00186283,"min":0.00105702,"recorded_attempt_count":22,"run_count":14,"total":0.035421560000000005},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.00223773125,"median":0.00220356,"min":0.00093502,"recorded_attempt_count":23,"run_count":14,"total":0.030659259999999997}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":45},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00596013,"mean":0.0023166812500000004,"median":0.00193686,"min":0.00093502,"recorded_attempt_count":45,"run_count":28,"total":0.06608082},"codegen_latency_ms":{"attempt_count":45,"max_ms":490920,"mean_ms":93765.89285714286,"min_ms":17974,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":22,"max_ms":490920,"mean_ms":102055.21428571428,"min_ms":17974,"run_count":14},"none":{"attempt_count":23,"max_ms":199208,"mean_ms":85476.57142857143,"min_ms":34688,"run_count":14}},"codegen_output_tokens":{"attempt_count":45,"output_max":42038,"output_mean":6248.107142857143,"output_min":1564,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":22,"output_max":42038,"output_mean":7478.214285714285,"output_min":1564,"run_count":14},"none":{"attempt_count":23,"output_max":11735,"output_mean":5018.0,"output_min":1646,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"none":36.175716220176255},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.42857142857142855,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.42857142857142855}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-07-27T11:54:26Z","match_totals_all":{"draws":63,"losses":45,"wins":58},"match_totals_tracks":{"none":{"draws":63,"losses":45,"wins":58}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":52.40364823336918,"mean":37.02193320194721,"min":13.186846319074863},"per_game_match_totals_all":{"GB2-01":{"draws":8,"losses":6,"wins":10},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":17,"losses":6,"wins":7},"GB2-05":{"draws":0,"losses":16,"wins":20},"GB2-06":{"draws":0,"losses":6,"wins":8},"GB2-07":{"draws":0,"losses":9,"wins":13},"GB2-08":{"draws":30,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":8,"losses":6,"wins":10},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":17,"losses":6,"wins":7},"GB2-05":{"draws":0,"losses":16,"wins":20},"GB2-06":{"draws":0,"losses":6,"wins":8},"GB2-07":{"draws":0,"losses":9,"wins":13},"GB2-08":{"draws":30,"losses":2,"wins":0}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1529.7073139467598,"GB2-02":1500.9592129056118,"GB2-03":1503.1949543097946,"GB2-05":1506.078781468915,"GB2-06":1498.968196610536,"GB2-07":1543.030878826474,"GB2-08":1486.2472684126587}},"per_game_tracks":{"none":{"GB2-01":42.23174511394901,"GB2-02":20.688739759146618,"GB2-03":52.40364823336918,"GB2-05":42.41308178766992,"GB2-06":40.15867164754771,"GB2-07":42.147280680476456,"GB2-08":13.186846319074863}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":37.02193320194721},"reasoning_agg":{"none":{"max":52.40364823336918,"mean":37.02193320194721,"min":13.186846319074863}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":52.40364823336918},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":52.40364823336918,"expected_score":45.528260914629286,"reliability_score":13.142528230016055,"uncertainty_avg":86.85747176998395,"uncertainty_penalty":8.506327712682072}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.04649778,"mean":0.039593841,"median":0.039509778,"min":0.030762138,"recorded_attempt_count":32,"run_count":16,"total":0.6335014560000001},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.014209038,"mean":0.0093957345,"median":0.009312405,"min":0.004429524000000001,"recorded_attempt_count":25,"run_count":16,"total":0.150331752}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.04649778,"mean":0.024494787749999997,"median":0.022485588,"min":0.004429524000000001,"recorded_attempt_count":57,"run_count":32,"total":0.783833208},"codegen_latency_ms":{"attempt_count":58,"max_ms":848935,"mean_ms":404316.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":33,"max_ms":848935,"mean_ms":690334.25,"min_ms":443841,"run_count":16},"none":{"attempt_count":25,"max_ms":266268,"mean_ms":118299.25,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":57,"output_max":40000,"output_mean":18334.0625,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":32,"output_max":40000,"output_mean":31078.25,"output_min":16796,"run_count":16},"none":{"attempt_count":25,"output_max":13510,"output_mean":5589.875,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"none":35.33672507216442},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"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":"2026-07-27T11:54:00Z","match_totals_all":{"draws":80,"losses":56,"wins":66},"match_totals_tracks":{"none":{"draws":80,"losses":56,"wins":66}},"model_slug":"meituan-longcat-2-0","overall":{"max":50.12310158170739,"mean":35.93158565152946,"min":13.081708132088846},"per_game_match_totals_all":{"GB2-01":{"draws":13,"losses":7,"wins":14},"GB2-02":{"draws":10,"losses":0,"wins":0},"GB2-03":{"draws":21,"losses":7,"wins":6},"GB2-04":{"draws":4,"losses":2,"wins":2},"GB2-05":{"draws":0,"losses":21,"wins":15},"GB2-06":{"draws":0,"losses":5,"wins":13},"GB2-07":{"draws":0,"losses":11,"wins":15},"GB2-08":{"draws":32,"losses":3,"wins":1}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":13,"losses":7,"wins":14},"GB2-02":{"draws":10,"losses":0,"wins":0},"GB2-03":{"draws":21,"losses":7,"wins":6},"GB2-04":{"draws":4,"losses":2,"wins":2},"GB2-05":{"draws":0,"losses":21,"wins":15},"GB2-06":{"draws":0,"losses":5,"wins":13},"GB2-07":{"draws":0,"losses":11,"wins":15},"GB2-08":{"draws":32,"losses":3,"wins":1}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1522.0976596991115,"GB2-02":1497.0276434906507,"GB2-03":1490.4276222977142,"GB2-04":1496.4112467848165,"GB2-05":1447.547535104076,"GB2-06":1557.9227968187288,"GB2-07":1504.6437886407325,"GB2-08":1480.080810281208}},"per_game_tracks":{"none":{"GB2-01":44.02603444825141,"GB2-02":27.76477026774663,"GB2-03":50.12310158170739,"GB2-04":32.02104837812793,"GB2-05":32.358838110049646,"GB2-06":47.4412296068665,"GB2-07":35.877070052477,"GB2-08":13.081708132088846}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":35.93158565152946},"reasoning_agg":{"none":{"max":50.12310158170739,"mean":35.93158565152946,"min":13.081708132088846}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":50.12310158170739},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":50.12310158170739,"expected_score":43.712843198271166,"reliability_score":14.8599026751412,"uncertainty_avg":85.1400973248588,"uncertainty_penalty":7.781257546741706}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.38568888333333334,"mean":0.29249454166666666,"median":0.2834616125,"min":0.2238526,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":25},"run_count":17,"token_priced_attempt_count":25,"total":5.07700365},"medium":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":49},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":0.0362005625,"mean":0.024352715625,"median":0.025206018750000003,"min":0.0165820625,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":49},"run_count":32,"token_priced_attempt_count":49,"total":0.7792869000000001},"none":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":56},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":0.013223525,"mean":0.008998335937500001,"median":0.008458650000000002,"min":0.0058062875,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":56},"run_count":32,"token_priced_attempt_count":56,"total":0.28794675000000003}},"codegen_cost_usd":{"admitted_cell_count":65,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":130},"evidence_basis":"Standard list-price estimate","failed_cell_count":16,"max":0.38568888333333334,"mean":0.10861519774305556,"median":0.025206018750000003,"min":0.0058062875,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":130},"run_count":81,"token_priced_attempt_count":130,"total":6.1442372999999995},"codegen_latency_ms":{"attempt_count":130,"max_ms":4769864,"mean_ms":387335.3209876543,"min_ms":20868,"run_count":81},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":25,"max_ms":4769864,"mean_ms":1538065.3529411764,"min_ms":584445,"run_count":17},"medium":{"attempt_count":49,"max_ms":1064325,"mean_ms":119877.59375,"min_ms":36200,"run_count":32},"none":{"attempt_count":56,"max_ms":101610,"mean_ms":43467.71875,"min_ms":20868,"run_count":32}},"codegen_output_tokens":{"attempt_count":130,"output_max":316330,"output_mean":57506.49382716049,"output_min":2711,"run_count":81},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":25,"output_max":316330,"output_mean":230905.0,"output_min":131376,"run_count":17},"medium":{"attempt_count":49,"output_max":27931,"output_mean":17655.9375,"output_min":7818,"run_count":32},"none":{"attempt_count":56,"output_max":10894,"output_mean":5239.09375,"output_min":2711,"run_count":32}},"display_name":"GPT-5.4 Nano","economics":{"all":39.96028479927107,"highest":41.77559118513494,"medium":33.63533465737553,"none":44.46992855530277},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":25,"evaluated_cells":32,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":13,"first_pass_rate":0.40625,"model_code_failure_rate":0.21875,"model_code_failures":7,"repaired_admitted":12,"repaired_rate":0.375},"baseline":{"admitted_plugins":25,"evaluated_cells":32,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-06","GB2-07"],"first_pass_admitted":10,"first_pass_rate":0.3125,"model_code_failure_rate":0.21875,"model_code_failures":7,"repaired_admitted":15,"repaired_rate":0.46875},"intensive":{"admitted_plugins":15,"evaluated_cells":17,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":10,"first_pass_rate":0.5882352941176471,"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07"],"infra_failures_excluded":9,"model_code_failure_rate":0.1176470588235294,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.29411764705882354}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":805,"losses":954,"wins":647},"match_totals_tracks":{"highest":{"draws":172,"losses":210,"wins":171},"medium":{"draws":239,"losses":416,"wins":228},"none":{"draws":394,"losses":328,"wins":248}},"model_slug":"gpt-5-4-nano","overall":{"max":62.474340824695595,"mean":35.928055128048655,"min":19.00156075859134},"per_game":{"GB2-01":20.40622958183412,"GB2-02":15.262649000659373,"GB2-03":38.39143751674923,"GB2-04":25.436526819126385,"GB2-05":59.862626312371006,"GB2-06":85.33771358831747,"GB2-07":46.18505938257291,"GB2-08":43.322487279449035},"per_game_all":{"GB2-01":24.24120502223127,"GB2-02":32.88912314602112,"GB2-03":38.54029110428968,"GB2-04":49.19116301843803,"GB2-05":39.102275103367155,"GB2-06":66.97846678831257,"GB2-07":34.00585053803241,"GB2-08":34.73390367347637},"per_game_match_totals_all":{"GB2-01":{"draws":94,"losses":211,"wins":79},"GB2-02":{"draws":287,"losses":23,"wins":6},"GB2-03":{"draws":62,"losses":48,"wins":34},"GB2-04":{"draws":116,"losses":46,"wins":38},"GB2-05":{"draws":0,"losses":205,"wins":144},"GB2-06":{"draws":17,"losses":130,"wins":157},"GB2-07":{"draws":0,"losses":205,"wins":96},"GB2-08":{"draws":229,"losses":86,"wins":93}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":38,"wins":9},"GB2-02":{"draws":65,"losses":10,"wins":3},"GB2-03":{"draws":6,"losses":9,"wins":5},"GB2-04":{"draws":23,"losses":23,"wins":18},"GB2-05":{"draws":0,"losses":37,"wins":42},"GB2-06":{"draws":4,"losses":10,"wins":22},"GB2-07":{"draws":0,"losses":52,"wins":32},"GB2-08":{"draws":57,"losses":31,"wins":40}},"medium":{"GB2-01":{"draws":26,"losses":88,"wins":22},"GB2-02":{"draws":88,"losses":6,"wins":2},"GB2-03":{"draws":13,"losses":6,"wins":3},"GB2-04":{"draws":45,"losses":13,"wins":16},"GB2-05":{"draws":0,"losses":83,"wins":63},"GB2-06":{"draws":12,"losses":82,"wins":66},"GB2-07":{"draws":0,"losses":110,"wins":29},"GB2-08":{"draws":55,"losses":28,"wins":27}},"none":{"GB2-01":{"draws":51,"losses":85,"wins":48},"GB2-02":{"draws":134,"losses":7,"wins":1},"GB2-03":{"draws":43,"losses":33,"wins":26},"GB2-04":{"draws":48,"losses":10,"wins":4},"GB2-05":{"draws":0,"losses":85,"wins":39},"GB2-06":{"draws":1,"losses":38,"wins":69},"GB2-07":{"draws":0,"losses":43,"wins":35},"GB2-08":{"draws":117,"losses":27,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1364.1279962097667,"GB2-02":1480.6718547096534,"GB2-03":1458.8393696564847,"GB2-04":1492.6517901328516,"GB2-05":1450.1721718351364,"GB2-06":1586.9339370493024,"GB2-07":1402.83458245166,"GB2-08":1498.1427246204064},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1340.674059333723,"GB2-02":1475.1460655091832,"GB2-03":1456.2986766562403,"GB2-04":1479.6884547552384,"GB2-05":1542.1155814285205,"GB2-06":1649.6360187308812,"GB2-07":1433.535087741965,"GB2-08":1516.0879654523894},"medium":{"GB2-01":1324.6260459129842,"GB2-02":1480.7886719944054,"GB2-03":1443.375433605767,"GB2-04":1523.4010262362171,"GB2-05":1445.2562195349926,"GB2-06":1504.8279002211525,"GB2-07":1325.1028552232106,"GB2-08":1487.3596350653709},"none":{"GB2-01":1427.0838833825933,"GB2-02":1486.080826625372,"GB2-03":1476.843998707447,"GB2-04":1474.8658894070993,"GB2-05":1363.1447145418963,"GB2-06":1606.3378921958729,"GB2-07":1449.865804389804,"GB2-08":1490.9805733434591}},"per_game_tracks":{"highest":{"GB2-01":20.40622958183412,"GB2-02":15.262649000659373,"GB2-03":38.39143751674923,"GB2-04":25.436526819126385,"GB2-05":59.862626312371006,"GB2-06":85.33771358831747,"GB2-07":46.18505938257291,"GB2-08":43.322487279449035},"medium":{"GB2-01":19.00156075859134,"GB2-02":20.930379612708386,"GB2-03":22.83228761321237,"GB2-04":67.80482331562605,"GB2-05":34.1121056070885,"GB2-06":45.54670444463535,"GB2-07":21.796920631650735,"GB2-08":37.057895275491454},"none":{"GB2-01":33.31582472626836,"GB2-02":62.474340824695595,"GB2-03":54.39714818290744,"GB2-04":54.332138920561675,"GB2-05":23.33209339064194,"GB2-06":70.05098233198491,"GB2-07":34.03557159987359,"GB2-08":23.82132846548862}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.987881929724644,"medium":28.312003923841633,"none":37.484279530579684},"reasoning_agg":{"highest":{"max":43.322487279449035,"mean":41.987881929724644,"min":43.322487279449035},"medium":{"max":45.54670444463535,"mean":28.312003923841633,"min":19.00156075859134},"none":{"max":62.474340824695595,"mean":37.484279530579684,"min":23.821328465488616}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":62.474340824695595,"expected_score":33.65890407773062,"reasoning_variance":13.67587800588301,"reliability_score":60.28952409979728,"uncertainty_avg":39.71047590020272,"uncertainty_penalty":-2.2691510503180368},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":43.322487279449035,"expected_score":36.89881297783175,"reliability_score":59.334505432851614,"uncertainty_avg":40.665494567148386,"uncertainty_penalty":-5.089068951892891},"medium":{"ceiling_score":45.54670444463535,"expected_score":28.77942025976696,"reliability_score":58.2656580277582,"uncertainty_avg":41.7343419722418,"uncertainty_penalty":0.4674163359253285},"none":{"ceiling_score":62.474340824695595,"expected_score":35.298478995593165,"reliability_score":63.268408838782044,"uncertainty_avg":36.731591161217956,"uncertainty_penalty":-2.1858005349865195}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.341716425,"mean":0.30867194062500003,"median":0.31836633750000004,"min":0.2745495,"recorded_attempt_count":33,"run_count":16,"total":4.9387510500000005},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.25698975,"mean":0.172479834375,"median":0.166217925,"min":0.10864875,"recorded_attempt_count":29,"run_count":16,"total":2.75967735},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","max":0.058529250000000005,"mean":0.03888066562499999,"median":0.038104875,"min":0.029012250000000003,"recorded_attempt_count":20,"run_count":16,"total":0.62209065}},"codegen_cost_usd":{"admitted_cell_count":40,"cell_count":24,"cost_basis_counts":{"provider_reported":82},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.341716425,"mean":0.17334414687500002,"median":0.166217925,"min":0.029012250000000003,"recorded_attempt_count":82,"run_count":48,"total":8.320519050000001},"codegen_latency_ms":{"attempt_count":82,"max_ms":190231,"mean_ms":91741.70833333331,"min_ms":16474,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":33,"max_ms":190231,"mean_ms":162520.375,"min_ms":111427,"run_count":16},"medium":{"attempt_count":29,"max_ms":131703,"mean_ms":90173.1875,"min_ms":44747,"run_count":16},"none":{"attempt_count":20,"max_ms":46243,"mean_ms":22531.5625,"min_ms":16474,"run_count":16}},"codegen_output_tokens":{"attempt_count":82,"output_max":45822,"output_mean":20391.416666666668,"output_min":1873,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":33,"output_max":45822,"output_mean":37854.8125,"output_min":25990,"run_count":16},"medium":{"attempt_count":29,"output_max":31826,"output_mean":20126.3125,"output_min":8874,"run_count":16},"none":{"attempt_count":20,"output_max":6181,"output_mean":3193.125,"output_min":1873,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"medium":35.558510524709966},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":4,"first_pass_rate":0.25,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":12,"repaired_rate":0.75}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:26:38Z","match_totals_all":{"draws":65,"losses":65,"wins":90},"match_totals_tracks":{"medium":{"draws":65,"losses":65,"wins":90}},"model_slug":"google-gemini-3-6-flash","overall":{"max":58.957069881532234,"mean":35.558510524709966,"min":2.1097136915519967},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":10,"wins":20},"GB2-02":{"draws":20,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":10,"wins":8},"GB2-04":{"draws":20,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":15,"wins":21},"GB2-06":{"draws":4,"losses":9,"wins":21},"GB2-07":{"draws":0,"losses":11,"wins":13},"GB2-08":{"draws":13,"losses":6,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":10,"wins":20},"GB2-02":{"draws":20,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":10,"wins":8},"GB2-04":{"draws":20,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":15,"wins":21},"GB2-06":{"draws":4,"losses":9,"wins":21},"GB2-07":{"draws":0,"losses":11,"wins":13},"GB2-08":{"draws":13,"losses":6,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1539.9775743068467,"GB2-02":1497.5921244000888,"GB2-03":1482.9907326414416,"GB2-04":1492.7797816007724,"GB2-05":1556.3686201647674,"GB2-06":1594.994455451696,"GB2-07":1506.668052138977,"GB2-08":1472.7970267677204}},"per_game_tracks":{"medium":{"GB2-01":48.33133201493449,"GB2-02":2.1097136915519967,"GB2-03":28.635035156588028,"GB2-04":25.798956755166984,"GB2-05":49.762827771825826,"GB2-06":58.957069881532234,"GB2-07":49.456755083385794,"GB2-08":21.416393842694415}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.558510524709966},"reasoning_agg":{"medium":{"max":58.957069881532234,"mean":35.558510524709966,"min":2.1097136915519967}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":58.957069881532234},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":58.957069881532234,"expected_score":45.81992761983816,"reliability_score":13.5675286853984,"uncertainty_avg":86.4324713146016,"uncertainty_penalty":10.261417095128195}}},{"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":0.09705768,"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_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":25.80423262137526,"none":49.17715878863995},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:52:47Z","match_totals_all":{"draws":133,"losses":177,"wins":140},"match_totals_tracks":{"medium":{"draws":73,"losses":93,"wins":48},"none":{"draws":60,"losses":84,"wins":92}},"model_slug":"minimax-minimax-m3","overall":{"max":79.61413719157319,"mean":35.36076820191823,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":11,"losses":35,"wins":38},"GB2-02":{"draws":55,"losses":3,"wins":0},"GB2-03":{"draws":14,"losses":7,"wins":15},"GB2-04":{"draws":19,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":52,"wins":26},"GB2-06":{"draws":0,"losses":21,"wins":9},"GB2-07":{"draws":0,"losses":36,"wins":34},"GB2-08":{"draws":34,"losses":22,"wins":18}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":1,"losses":17,"wins":16},"GB2-02":{"draws":24,"losses":2,"wins":0},"GB2-04":{"draws":19,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":28,"wins":4},"GB2-06":{"draws":0,"losses":21,"wins":9},"GB2-07":{"draws":0,"losses":18,"wins":16},"GB2-08":{"draws":29,"losses":6,"wins":3}},"none":{"GB2-01":{"draws":10,"losses":18,"wins":22},"GB2-02":{"draws":31,"losses":1,"wins":0},"GB2-03":{"draws":14,"losses":7,"wins":15},"GB2-05":{"draws":0,"losses":24,"wins":22},"GB2-07":{"draws":0,"losses":18,"wins":18},"GB2-08":{"draws":5,"losses":16,"wins":15}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1457.114416527839,"GB2-02":1466.9920532086492,"GB2-04":1483.854990578349,"GB2-05":1264.52824593137,"GB2-06":1335.5935473400814,"GB2-07":1535.1848606132364,"GB2-08":1465.538411105615},"none":{"GB2-01":1525.112314307578,"GB2-02":1478.537675568277,"GB2-03":1552.4562739272724,"GB2-05":1520.1005285778606,"GB2-07":1429.720675277115,"GB2-08":1518.8870364720128}},"per_game_tracks":{"medium":{"GB2-01":39.9064814459528,"GB2-02":9.435912482100369,"GB2-04":30.506939558455247,"GB2-05":0.0,"GB2-06":4.59927656381455,"GB2-07":63.90308784590045,"GB2-08":32.27793045340338},"none":{"GB2-01":51.4965044780349,"GB2-02":53.89281199401509,"GB2-03":79.61413719157319,"GB2-05":50.833251905571835,"GB2-07":29.517244738259865,"GB2-08":29.709002424384796}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.95703347829262,"none":45.76450292554386},"reasoning_agg":{"medium":{"max":63.90308784590045,"mean":24.95703347829262,"min":0.0},"none":{"max":79.61413719157319,"mean":45.76450292554386,"min":29.517244738259865}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":79.61413719157319,"reasoning_variance":20.80746944725124},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.90308784590045,"expected_score":23.150799494678886,"reliability_score":53.5685147396547,"uncertainty_avg":46.4314852603453,"uncertainty_penalty":-1.8062339836137333},"none":{"ceiling_score":79.61413719157319,"expected_score":41.362124272922486,"reliability_score":64.3193651856279,"uncertainty_avg":35.680634814372105,"uncertainty_penalty":-4.402378652621373}}},{"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_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":222264.07142857145,"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":41.263640734617546,"none":36.09408877823682},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:24:44Z","match_totals_all":{"draws":89,"losses":149,"wins":116},"match_totals_tracks":{"medium":{"draws":24,"losses":60,"wins":46},"none":{"draws":65,"losses":89,"wins":70}},"model_slug":"google-gemma-4-31b-it","overall":{"max":68.5453219404693,"mean":35.30295002484483,"min":9.709883647751884},"per_game_match_totals_all":{"GB2-01":{"draws":11,"losses":11,"wins":16},"GB2-04":{"draws":48,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":43,"wins":31},"GB2-06":{"draws":0,"losses":42,"wins":26},"GB2-07":{"draws":0,"losses":41,"wins":37},"GB2-08":{"draws":30,"losses":7,"wins":1}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":24,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":18,"wins":14},"GB2-06":{"draws":0,"losses":21,"wins":9},"GB2-07":{"draws":0,"losses":17,"wins":19}},"none":{"GB2-01":{"draws":11,"losses":11,"wins":16},"GB2-04":{"draws":24,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":25,"wins":17},"GB2-06":{"draws":0,"losses":21,"wins":17},"GB2-07":{"draws":0,"losses":24,"wins":18},"GB2-08":{"draws":30,"losses":7,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1516.6299865362912,"GB2-05":1490.740816162827,"GB2-06":1357.8619527446117,"GB2-07":1476.7398808653206},"none":{"GB2-01":1507.3231046273431,"GB2-04":1507.2609392463116,"GB2-05":1359.251477649065,"GB2-06":1448.9093319380038,"GB2-07":1413.0985567402486,"GB2-08":1453.467137194346}},"per_game_tracks":{"medium":{"GB2-04":61.08294261841314,"GB2-05":41.73808865570921,"GB2-06":9.709883647751884,"GB2-07":52.52364801659594},"none":{"GB2-01":46.835006135287266,"GB2-04":68.5453219404693,"GB2-05":22.74750450274291,"GB2-06":37.92206984165862,"GB2-07":27.150376324688956,"GB2-08":13.364253924573829}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.876331759555605,"none":34.72956829013406},"reasoning_agg":{"medium":{"max":61.08294261841314,"mean":35.876331759555605,"min":9.709883647751884},"none":{"max":68.5453219404693,"mean":34.72956829013406,"min":13.364253924573829}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":68.5453219404693,"reasoning_variance":1.1467634694215434},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":61.08294261841314,"expected_score":43.219735770436436,"reliability_score":57.230049844559005,"uncertainty_avg":42.769950155440995,"uncertainty_penalty":7.343404010880832},"none":{"ceiling_score":68.5453219404693,"expected_score":32.037894289134876,"reliability_score":62.26402568247118,"uncertainty_avg":37.73597431752882,"uncertainty_penalty":-2.6916740009991855}}},{"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":0.10247140625,"median":0.113468875,"min":0.061553,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.2156775,"mean":0.157461515625,"median":0.15705206249999998,"min":0.098579625,"recorded_attempt_count":33,"run_count":16,"total":2.51938425}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.2156775,"mean":0.12996646093750003,"median":0.12798825,"min":0.061553,"recorded_attempt_count":50,"run_count":24,"total":3.3391555},"codegen_latency_ms":{"attempt_count":50,"max_ms":1200477,"mean_ms":884695.875,"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":33,"max_ms":1200477,"mean_ms":915965.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":50,"output_max":131072,"output_mean":108502.5,"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":33,"output_max":131072,"output_mean":115220.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":23.857298172442643,"none":49.10099296635809},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:59:44Z","match_totals_all":{"draws":133,"losses":161,"wins":122},"match_totals_tracks":{"medium":{"draws":27,"losses":84,"wins":41},"none":{"draws":106,"losses":77,"wins":81}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":95.34897925067617,"mean":35.156732012982545,"min":0.0},"per_game_match_totals_all":{"GB2-02":{"draws":31,"losses":2,"wins":1},"GB2-03":{"draws":32,"losses":17,"wins":7},"GB2-04":{"draws":27,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":52,"wins":36},"GB2-06":{"draws":3,"losses":44,"wins":23},"GB2-07":{"draws":0,"losses":19,"wins":51},"GB2-08":{"draws":40,"losses":25,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":16,"losses":7,"wins":3},"GB2-05":{"draws":0,"losses":24,"wins":8},"GB2-06":{"draws":3,"losses":19,"wins":8},"GB2-07":{"draws":0,"losses":15,"wins":19},"GB2-08":{"draws":8,"losses":19,"wins":3}},"none":{"GB2-02":{"draws":31,"losses":2,"wins":1},"GB2-03":{"draws":16,"losses":10,"wins":4},"GB2-04":{"draws":27,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":28,"wins":28},"GB2-06":{"draws":0,"losses":25,"wins":15},"GB2-07":{"draws":0,"losses":4,"wins":32},"GB2-08":{"draws":32,"losses":6,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1476.9584294800973,"GB2-05":1339.2808602259393,"GB2-06":1349.6013075721278,"GB2-07":1494.0446656983331,"GB2-08":1333.6665330223236},"none":{"GB2-02":1485.674894437184,"GB2-03":1414.1389203156275,"GB2-04":1499.570722181966,"GB2-05":1506.6035841331557,"GB2-06":1404.4673187823385,"GB2-07":1759.6472794687916,"GB2-08":1435.650264464338}},"per_game_tracks":{"medium":{"GB2-03":42.04924364747344,"GB2-05":13.792475101982172,"GB2-06":7.814062596829199,"GB2-07":55.630709515928395,"GB2-08":0.0},"none":{"GB2-02":61.2573739944604,"GB2-03":32.64156349853694,"GB2-04":67.15816675616314,"GB2-05":49.43633061856956,"GB2-06":29.07107453638765,"GB2-07":95.34897925067617,"GB2-08":8.793462109712836}},"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":21.212471059606987,"none":49.1009929663581},"reasoning_agg":{"medium":{"max":55.630709515928395,"mean":21.212471059606987,"min":0.0},"none":{"max":95.34897925067617,"mean":49.1009929663581,"min":8.793462109712836}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":95.34897925067617,"reasoning_variance":27.888521906751112},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":55.630709515928395,"expected_score":21.703188380062887,"reliability_score":54.27307993151737,"uncertainty_avg":45.72692006848263,"uncertainty_penalty":0.4907173204559001},"none":{"ceiling_score":95.34897925067617,"expected_score":41.2145855663324,"reliability_score":62.22174330679943,"uncertainty_avg":37.77825669320057,"uncertainty_penalty":-7.886407400025696}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0056201515,"mean":0.0029446039375,"median":0.001956843,"min":0.001266762,"recorded_attempt_count":13,"run_count":9,"total":0.029176983},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0056201515,"mean":0.00210600034375,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":24,"run_count":17,"total":0.039316157},"codegen_latency_ms":{"attempt_count":24,"max_ms":257254,"mean_ms":73974.64705882352,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":257254,"mean_ms":112054.22222222222,"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":24,"output_max":22587,"output_mean":7143.882352941177,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":22587,"output_mean":11299.555555555557,"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":26.739160491480515,"none":52.80550738574448},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:48:11Z","match_totals_all":{"draws":171,"losses":195,"wins":142},"match_totals_tracks":{"highest":{"draws":51,"losses":128,"wins":73},"none":{"draws":120,"losses":67,"wins":69}},"model_slug":"tencent-hy3-preview","overall":{"max":83.18862534630858,"mean":35.015616292377246,"min":0.6743096635519508},"per_game":{"GB2-01":56.21371303529037,"GB2-02":0.6743096635519508,"GB2-04":6.644618738161239,"GB2-05":53.705445365017944,"GB2-06":12.480806195601517,"GB2-07":28.298825081998036,"GB2-08":29.15640536074257},"per_game_match_totals_all":{"GB2-01":{"draws":13,"losses":24,"wins":43},"GB2-02":{"draws":59,"losses":9,"wins":0},"GB2-03":{"draws":17,"losses":11,"wins":18},"GB2-04":{"draws":29,"losses":10,"wins":5},"GB2-05":{"draws":0,"losses":50,"wins":44},"GB2-06":{"draws":0,"losses":29,"wins":5},"GB2-07":{"draws":0,"losses":27,"wins":11},"GB2-08":{"draws":53,"losses":35,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":19,"wins":15},"GB2-02":{"draws":27,"losses":5,"wins":0},"GB2-04":{"draws":11,"losses":6,"wins":1},"GB2-05":{"draws":0,"losses":20,"wins":26},"GB2-06":{"draws":0,"losses":29,"wins":5},"GB2-07":{"draws":0,"losses":27,"wins":11},"GB2-08":{"draws":9,"losses":22,"wins":15}},"none":{"GB2-01":{"draws":9,"losses":5,"wins":28},"GB2-02":{"draws":32,"losses":4,"wins":0},"GB2-03":{"draws":17,"losses":11,"wins":18},"GB2-04":{"draws":18,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":30,"wins":18},"GB2-08":{"draws":44,"losses":13,"wins":1}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1520.780584199999,"GB2-02":1436.753013965462,"GB2-04":1434.684463471355,"GB2-05":1499.786786184171,"GB2-06":1253.9238079402735,"GB2-07":1324.637542538814,"GB2-08":1429.5149506200614},"none":{"GB2-01":1705.7059384966783,"GB2-02":1469.717991414446,"GB2-03":1506.6240970230965,"GB2-04":1490.3547180558796,"GB2-05":1480.4441921239832,"GB2-08":1440.1888165584944}},"per_game_tracks":{"highest":{"GB2-01":56.21371303529037,"GB2-02":0.6743096635519508,"GB2-04":6.644618738161239,"GB2-05":53.705445365017944,"GB2-06":12.480806195601517,"GB2-07":28.298825081998036,"GB2-08":29.15640536074257},"none":{"GB2-01":83.18862534630858,"GB2-02":49.91272418674253,"GB2-03":67.11676171014805,"GB2-04":59.356929451427035,"GB2-05":44.227928479050334,"GB2-08":13.03007514079034}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.890170824228864,"none":49.14106176052562},"reasoning_agg":{"highest":{"max":56.21371303529037,"mean":20.890170824228864,"min":0.6743096635519508},"none":{"max":83.18862534630858,"mean":49.14106176052562,"min":13.03007514079034}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":83.18862534630858,"reasoning_variance":28.25089093629676},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.21371303529037,"expected_score":21.885360892251306,"reliability_score":59.142104901576694,"uncertainty_avg":40.857895098423306,"uncertainty_penalty":0.9951900680224419},"none":{"ceiling_score":83.18862534630858,"expected_score":41.50001800760429,"reliability_score":66.39510894135846,"uncertainty_avg":33.60489105864154,"uncertainty_penalty":-7.641043752921334}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":46},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.02904086,"mean":0.020196066154166664,"median":0.0210709803,"min":0.0085050301,"recorded_attempt_count":46,"run_count":21,"total":0.426437947},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.004834030033333333,"mean":0.0027724950333333333,"median":0.002243999216666667,"min":0.00169122,"recorded_attempt_count":35,"run_count":24,"total":0.0665398808}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":16,"cost_basis_counts":{"provider_reported":81},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.02904086,"mean":0.01148428059375,"median":0.006669530066666667,"min":0.00169122,"recorded_attempt_count":81,"run_count":45,"total":0.4929778278},"codegen_latency_ms":{"attempt_count":81,"max_ms":2511116,"mean_ms":633843.1555555556,"min_ms":19112,"run_count":45},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":46,"max_ms":2511116,"mean_ms":1185686.761904762,"min_ms":46510,"run_count":21},"none":{"attempt_count":35,"max_ms":1132276,"mean_ms":150980.0,"min_ms":19112,"run_count":24}},"codegen_output_tokens":{"attempt_count":79,"output_max":146589,"output_mean":36322.91111111111,"output_min":1540,"run_count":45},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":46,"output_max":146589,"output_mean":73252.28571428571,"output_min":6076,"run_count":21},"none":{"attempt_count":33,"output_max":23326,"output_mean":4009.7083333333335,"output_min":1540,"run_count":24}},"display_name":"MiMo-V2.5","economics":{"medium":28.381144624300596,"none":47.88371757545439},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":21,"failed_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.047619047619047616,"infra_excluded_game_aliases":["GB2-03","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.2857142857142857,"model_code_failures":6,"repaired_admitted":14,"repaired_rate":0.6666666666666666},"baseline":{"admitted_plugins":17,"evaluated_cells":24,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"first_pass_admitted":12,"first_pass_rate":0.5,"model_code_failure_rate":0.2916666666666667,"model_code_failures":7,"repaired_admitted":5,"repaired_rate":0.20833333333333337}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:54:00Z","match_totals_all":{"draws":382,"losses":403,"wins":345},"match_totals_tracks":{"medium":{"draws":186,"losses":171,"wins":119},"none":{"draws":196,"losses":232,"wins":226}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":54.05316713549553,"mean":33.141999308828474,"min":17.212298642006523},"per_game_match_totals_all":{"GB2-01":{"draws":41,"losses":87,"wins":80},"GB2-02":{"draws":107,"losses":8,"wins":3},"GB2-03":{"draws":19,"losses":7,"wins":4},"GB2-04":{"draws":109,"losses":21,"wins":10},"GB2-05":{"draws":0,"losses":94,"wins":100},"GB2-06":{"draws":3,"losses":70,"wins":67},"GB2-07":{"draws":0,"losses":83,"wins":73},"GB2-08":{"draws":103,"losses":33,"wins":8}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":34,"wins":33},"GB2-02":{"draws":74,"losses":7,"wins":3},"GB2-04":{"draws":64,"losses":19,"wins":3},"GB2-05":{"draws":0,"losses":38,"wins":34},"GB2-06":{"draws":3,"losses":20,"wins":7},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":38,"losses":20,"wins":8}},"none":{"GB2-01":{"draws":34,"losses":53,"wins":47},"GB2-02":{"draws":33,"losses":1,"wins":0},"GB2-03":{"draws":19,"losses":7,"wins":4},"GB2-04":{"draws":45,"losses":2,"wins":7},"GB2-05":{"draws":0,"losses":56,"wins":66},"GB2-06":{"draws":0,"losses":50,"wins":60},"GB2-07":{"draws":0,"losses":50,"wins":42},"GB2-08":{"draws":65,"losses":13,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1494.368041364297,"GB2-02":1480.5254240044396,"GB2-04":1448.1948345927178,"GB2-05":1456.1819597490994,"GB2-06":1350.3704281952048,"GB2-07":1461.5844484411018,"GB2-08":1434.2157759662584},"none":{"GB2-01":1458.7557101809718,"GB2-02":1479.2351944215804,"GB2-03":1501.016743355424,"GB2-04":1522.4792223445877,"GB2-05":1530.143616938086,"GB2-06":1528.16180493796,"GB2-07":1462.6954148036589,"GB2-08":1424.8395520411118}},"per_game_tracks":{"medium":{"GB2-01":46.20378209857442,"GB2-02":18.518345064871987,"GB2-04":17.21229864200652,"GB2-05":36.062689180594305,"GB2-06":7.9905760576403635,"GB2-07":48.69776156624108,"GB2-08":23.98255976017552},"none":{"GB2-01":38.83097882413339,"GB2-02":56.07761467889641,"GB2-03":60.90249390340902,"GB2-04":77.5505643354487,"GB2-05":51.92787154128782,"GB2-06":54.05316713549553,"GB2-07":37.50410514129298,"GB2-08":6.222945043671273}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.000413908385976,"none":44.28358470927097},"reasoning_agg":{"medium":{"max":36.062689180594305,"mean":22.000413908385976,"min":17.212298642006523},"none":{"max":54.05316713549553,"mean":44.28358470927097,"min":38.83097882413339}},"reasoning_labels":{"highest":"Highest","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":54.05316713549553,"reasoning_variance":22.283170800884992},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.062689180594305,"expected_score":25.663327810047004,"reliability_score":56.47256483789287,"uncertainty_avg":43.52743516210713,"uncertainty_penalty":3.662913901661028},"none":{"ceiling_score":54.05316713549553,"expected_score":39.74507698172538,"reliability_score":61.86067630498743,"uncertainty_avg":38.13932369501257,"uncertainty_penalty":-4.538507727545586}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.213668025,"mean":0.180929025625,"median":0.1746528825,"min":0.16318875,"recorded_attempt_count":37,"run_count":16,"total":2.8948644100000003},"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.07934969,"mean":0.053583788125,"median":0.0553142075,"min":0.02549349,"recorded_attempt_count":37,"run_count":16,"total":0.85734061},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.053540475,"mean":0.026315053125,"median":0.024512850000000003,"min":0.012912625,"recorded_attempt_count":28,"run_count":16,"total":0.42104085}},"codegen_cost_usd":{"admitted_cell_count":28,"cell_count":24,"cost_basis_counts":{"provider_reported":102},"evidence_basis":"Provider-reported","failed_cell_count":20,"max":0.213668025,"mean":0.08694262229166666,"median":0.059337825,"min":0.012912625,"recorded_attempt_count":102,"run_count":48,"total":4.17324587},"codegen_latency_ms":{"attempt_count":102,"max_ms":555301,"mean_ms":164986.0625,"min_ms":16963,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":37,"max_ms":555301,"mean_ms":365326.75,"min_ms":229871,"run_count":16},"medium":{"attempt_count":37,"max_ms":241627,"mean_ms":93984.5625,"min_ms":43075,"run_count":16},"none":{"attempt_count":28,"max_ms":81344,"mean_ms":35646.875,"min_ms":16963,"run_count":16}},"codegen_output_tokens":{"attempt_count":102,"output_max":55341,"output_mean":17791.3125,"output_min":1372,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":37,"output_max":55341,"output_mean":40717.5625,"output_min":32915,"run_count":16},"medium":{"attempt_count":37,"output_max":17296,"output_mean":9330.3125,"output_min":3762,"run_count":16},"none":{"attempt_count":28,"output_max":6979,"output_mean":3326.0625,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"medium":24.214016401287545,"none":40.79356898262435},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-06","GB2-08"],"model_code_failure_rate":0.3125,"model_code_failures":5,"repaired_admitted":11,"repaired_rate":0.6875},"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}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-07-27T11:37:44Z","match_totals_all":{"draws":103,"losses":135,"wins":100},"match_totals_tracks":{"medium":{"draws":42,"losses":69,"wins":45},"none":{"draws":61,"losses":66,"wins":55}},"model_slug":"thinkingmachines-inkling","overall":{"max":64.60079357162957,"mean":32.88188735133476,"min":21.357771908138673},"per_game_match_totals_all":{"GB2-01":{"draws":22,"losses":26,"wins":14},"GB2-02":{"draws":31,"losses":2,"wins":1},"GB2-03":{"draws":13,"losses":4,"wins":11},"GB2-04":{"draws":36,"losses":5,"wins":3},"GB2-05":{"draws":0,"losses":45,"wins":21},"GB2-06":{"draws":0,"losses":16,"wins":12},"GB2-07":{"draws":0,"losses":25,"wins":25},"GB2-08":{"draws":1,"losses":12,"wins":13}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":6,"losses":12,"wins":10},"GB2-02":{"draws":12,"losses":2,"wins":0},"GB2-04":{"draws":24,"losses":2,"wins":2},"GB2-05":{"draws":0,"losses":21,"wins":11},"GB2-06":{"draws":0,"losses":7,"wins":1},"GB2-07":{"draws":0,"losses":15,"wins":19},"GB2-08":{"draws":0,"losses":10,"wins":2}},"none":{"GB2-01":{"draws":16,"losses":14,"wins":4},"GB2-02":{"draws":19,"losses":0,"wins":1},"GB2-03":{"draws":13,"losses":4,"wins":11},"GB2-04":{"draws":12,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":24,"wins":10},"GB2-06":{"draws":0,"losses":9,"wins":11},"GB2-07":{"draws":0,"losses":10,"wins":6},"GB2-08":{"draws":1,"losses":2,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1469.1703128263923,"GB2-02":1476.5165180773963,"GB2-04":1498.9426403953455,"GB2-05":1437.677306980349,"GB2-06":1409.0366112171782,"GB2-07":1537.9725594606507,"GB2-08":1421.3290397954354},"none":{"GB2-01":1414.3890401286033,"GB2-02":1512.8643469259814,"GB2-03":1544.5208275529408,"GB2-04":1488.3707120341571,"GB2-05":1405.2827932672362,"GB2-06":1516.3991431514291,"GB2-07":1453.608405387298,"GB2-08":1631.4149113794704}},"per_game_tracks":{"medium":{"GB2-01":36.07568953380168,"GB2-02":0.0,"GB2-04":29.535453241635565,"GB2-05":26.801153584609377,"GB2-06":7.342230766808901,"GB2-07":58.51966042429289,"GB2-08":11.223927257864382},"none":{"GB2-01":24.587483006708855,"GB2-02":67.30175645514417,"GB2-03":64.60079357162957,"GB2-04":21.357771908138673,"GB2-05":24.440841735328114,"GB2-06":47.060867446466304,"GB2-07":28.047289168020956,"GB2-08":48.951748569558106}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.35891071379612,"none":31.4048639888734},"reasoning_agg":{"medium":{"max":58.51966042429288,"mean":34.35891071379612,"min":26.801153584609374},"none":{"max":64.60079357162957,"mean":31.4048639888734,"min":21.357771908138673}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":64.60079357162957,"reasoning_variance":2.954046724922719},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":58.51966042429288,"expected_score":33.490264405389226,"reliability_score":13.058980078397909,"uncertainty_avg":86.94101992160209,"uncertainty_penalty":-0.8686463084068947},"none":{"ceiling_score":64.60079357162957,"expected_score":47.89840329092107,"reliability_score":21.3471161609655,"uncertainty_avg":78.6528838390345,"uncertainty_penalty":16.493539302047665}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.25293804045,"mean":0.19953128278325,"median":0.20662718916666667,"min":0.13279406625,"recorded_attempt_count":57,"run_count":27,"total":5.24138213703}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.25293804045,"mean":0.19953128278325,"median":0.20662718916666667,"min":0.13279406625,"recorded_attempt_count":57,"run_count":27,"total":5.24138213703},"codegen_latency_ms":{"attempt_count":57,"max_ms":3869582,"mean_ms":1358902.4074074074,"min_ms":364048,"run_count":27},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":57,"max_ms":3869582,"mean_ms":1358902.4074074074,"min_ms":364048,"run_count":27}},"codegen_output_tokens":{"attempt_count":57,"output_max":109372,"output_mean":63750.148148148146,"output_min":27968,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":109372,"output_mean":63750.148148148146,"output_min":27968,"run_count":27}},"display_name":"GLM-5.2","economics":{"highest":42.95394227119424},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"intensive":{"admitted_plugins":19,"evaluated_cells":27,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.037037037037037035,"infra_excluded_game_aliases":["GB2-03","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.2962962962962963,"model_code_failures":8,"repaired_admitted":18,"repaired_rate":0.6666666666666666}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-07-27T11:37:08Z","match_totals_all":{"draws":208,"losses":272,"wins":224},"match_totals_tracks":{"highest":{"draws":208,"losses":272,"wins":224}},"model_slug":"z-ai-glm-5-2","overall":{"max":55.51085521501481,"mean":31.583501662753424,"min":8.131943485676215},"per_game":{"GB2-01":50.480122474928095,"GB2-02":8.131943485676215,"GB2-03":46.49344565710838,"GB2-04":26.210182281089224,"GB2-05":45.38065817286552,"GB2-06":82.51331768806509,"GB2-07":55.51085521501481,"GB2-08":28.91101319480657},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":20,"wins":18},"GB2-02":{"draws":82,"losses":17,"wins":5},"GB2-03":{"draws":14,"losses":15,"wins":11},"GB2-04":{"draws":39,"losses":18,"wins":13},"GB2-05":{"draws":0,"losses":76,"wins":58},"GB2-06":{"draws":3,"losses":12,"wins":21},"GB2-07":{"draws":0,"losses":67,"wins":73},"GB2-08":{"draws":42,"losses":47,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":28,"losses":20,"wins":18},"GB2-02":{"draws":82,"losses":17,"wins":5},"GB2-03":{"draws":14,"losses":15,"wins":11},"GB2-04":{"draws":39,"losses":18,"wins":13},"GB2-05":{"draws":0,"losses":76,"wins":58},"GB2-06":{"draws":3,"losses":12,"wins":21},"GB2-07":{"draws":0,"losses":67,"wins":73},"GB2-08":{"draws":42,"losses":47,"wins":25}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1495.6184301506669,"GB2-02":1457.2492766448477,"GB2-03":1474.149296914641,"GB2-04":1480.460269447029,"GB2-05":1449.8903622442135,"GB2-06":1634.2238790629876,"GB2-07":1488.938022917073,"GB2-08":1433.7596844115794}},"per_game_tracks":{"highest":{"GB2-01":50.480122474928095,"GB2-02":8.131943485676215,"GB2-03":46.49344565710838,"GB2-04":26.210182281089224,"GB2-05":45.38065817286552,"GB2-06":82.51331768806509,"GB2-07":55.51085521501481,"GB2-08":28.91101319480657}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.583501662753424},"reasoning_agg":{"highest":{"max":55.51085521501481,"mean":31.583501662753424,"min":8.131943485676215}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":55.51085521501481},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.51085521501481,"expected_score":37.77794675167457,"reliability_score":59.565916988547585,"uncertainty_avg":40.434083011452415,"uncertainty_penalty":6.194445088921146}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.08193244999999999,"mean":0.05495368125,"median":0.056941025,"min":0.02174195,"recorded_attempt_count":18,"run_count":8,"total":0.43962945},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.0371769625,"median":0.029592175,"min":0.02387735,"recorded_attempt_count":17,"run_count":8,"total":0.2974157},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03772852,"mean":0.024905897500000003,"median":0.0260953,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":55},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.08193244999999999,"mean":0.03901218041666666,"median":0.03030545,"min":0.00984735,"recorded_attempt_count":55,"run_count":24,"total":0.9362923300000002},"codegen_latency_ms":{"attempt_count":55,"max_ms":388984,"mean_ms":191923.16666666663,"min_ms":73907,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":388984,"mean_ms":256781.125,"min_ms":132388,"run_count":8},"medium":{"attempt_count":17,"max_ms":302393,"mean_ms":191196.875,"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":55,"output_max":67551,"output_mean":30962.125,"output_min":6729,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":67551,"output_mean":44594.375,"output_min":16213,"run_count":8},"medium":{"attempt_count":17,"output_max":59186,"output_mean":29392.75,"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":32.76551006310001,"highest":26.35982863065856,"medium":35.58679555992142,"none":42.51427055803178},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"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},"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":"2026-07-27T11:46:13Z","match_totals_all":{"draws":157,"losses":271,"wins":160},"match_totals_tracks":{"highest":{"draws":29,"losses":117,"wins":42},"medium":{"draws":53,"losses":42,"wins":31},"none":{"draws":75,"losses":112,"wins":87}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":79.92521571615971,"mean":31.49361001016307,"min":1.0465554861299626},"per_game":{"GB2-01":3.9398082634195895,"GB2-05":46.45789692253995,"GB2-06":33.58154323586737,"GB2-07":19.50303459333689,"GB2-08":28.316860138128988},"per_game_all":{"GB2-05":41.65336743711146,"GB2-06":23.877652689088553},"per_game_match_totals_all":{"GB2-01":{"draws":14,"losses":53,"wins":21},"GB2-02":{"draws":25,"losses":2,"wins":1},"GB2-03":{"draws":21,"losses":10,"wins":9},"GB2-04":{"draws":40,"losses":5,"wins":11},"GB2-05":{"draws":0,"losses":60,"wins":52},"GB2-06":{"draws":1,"losses":66,"wins":33},"GB2-07":{"draws":0,"losses":54,"wins":30},"GB2-08":{"draws":56,"losses":21,"wins":3}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":28,"wins":3},"GB2-05":{"draws":0,"losses":22,"wins":16},"GB2-06":{"draws":0,"losses":24,"wins":12},"GB2-07":{"draws":0,"losses":30,"wins":8},"GB2-08":{"draws":28,"losses":13,"wins":3}},"medium":{"GB2-02":{"draws":25,"losses":2,"wins":1},"GB2-04":{"draws":27,"losses":2,"wins":3},"GB2-05":{"draws":0,"losses":17,"wins":19},"GB2-06":{"draws":1,"losses":21,"wins":8}},"none":{"GB2-01":{"draws":13,"losses":25,"wins":18},"GB2-03":{"draws":21,"losses":10,"wins":9},"GB2-04":{"draws":13,"losses":3,"wins":8},"GB2-05":{"draws":0,"losses":21,"wins":17},"GB2-06":{"draws":0,"losses":21,"wins":13},"GB2-07":{"draws":0,"losses":24,"wins":22},"GB2-08":{"draws":28,"losses":8,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1464.0510917518425,"GB2-06":1376.7838925716496},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1255.2843871872406,"GB2-05":1461.011643257222,"GB2-06":1367.213385956214,"GB2-07":1269.6829258604,"GB2-08":1425.8006075070234},"medium":{"GB2-02":1494.0712950505915,"GB2-04":1521.4129425895555,"GB2-05":1481.8693990249562,"GB2-06":1365.0568095133358},"none":{"GB2-01":1483.9524775947305,"GB2-03":1521.319036264691,"GB2-04":1531.2193865030604,"GB2-05":1449.2722329733497,"GB2-06":1398.0814822453988,"GB2-07":1460.211606613225,"GB2-08":1407.1612808667935}},"per_game_tracks":{"highest":{"GB2-01":3.9398082634195895,"GB2-05":46.45789692253995,"GB2-06":33.58154323586737,"GB2-07":19.50303459333689,"GB2-08":28.316860138128988},"medium":{"GB2-02":26.18770564068995,"GB2-04":63.98281410397966,"GB2-05":40.81555661997909,"GB2-06":11.361105875036971},"none":{"GB2-01":44.61506302295249,"GB2-03":70.5555964752065,"GB2-04":79.92521571615971,"GB2-05":37.68664876881536,"GB2-06":26.690308956361317,"GB2-07":37.08050548059713,"GB2-08":1.0465554861299626}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.437570253027303,"medium":29.92480881670472,"none":41.118450960757194},"reasoning_agg":{"highest":{"max":46.45789692253995,"mean":23.437570253027303,"min":3.9398082634195895},"medium":{"max":63.98281410397966,"mean":29.92480881670472,"min":11.361105875036971},"none":{"max":79.92521571615971,"mean":41.118450960757194,"min":1.0465554861299626}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":79.92521571615971,"expected_score":34.26334700248412,"reasoning_variance":17.68088070772989,"reliability_score":60.60913040055274,"uncertainty_avg":39.39086959944726,"uncertainty_penalty":2.7697369923210466},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":46.45789692253995,"expected_score":20.64103458180999,"reliability_score":62.969585062878465,"uncertainty_avg":37.030414937121535,"uncertainty_penalty":-2.7965356712173133},"medium":{"ceiling_score":63.98281410397966,"expected_score":38.17506331653006,"reliability_score":55.77783956688975,"uncertainty_avg":44.22216043311025,"uncertainty_penalty":8.250254499825338},"none":{"ceiling_score":79.92521571615971,"expected_score":39.64225583044195,"reliability_score":63.17500134648909,"uncertainty_avg":36.82499865351091,"uncertainty_penalty":-1.4761951303152472}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.015971877,"mean":0.00979196948,"median":0.009500477,"min":0.003562685,"recorded_attempt_count":26,"run_count":15,"total":0.14255357568000002},"none":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0027823742,"mean":0.0022230800541666665,"median":0.002112839,"min":0.001825724,"recorded_attempt_count":34,"run_count":24,"total":0.05335392129999999}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":16,"cost_basis_counts":{"provider_reported":60},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.015971877,"mean":0.006007524767083333,"median":0.0031725295999999997,"min":0.001825724,"recorded_attempt_count":60,"run_count":39,"total":0.19590749698},"codegen_latency_ms":{"attempt_count":60,"max_ms":1394682,"mean_ms":253119.97435897432,"min_ms":18361,"run_count":39},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":26,"max_ms":1394682,"mean_ms":546872.0,"min_ms":61403,"run_count":15},"none":{"attempt_count":34,"max_ms":161045,"mean_ms":69524.95833333333,"min_ms":18361,"run_count":24}},"codegen_output_tokens":{"attempt_count":60,"output_max":82048,"output_mean":14181.94871794872,"output_min":1698,"run_count":39},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":26,"output_max":82048,"output_mean":31146.866666666665,"output_min":4091,"run_count":15},"none":{"attempt_count":34,"output_max":7189,"output_mean":3578.875,"output_min":1698,"run_count":24}},"display_name":"DeepSeek V4 Flash","economics":{"highest":27.58940988501003,"none":42.69203208177206},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":19,"evaluated_cells":24,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-06"],"first_pass_admitted":14,"first_pass_rate":0.5833333333333334,"model_code_failure_rate":0.20833333333333337,"model_code_failures":5,"repaired_admitted":5,"repaired_rate":0.20833333333333337},"intensive":{"admitted_plugins":11,"evaluated_cells":15,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3333333333333333,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.26666666666666666,"model_code_failures":4,"repaired_admitted":6,"repaired_rate":0.4}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":402,"losses":479,"wins":293},"match_totals_tracks":{"highest":{"draws":94,"losses":208,"wins":104},"none":{"draws":308,"losses":271,"wins":189}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":54.69977007923055,"mean":29.640803246120996,"min":8.965164241668603},"per_game":{"GB2-01":36.8592483535278,"GB2-02":10.460999311305802,"GB2-05":26.853525961024484,"GB2-06":8.965164241668603,"GB2-07":52.70367499036416,"GB2-08":29.693846452169353},"per_game_match_totals_all":{"GB2-01":{"draws":33,"losses":48,"wins":37},"GB2-02":{"draws":122,"losses":8,"wins":4},"GB2-03":{"draws":24,"losses":24,"wins":22},"GB2-04":{"draws":86,"losses":8,"wins":2},"GB2-05":{"draws":0,"losses":139,"wins":83},"GB2-06":{"draws":0,"losses":109,"wins":35},"GB2-07":{"draws":0,"losses":113,"wins":101},"GB2-08":{"draws":137,"losses":30,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":32,"wins":21},"GB2-02":{"draws":54,"losses":8,"wins":4},"GB2-05":{"draws":0,"losses":59,"wins":29},"GB2-06":{"draws":0,"losses":62,"wins":10},"GB2-07":{"draws":0,"losses":39,"wins":37},"GB2-08":{"draws":27,"losses":8,"wins":3}},"none":{"GB2-01":{"draws":20,"losses":16,"wins":16},"GB2-02":{"draws":68,"losses":0,"wins":0},"GB2-03":{"draws":24,"losses":24,"wins":22},"GB2-04":{"draws":86,"losses":8,"wins":2},"GB2-05":{"draws":0,"losses":80,"wins":54},"GB2-06":{"draws":0,"losses":47,"wins":25},"GB2-07":{"draws":0,"losses":74,"wins":64},"GB2-08":{"draws":110,"losses":22,"wins":6}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1424.9848690942515,"GB2-02":1465.773715369278,"GB2-05":1336.673630388395,"GB2-06":1232.8869371950857,"GB2-07":1477.1149319829356,"GB2-08":1438.4189706552147},"none":{"GB2-01":1492.673476147228,"GB2-02":1501.299210615165,"GB2-03":1485.6576677355238,"GB2-04":1476.7720305005123,"GB2-05":1457.4189954750702,"GB2-06":1362.5691088660114,"GB2-07":1467.0479404185153,"GB2-08":1441.7128213768312}},"per_game_tracks":{"highest":{"GB2-01":36.8592483535278,"GB2-02":10.460999311305802,"GB2-05":26.853525961024484,"GB2-06":8.965164241668603,"GB2-07":52.70367499036416,"GB2-08":29.693846452169353},"none":{"GB2-01":45.83471506675062,"GB2-02":73.75800877437129,"GB2-03":57.43069486887003,"GB2-04":54.69977007923054,"GB2-05":39.90961523070116,"GB2-06":19.739319069100688,"GB2-07":38.3714035957878,"GB2-08":11.79272996936442}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.14151119888839,"none":34.140095293353596},"reasoning_agg":{"highest":{"max":52.70367499036416,"mean":25.14151119888839,"min":8.965164241668603},"none":{"max":54.69977007923055,"mean":34.140095293353596,"min":11.792729969364421}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":54.69977007923055,"reasoning_variance":8.998584094465205},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.70367499036416,"expected_score":22.545952843187774,"reliability_score":62.26317642326027,"uncertainty_avg":37.73682357673973,"uncertainty_penalty":-2.595558355700618},"none":{"ceiling_score":54.69977007923055,"expected_score":34.233564372679666,"reliability_score":65.01348533865585,"uncertainty_avg":34.986514661344145,"uncertainty_penalty":0.09346907932606996}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.00855959175,"median":0.005979701,"min":0.00271606,"recorded_attempt_count":18,"run_count":8,"total":0.068476734},"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":0.001130258,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","max":0.0032939400000000004,"mean":0.0016413085,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":24,"cost_basis_counts":{"provider_reported":47},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.01660212,"mean":0.004222185916666667,"median":0.0025298300000000003,"min":0.00045831,"recorded_attempt_count":47,"run_count":24,"total":0.10133246200000004},"codegen_latency_ms":{"attempt_count":47,"max_ms":622759,"mean_ms":224913.25,"min_ms":19833,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":622759,"mean_ms":459174.25,"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":47,"output_max":43929,"output_mean":12093.125,"output_min":1331,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":43929,"output_mean":27685.0,"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":30.89431132465674,"highest":29.894449942717813,"medium":26.38652181511472,"none":36.03113031491113},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":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},"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":"2026-07-27T11:52:32Z","match_totals_all":{"draws":284,"losses":247,"wins":157},"match_totals_tracks":{"highest":{"draws":83,"losses":71,"wins":48},"medium":{"draws":88,"losses":70,"wins":40},"none":{"draws":113,"losses":106,"wins":69}},"model_slug":"openai-gpt-oss-120b","overall":{"max":72.33288843526658,"mean":29.377225931426725,"min":4.749259728296156},"per_game":{"GB2-02":4.749259728296156,"GB2-04":19.61494188087154,"GB2-06":67.57825172001401,"GB2-07":26.97606284751384,"GB2-08":30.553733536893517},"per_game_all":{"GB2-02":35.637891649988084,"GB2-04":24.477158571272557,"GB2-06":39.23440412866345,"GB2-08":24.22779094870286},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":29,"wins":21},"GB2-02":{"draws":95,"losses":6,"wins":1},"GB2-03":{"draws":33,"losses":11,"wins":6},"GB2-04":{"draws":53,"losses":21,"wins":6},"GB2-05":{"draws":0,"losses":36,"wins":34},"GB2-06":{"draws":3,"losses":74,"wins":55},"GB2-07":{"draws":0,"losses":50,"wins":24},"GB2-08":{"draws":82,"losses":20,"wins":10}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":28,"losses":4,"wins":0},"GB2-04":{"draws":21,"losses":9,"wins":4},"GB2-06":{"draws":2,"losses":24,"wins":28},"GB2-07":{"draws":0,"losses":27,"wins":11},"GB2-08":{"draws":32,"losses":7,"wins":5}},"medium":{"GB2-01":{"draws":7,"losses":14,"wins":9},"GB2-02":{"draws":28,"losses":1,"wins":1},"GB2-03":{"draws":12,"losses":6,"wins":2},"GB2-04":{"draws":21,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":17,"wins":15},"GB2-06":{"draws":0,"losses":21,"wins":9},"GB2-08":{"draws":20,"losses":9,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":15,"wins":12},"GB2-02":{"draws":39,"losses":1,"wins":0},"GB2-03":{"draws":21,"losses":5,"wins":4},"GB2-04":{"draws":11,"losses":10,"wins":1},"GB2-05":{"draws":0,"losses":19,"wins":19},"GB2-06":{"draws":1,"losses":29,"wins":18},"GB2-07":{"draws":0,"losses":23,"wins":13},"GB2-08":{"draws":30,"losses":4,"wins":2}}},"per_game_raw_elo_all":{"GB2-02":1480.557224291172,"GB2-04":1454.4561744820778,"GB2-06":1451.5255410489399,"GB2-08":1450.600912390418},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1449.2568338626152,"GB2-04":1456.8705310684709,"GB2-06":1540.902731441204,"GB2-07":1316.3731470138785,"GB2-08":1439.1140856424922},"medium":{"GB2-01":1421.1004908587392,"GB2-02":1498.1132233171525,"GB2-03":1453.8163406856963,"GB2-04":1481.10994549556,"GB2-05":1391.6761237621845,"GB2-06":1342.2444321636067,"GB2-08":1471.9940163629956},"none":{"GB2-01":1414.307963840611,"GB2-02":1494.301615693748,"GB2-03":1477.898902263975,"GB2-04":1425.3880468822022,"GB2-05":1437.1618665866622,"GB2-06":1471.429459542009,"GB2-07":1395.4286950057094,"GB2-08":1440.6946351657664}},"per_game_tracks":{"highest":{"GB2-02":4.749259728296156,"GB2-04":19.61494188087154,"GB2-06":67.57825172001401,"GB2-07":26.97606284751384,"GB2-08":30.553733536893517},"medium":{"GB2-01":33.564556742996984,"GB2-02":29.83152678640151,"GB2-03":25.982948884274855,"GB2-04":33.26078844607971,"GB2-05":23.459834225206247,"GB2-06":6.125657033187752,"GB2-08":32.48034058765597},"none":{"GB2-01":30.04823822167929,"GB2-02":72.33288843526658,"GB2-03":53.3823734015744,"GB2-04":20.55574538686643,"GB2-05":35.60638254796547,"GB2-06":43.99930363278859,"GB2-07":22.674812171589178,"GB2-08":9.649298721559102}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.58034240378717,"medium":25.520205075581885,"none":36.031130314911124},"reasoning_agg":{"highest":{"max":67.57825172001401,"mean":26.58034240378717,"min":4.749259728296156},"medium":{"max":33.564556742996984,"mean":25.520205075581885,"min":6.125657033187752},"none":{"max":72.33288843526658,"mean":36.031130314911124,"min":9.649298721559102}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":72.33288843526658,"expected_score":22.4045463532914,"reasoning_variance":10.51092523932924,"reliability_score":59.07282316618899,"uncertainty_avg":40.92717683381101,"uncertainty_penalty":-6.972679578135324},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.57825172001401,"expected_score":23.412738564969104,"reliability_score":65.03521683008773,"uncertainty_avg":34.96478316991227,"uncertainty_penalty":-3.167603838818067},"medium":{"ceiling_score":33.564556742996984,"expected_score":22.87925799853638,"reliability_score":50.52220655516337,"uncertainty_avg":49.47779344483663,"uncertainty_penalty":-2.640947077045503},"none":{"ceiling_score":72.33288843526658,"expected_score":26.492855756022163,"reliability_score":60.237193559344526,"uncertainty_avg":39.762806440655474,"uncertainty_penalty":-9.538274558888961}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":34,"run_count":15,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":29,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"provider_reported":63},"evidence_basis":"Provider-reported","failed_cell_count":14,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":63,"run_count":31,"total":0.0},"codegen_latency_ms":{"attempt_count":64,"max_ms":235183,"mean_ms":106145.67741935483,"min_ms":16415,"run_count":31},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":235183,"mean_ms":183971.06666666668,"min_ms":161500,"run_count":15},"none":{"attempt_count":29,"max_ms":62224,"mean_ms":33184.375,"min_ms":16415,"run_count":16}},"codegen_output_tokens":{"attempt_count":63,"output_max":52074,"output_mean":22315.225806451617,"output_min":1505,"run_count":31},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":34,"output_max":52074,"output_mean":40986.933333333334,"output_min":20000,"run_count":15},"none":{"attempt_count":29,"output_max":10355,"output_mean":4810.5,"output_min":1505,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"none":32.59084674857204},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"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":"2026-07-27T11:37:35Z","match_totals_all":{"draws":74,"losses":53,"wins":35},"match_totals_tracks":{"none":{"draws":74,"losses":53,"wins":35}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":46.87151441246823,"mean":27.503418933579056,"min":15.744626204273619},"per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":8,"wins":14},"GB2-02":{"draws":13,"losses":1,"wins":0},"GB2-03":{"draws":8,"losses":15,"wins":7},"GB2-04":{"draws":7,"losses":0,"wins":1},"GB2-06":{"draws":0,"losses":25,"wins":11},"GB2-08":{"draws":34,"losses":4,"wins":2}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":12,"losses":8,"wins":14},"GB2-02":{"draws":13,"losses":1,"wins":0},"GB2-03":{"draws":8,"losses":15,"wins":7},"GB2-04":{"draws":7,"losses":0,"wins":1},"GB2-06":{"draws":0,"losses":25,"wins":11},"GB2-08":{"draws":34,"losses":4,"wins":2}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1537.8644065106223,"GB2-02":1485.0090048306092,"GB2-03":1457.1319264772342,"GB2-04":1510.6904748219472,"GB2-06":1407.729727130636,"GB2-08":1486.280557989201}},"per_game_tracks":{"none":{"GB2-01":46.87151441246823,"GB2-02":32.03291644368013,"GB2-03":37.419570844397725,"GB2-04":39.78169164475862,"GB2-06":23.694760941853907,"GB2-08":15.74462620427362}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":27.503418933579052},"reasoning_agg":{"none":{"max":46.87151441246823,"mean":27.503418933579052,"min":15.744626204273619}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":46.87151441246823},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":46.87151441246823,"expected_score":38.214531466863626,"reliability_score":20.38144713110539,"uncertainty_avg":79.61855286889461,"uncertainty_penalty":10.711112533284574}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","max":0.04815395,"mean":0.0408814375,"median":0.040641,"min":0.0341807,"recorded_attempt_count":34,"run_count":16,"total":0.654103},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","max":0.03261155,"mean":0.02559155625,"median":0.02516155,"min":0.017927,"recorded_attempt_count":32,"run_count":16,"total":0.4094649},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0148808,"mean":0.0114004875,"median":0.01124825,"min":0.00845595,"recorded_attempt_count":23,"run_count":16,"total":0.1824078}},"codegen_cost_usd":{"admitted_cell_count":47,"cell_count":24,"cost_basis_counts":{"provider_reported":89},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.04815395,"mean":0.025957827083333333,"median":0.02516155,"min":0.00845595,"recorded_attempt_count":89,"run_count":48,"total":1.2459757000000002},"codegen_latency_ms":{"attempt_count":89,"max_ms":61871,"mean_ms":33706.5625,"min_ms":13028,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":34,"max_ms":61871,"mean_ms":50306.25,"min_ms":38302,"run_count":16},"medium":{"attempt_count":32,"max_ms":47168,"mean_ms":32849.5625,"min_ms":19840,"run_count":16},"none":{"attempt_count":23,"max_ms":28160,"mean_ms":17963.875,"min_ms":13028,"run_count":16}},"codegen_output_tokens":{"attempt_count":89,"output_max":18224,"output_mean":8477.208333333334,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":34,"output_max":18224,"output_mean":14154.25,"output_min":11410,"run_count":16},"medium":{"attempt_count":32,"output_max":11113,"output_mean":8141.625,"output_min":4066,"run_count":16},"none":{"attempt_count":23,"output_max":4635,"output_mean":3135.75,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"medium":26.330732337583687},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-3.5-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":1,"first_pass_rate":0.0625,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":15,"repaired_rate":0.9375}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-07-27T11:23:13Z","match_totals_all":{"draws":65,"losses":92,"wins":59},"match_totals_tracks":{"medium":{"draws":65,"losses":92,"wins":59}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":39.49403324298903,"mean":26.330732337583687,"min":10.687874556687444},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":18,"wins":12},"GB2-02":{"draws":27,"losses":2,"wins":1},"GB2-03":{"draws":5,"losses":8,"wins":5},"GB2-04":{"draws":25,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":18,"wins":14},"GB2-06":{"draws":0,"losses":21,"wins":7},"GB2-07":{"draws":0,"losses":18,"wins":16},"GB2-08":{"draws":8,"losses":2,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":18,"wins":12},"GB2-02":{"draws":27,"losses":2,"wins":1},"GB2-03":{"draws":5,"losses":8,"wins":5},"GB2-04":{"draws":25,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":18,"wins":14},"GB2-06":{"draws":0,"losses":21,"wins":7},"GB2-07":{"draws":0,"losses":18,"wins":16},"GB2-08":{"draws":8,"losses":2,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1487.797607810497,"GB2-02":1492.3846438451174,"GB2-03":1476.0585952217525,"GB2-04":1489.5515824662566,"GB2-05":1443.6773331615564,"GB2-06":1427.8052627685006,"GB2-07":1440.571672800479,"GB2-08":1500.3531847189795}},"per_game_tracks":{"medium":{"GB2-01":39.42463493773098,"GB2-02":10.687874556687444,"GB2-03":17.606411536810622,"GB2-04":28.063275475905023,"GB2-05":28.002062687545138,"GB2-06":17.8800999826387,"GB2-07":39.49403324298903,"GB2-08":29.48746628036255}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.330732337583687},"reasoning_agg":{"medium":{"max":39.49403324298903,"mean":26.330732337583687,"min":10.687874556687444}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":39.49403324298903},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":39.49403324298903,"expected_score":33.89952189092764,"reliability_score":15.743433252665994,"uncertainty_avg":84.256566747334,"uncertainty_penalty":7.568789553343951}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.039679950000000005,"mean":0.029276065625,"median":0.0306386,"min":0.01864685,"recorded_attempt_count":33,"run_count":16,"total":0.46841705000000006},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0445032,"mean":0.03204184375,"median":0.0312573,"min":0.0200767,"recorded_attempt_count":19,"run_count":9,"total":0.2854256}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0445032,"mean":0.030658954687500004,"median":0.0312573,"min":0.01864685,"recorded_attempt_count":52,"run_count":25,"total":0.7538426500000001},"codegen_latency_ms":{"attempt_count":52,"max_ms":622714,"mean_ms":82027.44,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":33,"max_ms":622714,"mean_ms":92202.3125,"min_ms":23604,"run_count":16},"medium":{"attempt_count":19,"max_ms":124322,"mean_ms":63938.77777777778,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":52,"output_max":14193,"output_mean":7210.36,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":33,"output_max":14193,"output_mean":7320.375,"output_min":2728,"run_count":16},"medium":{"attempt_count":19,"output_max":10495,"output_mean":7014.777777777777,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"highest":25.40674358485684,"medium":31.476566167387638},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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},"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":"2026-07-27T11:52:38Z","match_totals_all":{"draws":219,"losses":195,"wins":99},"match_totals_tracks":{"highest":{"draws":153,"losses":127,"wins":53},"medium":{"draws":66,"losses":68,"wins":46}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":55.15900110831977,"mean":23.140636190097048,"min":9.318161446085837},"per_game":{"GB2-01":22.59446859678085,"GB2-02":12.846512132570249,"GB2-04":17.33260631114399,"GB2-05":24.034455633974915,"GB2-06":46.32724590921991,"GB2-08":29.305172925451135},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":37,"wins":24},"GB2-02":{"draws":90,"losses":12,"wins":2},"GB2-04":{"draws":26,"losses":5,"wins":1},"GB2-05":{"draws":0,"losses":55,"wins":21},"GB2-06":{"draws":5,"losses":36,"wins":30},"GB2-07":{"draws":0,"losses":27,"wins":9},"GB2-08":{"draws":83,"losses":23,"wins":12}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":7,"losses":20,"wins":5},"GB2-02":{"draws":62,"losses":10,"wins":2},"GB2-04":{"draws":26,"losses":5,"wins":1},"GB2-05":{"draws":0,"losses":55,"wins":21},"GB2-06":{"draws":2,"losses":19,"wins":14},"GB2-08":{"draws":56,"losses":18,"wins":10}},"medium":{"GB2-01":{"draws":8,"losses":17,"wins":19},"GB2-02":{"draws":28,"losses":2,"wins":0},"GB2-06":{"draws":3,"losses":17,"wins":16},"GB2-07":{"draws":0,"losses":27,"wins":9},"GB2-08":{"draws":27,"losses":5,"wins":2}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1352.021577319036,"GB2-02":1469.512786420403,"GB2-04":1450.734986094316,"GB2-05":1323.3921679507584,"GB2-06":1437.6711002822544,"GB2-08":1433.0538206061656},"medium":{"GB2-01":1545.9178791697766,"GB2-02":1467.277479313799,"GB2-06":1515.2683795787614,"GB2-07":1261.8703393618885,"GB2-08":1473.0393596669223}},"per_game_tracks":{"highest":{"GB2-01":22.59446859678085,"GB2-02":12.846512132570249,"GB2-04":17.33260631114399,"GB2-05":24.034455633974915,"GB2-06":46.32724590921991,"GB2-08":29.305172925451135},"medium":{"GB2-01":55.15900110831977,"GB2-02":12.486523784051508,"GB2-06":47.23065735165755,"GB2-07":9.318161446085837,"GB2-08":33.18848714682352}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.10629307257325,"medium":27.174979307620845},"reasoning_agg":{"highest":{"max":29.305172925451135,"mean":19.10629307257325,"min":12.846512132570247},"medium":{"max":55.15900110831977,"mean":27.174979307620845,"min":9.318161446085837}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":55.15900110831977,"reasoning_variance":8.068686235047593},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":29.305172925451135,"expected_score":19.192823866331455,"reliability_score":61.245749238924255,"uncertainty_avg":38.754250761075745,"uncertainty_penalty":0.08653079375820383},"medium":{"ceiling_score":55.15900110831977,"expected_score":27.11604227275702,"reliability_score":61.09946739168212,"uncertainty_avg":38.90053260831788,"uncertainty_penalty":-0.05893703486382407}}},{"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":29},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":29,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":44,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":44,"max_ms":905283,"mean_ms":194108.25,"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":29,"max_ms":62079,"mean_ms":36603.1875,"min_ms":21975,"run_count":16}},"codegen_output_tokens":{"attempt_count":44,"output_max":52275,"output_mean":12258.958333333334,"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":29,"output_max":6330,"output_mean":3335.5,"output_min":1733,"run_count":16}},"display_name":"North Mini Code","economics":{"medium":28.94568279276677,"none":17.31412596606637},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:52:47Z","match_totals_all":{"draws":121,"losses":181,"wins":88},"match_totals_tracks":{"medium":{"draws":48,"losses":77,"wins":51},"none":{"draws":73,"losses":104,"wins":37}},"model_slug":"cohere-north-mini-code","overall":{"max":56.46575348182567,"mean":21.33520178958176,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":41,"losses":35,"wins":8},"GB2-03":{"draws":11,"losses":8,"wins":3},"GB2-04":{"draws":12,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":16,"wins":22},"GB2-06":{"draws":1,"losses":23,"wins":6},"GB2-07":{"draws":0,"losses":79,"wins":45},"GB2-08":{"draws":56,"losses":16,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":11,"losses":8,"wins":3},"GB2-04":{"draws":12,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":16,"wins":22},"GB2-06":{"draws":1,"losses":23,"wins":6},"GB2-07":{"draws":0,"losses":18,"wins":18},"GB2-08":{"draws":24,"losses":8,"wins":0}},"none":{"GB2-01":{"draws":41,"losses":35,"wins":8},"GB2-07":{"draws":0,"losses":61,"wins":27},"GB2-08":{"draws":32,"losses":8,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1447.183071284368,"GB2-04":1478.6133297819465,"GB2-05":1499.7873290817167,"GB2-06":1315.5531581243893,"GB2-07":1496.3447611966587,"GB2-08":1433.1246964345382},"none":{"GB2-01":1355.698446909576,"GB2-07":1386.28480265296,"GB2-08":1436.7406344811243}},"per_game_tracks":{"medium":{"GB2-03":24.661168807432208,"GB2-04":24.613290244334937,"GB2-05":44.43676442158328,"GB2-06":0.0,"GB2-07":56.46575348182567,"GB2-08":23.497119801424535},"none":{"GB2-01":20.012603700473957,"GB2-07":22.07365930323166,"GB2-08":9.856114894493492}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.93699305697679,"none":15.733410522186734},"reasoning_agg":{"medium":{"max":56.46575348182567,"mean":26.93699305697679,"min":0.0},"none":{"max":22.07365930323166,"mean":15.733410522186734,"min":20.012603700473957}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":56.46575348182567,"reasoning_variance":11.203582534790055},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":56.46575348182567,"expected_score":28.81157508684824,"reliability_score":50.73831274828719,"uncertainty_avg":49.26168725171281,"uncertainty_penalty":1.8745820298714513},"none":{"ceiling_score":22.07365930323166,"expected_score":10.080400303964204,"reliability_score":68.05129182885223,"uncertainty_avg":31.948708171147775,"uncertainty_penalty":-5.65301021822253}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.0264053125,"median":0.022682375,"min":0.01946775,"recorded_attempt_count":18,"run_count":8,"total":0.2112425},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.00915140625,"median":0.00943475,"min":0.00402875,"recorded_attempt_count":16,"run_count":8,"total":0.07321125}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0422995,"mean":0.017778359375,"median":0.017199625,"min":0.00402875,"recorded_attempt_count":34,"run_count":16,"total":0.28445375},"codegen_latency_ms":{"attempt_count":34,"max_ms":98448,"mean_ms":41366.3125,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":98448,"mean_ms":60993.75,"min_ms":43206,"run_count":8},"medium":{"attempt_count":16,"max_ms":27929,"mean_ms":21738.875,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22966,"output_mean":8901.4375,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":22966,"output_mean":14376.25,"output_min":9966,"run_count":8},"medium":{"attempt_count":16,"output_max":5938,"output_mean":3426.625,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"highest":19.721081038400705,"medium":25.497787191605966},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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-3.1-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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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},"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":"2026-07-27T11:53:48Z","match_totals_all":{"draws":95,"losses":192,"wins":74},"match_totals_tracks":{"highest":{"draws":43,"losses":100,"wins":24},"medium":{"draws":52,"losses":92,"wins":50}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":43.3486882847466,"mean":20.631580417004145,"min":4.472300779672665},"per_game":{"GB2-04":10.70081970583965,"GB2-05":8.173473311910564,"GB2-06":14.264569800436952,"GB2-07":38.08567479511683,"GB2-08":27.380867578699544},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":6,"wins":5},"GB2-04":{"draws":31,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":58,"wins":20},"GB2-06":{"draws":0,"losses":49,"wins":16},"GB2-07":{"draws":0,"losses":55,"wins":17},"GB2-08":{"draws":43,"losses":20,"wins":15}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":14,"losses":4,"wins":0},"GB2-05":{"draws":0,"losses":34,"wins":4},"GB2-06":{"draws":0,"losses":30,"wins":5},"GB2-07":{"draws":0,"losses":26,"wins":12},"GB2-08":{"draws":29,"losses":6,"wins":3}},"medium":{"GB2-01":{"draws":21,"losses":6,"wins":5},"GB2-04":{"draws":17,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":24,"wins":16},"GB2-06":{"draws":0,"losses":19,"wins":11},"GB2-07":{"draws":0,"losses":29,"wins":5},"GB2-08":{"draws":14,"losses":14,"wins":12}}},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1449.176348909323,"GB2-05":1226.0484981314112,"GB2-06":1262.7117603855916,"GB2-07":1385.7841302351694,"GB2-08":1424.652526082737},"medium":{"GB2-01":1480.9762172263104,"GB2-04":1502.3477099979832,"GB2-05":1362.7819605792038,"GB2-06":1363.588591328709,"GB2-07":1239.6236487919457,"GB2-08":1478.7130163219108}},"per_game_tracks":{"highest":{"GB2-04":10.70081970583965,"GB2-05":8.173473311910564,"GB2-06":14.264569800436952,"GB2-07":38.08567479511683,"GB2-08":27.380867578699544},"medium":{"GB2-01":43.3486882847466,"GB2-04":39.0032724330916,"GB2-05":19.449988899220273,"GB2-06":11.024149271328271,"GB2-07":4.472300779672665,"GB2-08":35.68832348157636}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.534796177148497,"medium":23.728364656859792},"reasoning_agg":{"highest":{"max":38.08567479511683,"mean":17.534796177148497,"min":8.173473311910564},"medium":{"max":43.3486882847466,"mean":23.728364656859792,"min":4.472300779672665}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":43.3486882847466,"reasoning_variance":6.1935684797112955},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":38.08567479511683,"expected_score":13.868559618508806,"reliability_score":56.10331380475103,"uncertainty_avg":43.89668619524897,"uncertainty_penalty":-3.6662365586396906},"medium":{"ceiling_score":43.3486882847466,"expected_score":23.89695608771485,"reliability_score":55.043577785337504,"uncertainty_avg":44.956422214662496,"uncertainty_penalty":0.16859143085505934}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.33185775,"mean":0.18266821875,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":13,"run_count":9,"total":1.7932035000000002},"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":0.0429946875,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.34395749999999997}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":16,"cost_basis_counts":{"provider_reported":27},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.33185775,"mean":0.112831453125,"median":0.0747585,"min":0.0223935,"recorded_attempt_count":27,"run_count":17,"total":2.137160999999999},"codegen_latency_ms":{"attempt_count":27,"max_ms":776640,"mean_ms":204801.0588235294,"min_ms":28440,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":776640,"mean_ms":337673.77777777775,"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":27,"output_max":52664,"output_mean":14286.941176470587,"output_min":1452,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":52664,"output_mean":24216.444444444445,"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":8.12972026656631,"none":19.497599109748712},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","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":"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":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","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":"2026-07-27T11:52:31Z","match_totals_all":{"draws":45,"losses":204,"wins":58},"match_totals_tracks":{"highest":{"draws":4,"losses":123,"wins":15},"none":{"draws":41,"losses":81,"wins":43}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":42.18961139185141,"mean":11.51667499949597,"min":0.0},"per_game":{"GB2-01":11.384899189479697,"GB2-05":1.5935731413338652,"GB2-06":19.54040873545167,"GB2-07":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":10,"losses":50,"wins":11},"GB2-05":{"draws":0,"losses":63,"wins":27},"GB2-06":{"draws":2,"losses":50,"wins":20},"GB2-07":{"draws":0,"losses":38,"wins":0},"GB2-08":{"draws":33,"losses":3,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":24,"wins":4},"GB2-05":{"draws":0,"losses":34,"wins":4},"GB2-06":{"draws":0,"losses":27,"wins":7},"GB2-07":{"draws":0,"losses":38,"wins":0}},"none":{"GB2-01":{"draws":6,"losses":26,"wins":7},"GB2-05":{"draws":0,"losses":29,"wins":23},"GB2-06":{"draws":2,"losses":23,"wins":13},"GB2-08":{"draws":33,"losses":3,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1293.8922826724654,"GB2-05":1185.6656506732268,"GB2-06":1292.446587389948,"GB2-07":1147.831252434989},"none":{"GB2-01":1321.549235332169,"GB2-05":1466.3794030030658,"GB2-06":1316.4288158464587,"GB2-08":1449.0151829219694}},"per_game_tracks":{"highest":{"GB2-01":11.384899189479697,"GB2-05":1.5935731413338652,"GB2-06":19.54040873545167,"GB2-07":0.0},"none":{"GB2-01":13.453154928516817,"GB2-05":42.18961139185141,"GB2-06":10.563754125537807,"GB2-08":11.78387599308882}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":6.637888801550232,"none":16.39546119744171},"reasoning_agg":{"highest":{"max":19.54040873545167,"mean":6.637888801550232,"min":0.0},"none":{"max":42.18961139185141,"mean":16.39546119744171,"min":10.563754125537807}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":42.18961139185141,"reasoning_variance":9.757572395891476},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":19.54040873545167,"expected_score":4.942912105329908,"reliability_score":60.82939818605307,"uncertainty_avg":39.17060181394693,"uncertainty_penalty":-1.6949766962203237},"none":{"ceiling_score":42.18961139185141,"expected_score":16.45800250919232,"reliability_score":66.24980149155594,"uncertainty_avg":33.75019850844406,"uncertainty_penalty":0.06254131175061062}}}],"public_release_id":"gb2-20260727-16711ca582b2","results_cut_id":"gb2-20260727-16711ca582b2","snapshot_id":"20260727_120850","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-07-27 12:08 UTC","versus_totals_all":{"claude-fable-5":{"claude-opus-4-5":{"draws":1,"losses":2,"wins":11},"claude-opus-4-8":{"draws":1,"losses":8,"wins":9},"claude-opus-5":{"draws":8,"losses":11,"wins":13},"claude-sonnet-5":{"draws":6,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":14},"gpt-5.4":{"draws":4,"losses":9,"wins":11},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":26},"gpt-5.5":{"draws":5,"losses":10,"wins":7},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":16},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":14},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":15},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":5,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":6},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":13,"losses":16,"wins":41},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":15}},"claude-opus-4-5":{"claude-fable-5":{"draws":1,"losses":11,"wins":2},"claude-opus-4-8":{"draws":2,"losses":12,"wins":4},"claude-opus-5":{"draws":3,"losses":3,"wins":2},"claude-sonnet-5":{"draws":5,"losses":7,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":15},"deepseek/deepseek-v4-pro":{"draws":3,"losses":8,"wins":11},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":5},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":8,"losses":7,"wins":3},"gpt-5.4":{"draws":7,"losses":15,"wins":10},"gpt-5.4-mini":{"draws":20,"losses":15,"wins":23},"gpt-5.4-nano":{"draws":19,"losses":14,"wins":31},"gpt-5.5":{"draws":10,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":9,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":18,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":25,"losses":29,"wins":12},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":10},"o3":{"draws":7,"losses":10,"wins":9},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":10,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":11},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":22,"losses":44,"wins":18},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":16,"losses":7,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":10,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":1,"losses":9,"wins":8},"claude-opus-4-5":{"draws":2,"losses":4,"wins":12},"claude-opus-5":{"draws":2,"losses":7,"wins":5},"claude-sonnet-5":{"draws":7,"losses":5,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":5,"wins":17},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":1,"wins":12},"gpt-5.4":{"draws":4,"losses":11,"wins":15},"gpt-5.4-mini":{"draws":13,"losses":15,"wins":24},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":32},"gpt-5.5":{"draws":4,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":18,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":26,"wins":22},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":5,"losses":4,"wins":9},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":10},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":26,"wins":22},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":8},"z-ai/glm-5.2":{"draws":4,"losses":3,"wins":13}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":13,"wins":11},"claude-opus-4-5":{"draws":3,"losses":2,"wins":3},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":14,"losses":29,"wins":29},"claude-sonnet-5":{"draws":0,"losses":0,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":7,"wins":7},"gpt-5":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":6,"wins":16},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":17},"gpt-5.5":{"draws":4,"losses":3,"wins":11},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":8,"losses":10,"wins":16},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":29},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":8}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":14,"wins":0},"claude-opus-4-5":{"draws":5,"losses":10,"wins":7},"claude-opus-4-8":{"draws":7,"losses":12,"wins":5},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":11,"wins":5},"gpt-5.4":{"draws":5,"losses":7,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":16,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":13},"gpt-5.5":{"draws":6,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":21,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":16,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":8},"o3":{"draws":3,"losses":5,"wins":10},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":7},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":8},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":14,"wins":6}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":3,"losses":9,"wins":2},"claude-opus-4-8":{"draws":3,"losses":5,"wins":2},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":6,"wins":5},"gpt-5":{"draws":3,"losses":5,"wins":0},"gpt-5.4":{"draws":3,"losses":4,"wins":5},"gpt-5.4-mini":{"draws":15,"losses":16,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":8,"wins":10},"gpt-5.5":{"draws":6,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":9,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":11,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":0},"o3":{"draws":0,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":3,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":8,"losses":15,"wins":1},"claude-opus-4-8":{"draws":2,"losses":17,"wins":5},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":3,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":22,"losses":21,"wins":21},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":9},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":8},"gpt-5":{"draws":5,"losses":9,"wins":0},"gpt-5.4":{"draws":8,"losses":15,"wins":1},"gpt-5.4-mini":{"draws":41,"losses":34,"wins":25},"gpt-5.4-nano":{"draws":41,"losses":23,"wins":28},"gpt-5.5":{"draws":15,"losses":13,"wins":2},"gpt-5.6-luna":{"draws":21,"losses":10,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":27,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":4,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":25,"losses":41,"wins":10},"nex-agi/nex-n2-pro":{"draws":14,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":10},"o3":{"draws":5,"losses":14,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"stepfun/step-3.7-flash":{"draws":12,"losses":12,"wins":18},"tencent/hy3-preview":{"draws":14,"losses":12,"wins":8},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":20,"losses":46,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":21,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":12,"losses":13,"wins":11}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":3,"losses":11,"wins":8},"claude-opus-4-8":{"draws":5,"losses":3,"wins":4},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":9,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":2,"wins":6},"gpt-5.4":{"draws":3,"losses":13,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":19,"losses":9,"wins":22},"gpt-5.5":{"draws":5,"losses":10,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":3,"losses":5,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":24,"wins":10},"xiaomi/mimo-v2.5":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":13}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":5,"losses":7,"wins":0},"claude-opus-4-8":{"draws":5,"losses":5,"wins":0},"claude-sonnet-5":{"draws":4,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":15,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":17,"wins":11},"gpt-5.5":{"draws":5,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":14,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":3},"o3":{"draws":6,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":7,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":9,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":10,"wins":2}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":3,"losses":7,"wins":6},"claude-opus-4-5":{"draws":6,"losses":5,"wins":11},"claude-opus-4-8":{"draws":5,"losses":3,"wins":8},"claude-opus-5":{"draws":1,"losses":6,"wins":5},"claude-sonnet-5":{"draws":5,"losses":5,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":4,"wins":4},"gpt-5.4":{"draws":6,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":18},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":12},"gpt-5.5":{"draws":5,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":13,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":6},"o3":{"draws":0,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":7,"wins":16},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":5}},"google/gemini-3.5-flash-lite":{"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.6-flash":{"draws":18,"losses":18,"wins":10},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":16},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":2,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":16,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-8":{"draws":1,"losses":0,"wins":1},"claude-opus-5":{"draws":0,"losses":7,"wins":7},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":10,"wins":18},"google/gemini-3.6-flash":{"draws":10,"losses":11,"wins":11},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":8},"gpt-5.5":{"draws":0,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":9,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":16}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":0,"wins":1},"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":0,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":5,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":15},"gpt-5.5":{"draws":4,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":2},"o3":{"draws":2,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":7},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":9},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":6,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":4}},"gpt-5":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":8,"losses":3,"wins":7},"claude-opus-4-8":{"draws":5,"losses":12,"wins":1},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":10,"losses":5,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":4,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":20,"losses":13,"wins":21},"gpt-5.5":{"draws":3,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":5},"gpt-5.6-terra":{"draws":8,"losses":12,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":10,"wins":15},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":4},"o3":{"draws":2,"losses":5,"wins":9},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":20,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":3,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":8}},"gpt-5.4":{"claude-fable-5":{"draws":4,"losses":11,"wins":9},"claude-opus-4-5":{"draws":7,"losses":10,"wins":15},"claude-opus-4-8":{"draws":4,"losses":15,"wins":11},"claude-opus-5":{"draws":2,"losses":16,"wins":6},"claude-sonnet-5":{"draws":5,"losses":4,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":15},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":13},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":8},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":5,"wins":7},"gpt-5.4-mini":{"draws":28,"losses":12,"wins":34},"gpt-5.4-nano":{"draws":26,"losses":10,"wins":38},"gpt-5.5":{"draws":11,"losses":7,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":3,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":15,"wins":29},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"o3":{"draws":5,"losses":6,"wins":9},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":11},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":27,"losses":25,"wins":40},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":9},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":17}},"gpt-5.4-mini":{"claude-fable-5":{"draws":5,"losses":13,"wins":6},"claude-opus-4-5":{"draws":20,"losses":23,"wins":15},"claude-opus-4-8":{"draws":13,"losses":24,"wins":15},"claude-opus-5":{"draws":1,"losses":7,"wins":2},"claude-sonnet-5":{"draws":9,"losses":13,"wins":16},"cohere/north-mini-code":{"draws":15,"losses":7,"wins":16},"deepseek/deepseek-v4-flash":{"draws":41,"losses":25,"wins":34},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":15},"google/gemini-3.5-flash":{"draws":8,"losses":18,"wins":12},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":14,"losses":14,"wins":10},"gpt-5":{"draws":12,"losses":6,"wins":10},"gpt-5.4":{"draws":28,"losses":34,"wins":12},"gpt-5.4-mini":{"draws":72,"losses":42,"wins":42},"gpt-5.4-nano":{"draws":71,"losses":62,"wins":76},"gpt-5.5":{"draws":34,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":30,"losses":26,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":21,"wins":16},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":6,"wins":4},"minimax/minimax-m3":{"draws":15,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":46,"losses":41,"wins":21},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":14},"o3":{"draws":8,"losses":29,"wins":17},"openai/gpt-oss-120b":{"draws":25,"losses":23,"wins":16},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":11},"qwen/qwen3.7-plus":{"draws":14,"losses":23,"wins":13},"stepfun/step-3.7-flash":{"draws":16,"losses":17,"wins":27},"tencent/hy3-preview":{"draws":16,"losses":6,"wins":16},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":44,"losses":72,"wins":22},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":8},"xiaomi/mimo-v2.5":{"draws":48,"losses":48,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":7,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":17}},"gpt-5.4-nano":{"claude-fable-5":{"draws":3,"losses":26,"wins":7},"claude-opus-4-5":{"draws":19,"losses":31,"wins":14},"claude-opus-4-8":{"draws":13,"losses":32,"wins":13},"claude-opus-5":{"draws":4,"losses":17,"wins":3},"claude-sonnet-5":{"draws":11,"losses":13,"wins":10},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":8},"deepseek/deepseek-v4-flash":{"draws":41,"losses":28,"wins":23},"deepseek/deepseek-v4-pro":{"draws":19,"losses":22,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":11,"wins":17},"google/gemini-3.5-flash":{"draws":11,"losses":12,"wins":9},"google/gemini-3.5-flash-lite":{"draws":3,"losses":16,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":4},"google/gemma-4-31b-it":{"draws":8,"losses":15,"wins":15},"gpt-5":{"draws":20,"losses":21,"wins":13},"gpt-5.4":{"draws":26,"losses":38,"wins":10},"gpt-5.4-mini":{"draws":71,"losses":76,"wins":62},"gpt-5.4-nano":{"draws":58,"losses":57,"wins":57},"gpt-5.5":{"draws":18,"losses":19,"wins":13},"gpt-5.6-luna":{"draws":24,"losses":26,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":15},"gpt-5.6-terra":{"draws":28,"losses":22,"wins":24},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":16,"losses":17,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":37,"losses":56,"wins":38},"nex-agi/nex-n2-pro":{"draws":14,"losses":20,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":15,"wins":6},"o3":{"draws":17,"losses":13,"wins":18},"openai/gpt-oss-120b":{"draws":40,"losses":22,"wins":22},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":27,"losses":19,"wins":10},"qwen/qwen3.7-plus":{"draws":14,"losses":23,"wins":7},"stepfun/step-3.7-flash":{"draws":17,"losses":15,"wins":16},"tencent/hy3-preview":{"draws":22,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":8},"x-ai/grok-4.5":{"draws":36,"losses":67,"wins":49},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":4},"xiaomi/mimo-v2.5":{"draws":38,"losses":51,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":16,"wins":15},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":13}},"gpt-5.5":{"claude-fable-5":{"draws":5,"losses":7,"wins":10},"claude-opus-4-5":{"draws":10,"losses":8,"wins":16},"claude-opus-4-8":{"draws":4,"losses":3,"wins":11},"claude-opus-5":{"draws":4,"losses":11,"wins":3},"claude-sonnet-5":{"draws":6,"losses":4,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":15,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":3},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":6,"wins":12},"gpt-5.4":{"draws":11,"losses":10,"wins":7},"gpt-5.4-mini":{"draws":34,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":18,"losses":13,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":10,"wins":13},"gpt-5.6-terra":{"draws":11,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":14,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":4,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":6},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":17,"losses":30,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":18,"losses":1,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":11}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":16,"wins":2},"claude-opus-4-5":{"draws":9,"losses":8,"wins":9},"claude-opus-4-8":{"draws":8,"losses":14,"wins":8},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":3,"losses":3,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":3},"gpt-5":{"draws":6,"losses":3,"wins":3},"gpt-5.4":{"draws":15,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":30,"losses":28,"wins":26},"gpt-5.4-nano":{"draws":24,"losses":22,"wins":26},"gpt-5.5":{"draws":9,"losses":11,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":14,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":7},"o3":{"draws":2,"losses":7,"wins":7},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":4},"stepfun/step-3.7-flash":{"draws":3,"losses":11,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":7},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":17},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":21,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":7,"wins":8}},"gpt-5.6-sol":{"claude-fable-5":{"draws":5,"losses":14,"wins":7},"claude-opus-4-5":{"draws":7,"losses":5,"wins":18},"claude-opus-4-8":{"draws":6,"losses":8,"wins":18},"claude-opus-5":{"draws":8,"losses":16,"wins":10},"claude-sonnet-5":{"draws":3,"losses":4,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":8},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":5,"wins":9},"gpt-5.4":{"draws":6,"losses":20,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":24},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":36},"gpt-5.5":{"draws":9,"losses":13,"wins":10},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":15},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":23,"wins":47},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":4,"wins":6},"o3":{"draws":4,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":10},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":16,"losses":31,"wins":45},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":10},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":17}},"gpt-5.6-terra":{"claude-fable-5":{"draws":5,"losses":15,"wins":2},"claude-opus-4-5":{"draws":6,"losses":6,"wins":12},"claude-opus-4-8":{"draws":9,"losses":12,"wins":7},"claude-opus-5":{"draws":5,"losses":3,"wins":2},"claude-sonnet-5":{"draws":5,"losses":10,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":27},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":10,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":7},"gpt-5":{"draws":8,"losses":4,"wins":12},"gpt-5.4":{"draws":10,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":37,"losses":16,"wins":21},"gpt-5.4-nano":{"draws":28,"losses":24,"wins":22},"gpt-5.5":{"draws":11,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":4,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":24,"losses":26,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":10},"o3":{"draws":7,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":8,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":22,"losses":28,"wins":18},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":17,"losses":8,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":6}},"inclusionai/ling-3.0-flash":{"claude-opus-5":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":10,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1}},"meituan/longcat-2.0":{"claude-opus-4-5":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":3,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":2,"losses":4,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":6,"wins":0},"claude-opus-4-8":{"draws":4,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":2,"losses":7,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":4},"google/gemini-3.1-flash-lite":{"draws":1,"losses":6,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":7},"gpt-5":{"draws":3,"losses":5,"wins":2},"gpt-5.4":{"draws":5,"losses":7,"wins":4},"gpt-5.4-mini":{"draws":15,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":16,"losses":15,"wins":17},"gpt-5.5":{"draws":4,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":3,"losses":7,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"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":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":10,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":0,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":13,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":17,"wins":3},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":8},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":19,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":7,"wins":1},"o3":{"draws":0,"losses":8,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":7,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":10,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":12,"wins":0}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":2,"losses":3,"wins":1},"claude-opus-4-8":{"draws":2,"losses":1,"wins":3},"claude-sonnet-5":{"draws":1,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":3,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":5},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":21,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":5,"losses":3,"wins":8}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":9,"losses":32,"wins":5},"claude-opus-4-5":{"draws":25,"losses":12,"wins":29},"claude-opus-4-8":{"draws":16,"losses":22,"wins":26},"claude-sonnet-5":{"draws":14,"losses":8,"wins":16},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":25,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":15},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":12,"wins":13},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":17,"losses":15,"wins":10},"gpt-5.4":{"draws":12,"losses":29,"wins":15},"gpt-5.4-mini":{"draws":46,"losses":21,"wins":41},"gpt-5.4-nano":{"draws":37,"losses":38,"wins":56},"gpt-5.5":{"draws":22,"losses":20,"wins":14},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":14},"gpt-5.6-sol":{"draws":14,"losses":47,"wins":23},"gpt-5.6-terra":{"draws":24,"losses":16,"wins":26},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":28,"losses":26,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":5,"wins":17},"o3":{"draws":9,"losses":12,"wins":25},"openai/gpt-oss-120b":{"draws":23,"losses":2,"wins":27},"qwen/qwen3.7-max":{"draws":15,"losses":12,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":12,"losses":5,"wins":25},"tencent/hy3-preview":{"draws":6,"losses":12,"wins":20},"x-ai/grok-4.5":{"draws":40,"losses":74,"wins":58},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":19,"losses":16,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":11},"z-ai/glm-5.2":{"draws":26,"losses":17,"wins":19}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":6,"losses":2,"wins":2},"claude-opus-4-8":{"draws":5,"losses":3,"wins":2},"claude-sonnet-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":5,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":20},"gpt-5.5":{"draws":4,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":10,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":12,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":4}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":7,"losses":10,"wins":1},"claude-opus-4-8":{"draws":5,"losses":11,"wins":2},"claude-sonnet-5":{"draws":10,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":8,"losses":4,"wins":2},"gpt-5.4":{"draws":8,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":20,"losses":14,"wins":8},"gpt-5.4-nano":{"draws":31,"losses":6,"wins":15},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":10,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":17,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":3,"losses":8,"wins":1},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":7},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":3,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":6}},"o3":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":7,"losses":9,"wins":10},"claude-opus-4-8":{"draws":5,"losses":9,"wins":4},"claude-sonnet-5":{"draws":3,"losses":10,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":9,"wins":14},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":2,"losses":9,"wins":5},"gpt-5.4":{"draws":5,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":17,"wins":29},"gpt-5.4-nano":{"draws":17,"losses":18,"wins":13},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":25,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":8},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.7-max":{"draws":8,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":13},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":38,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":0,"losses":9,"wins":5}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":11,"losses":6,"wins":3},"claude-opus-4-8":{"draws":6,"losses":7,"wins":3},"claude-sonnet-5":{"draws":4,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":7,"wins":3},"gpt-5":{"draws":7,"losses":2,"wins":1},"gpt-5.4":{"draws":8,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":25,"losses":16,"wins":23},"gpt-5.4-nano":{"draws":40,"losses":22,"wins":22},"gpt-5.5":{"draws":8,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":23,"losses":27,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":0,"wins":2},"o3":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":8,"losses":15,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":14,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":8,"losses":11,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":5}},"poolside/laguna-s-2.1":{"claude-opus-4-8":{"draws":0,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":1},"gpt-5.4":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":8,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":18,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":4,"losses":7,"wins":5},"claude-opus-4-8":{"draws":2,"losses":7,"wins":5},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":4},"gpt-5":{"draws":2,"losses":3,"wins":3},"gpt-5.4":{"draws":4,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":27,"losses":10,"wins":19},"gpt-5.5":{"draws":3,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":6,"losses":11,"wins":7},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":13,"wins":12},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":8,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":15,"losses":17,"wins":10},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":7,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":7}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-sonnet-5":{"draws":4,"losses":1,"wins":3},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":9,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":23},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":23},"gpt-5.5":{"draws":5,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":7,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":0,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":7,"losses":11,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":1}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":10,"losses":9,"wins":1},"claude-opus-4-8":{"draws":0,"losses":3,"wins":3},"claude-sonnet-5":{"draws":2,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":18,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":11,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-5":{"draws":0,"losses":8,"wins":0},"gpt-5.4":{"draws":4,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":27,"wins":17},"gpt-5.4-nano":{"draws":17,"losses":16,"wins":15},"gpt-5.5":{"draws":4,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":4,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":25,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":5},"o3":{"draws":4,"losses":13,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":3,"losses":8,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":10,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":9,"wins":5}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":6,"losses":11,"wins":5},"claude-opus-4-8":{"draws":1,"losses":10,"wins":1},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":0,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":14,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":4,"wins":3},"gpt-5.4":{"draws":6,"losses":11,"wins":1},"gpt-5.4-mini":{"draws":16,"losses":16,"wins":6},"gpt-5.4-nano":{"draws":22,"losses":11,"wins":19},"gpt-5.5":{"draws":8,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":20,"wins":12},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":6},"o3":{"draws":6,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":21,"wins":8},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":3,"wins":10}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":4,"losses":1,"wins":1},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":0,"losses":9,"wins":1},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":16},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":12},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":7},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":9,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":13,"losses":41,"wins":16},"claude-opus-4-5":{"draws":22,"losses":18,"wins":44},"claude-opus-4-8":{"draws":12,"losses":22,"wins":26},"claude-opus-5":{"draws":5,"losses":29,"wins":14},"claude-sonnet-5":{"draws":15,"losses":10,"wins":27},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":20,"losses":12,"wins":46},"deepseek/deepseek-v4-pro":{"draws":4,"losses":10,"wins":24},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":7},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":21},"google/gemini-3.6-flash":{"draws":6,"losses":16,"wins":10},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":12},"gpt-5":{"draws":9,"losses":9,"wins":20},"gpt-5.4":{"draws":27,"losses":40,"wins":25},"gpt-5.4-mini":{"draws":44,"losses":22,"wins":72},"gpt-5.4-nano":{"draws":36,"losses":49,"wins":67},"gpt-5.5":{"draws":17,"losses":25,"wins":30},"gpt-5.6-luna":{"draws":15,"losses":17,"wins":24},"gpt-5.6-sol":{"draws":16,"losses":45,"wins":31},"gpt-5.6-terra":{"draws":22,"losses":18,"wins":28},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":16},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":21},"moonshotai/kimi-k3":{"draws":40,"losses":58,"wins":74},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":13},"o3":{"draws":11,"losses":17,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":22},"qwen/qwen3.7-max":{"draws":15,"losses":10,"wins":17},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":31},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":21},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":34,"losses":55,"wins":55},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":12,"losses":10,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":16},"z-ai/glm-5.2":{"draws":7,"losses":14,"wins":27}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":5,"losses":6,"wins":1},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"claude-sonnet-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":3,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":3,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":4,"wins":12},"gpt-5.5":{"draws":3,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":1},"o3":{"draws":3,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":16,"losses":11,"wins":7},"claude-opus-4-8":{"draws":9,"losses":19,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":13,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":12,"losses":11,"wins":9},"deepseek/deepseek-v4-flash":{"draws":18,"losses":21,"wins":21},"deepseek/deepseek-v4-pro":{"draws":1,"losses":7,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":5,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":10,"wins":6},"gpt-5":{"draws":6,"losses":1,"wins":3},"gpt-5.4":{"draws":14,"losses":14,"wins":4},"gpt-5.4-mini":{"draws":48,"losses":28,"wins":48},"gpt-5.4-nano":{"draws":38,"losses":31,"wins":51},"gpt-5.5":{"draws":18,"losses":9,"wins":1},"gpt-5.6-luna":{"draws":13,"losses":4,"wins":21},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":8},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":10,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":29,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":11,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":3},"o3":{"draws":12,"losses":18,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":13,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":32,"wins":10},"x-ai/grok-build-0.1":{"draws":9,"losses":9,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":8}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":3,"losses":5,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":4},"gpt-5":{"draws":3,"losses":3,"wins":0},"gpt-5.4":{"draws":4,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":16},"gpt-5.5":{"draws":4,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":8,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":16,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":8,"wins":7}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":15,"wins":2},"claude-opus-4-5":{"draws":8,"losses":12,"wins":10},"claude-opus-4-8":{"draws":4,"losses":13,"wins":3},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":12,"losses":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":6},"gpt-5":{"draws":9,"losses":8,"wins":9},"gpt-5.4":{"draws":3,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":23,"losses":13,"wins":16},"gpt-5.5":{"draws":4,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":17,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":26,"losses":19,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":9},"o3":{"draws":0,"losses":5,"wins":9},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":7,"losses":10,"wins":3},"x-ai/grok-4.5":{"draws":7,"losses":27,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":13,"wins":13}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-opus-4-5":{"draws":0,"losses":1,"wins":5},"claude-opus-4-8":{"draws":1,"losses":4,"wins":7},"claude-opus-5":{"draws":4,"losses":6,"wins":6},"claude-sonnet-5":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":5},"gpt-5":{"draws":1,"losses":0,"wins":9},"gpt-5.4":{"draws":2,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":13},"gpt-5.5":{"draws":3,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":4,"wins":6},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":25},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":26},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":15}},"claude-opus-4-5":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":3},"gpt-5":{"draws":7,"losses":3,"wins":2},"gpt-5.4":{"draws":2,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":8},"gpt-5.5":{"draws":1,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":8},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":10,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":1,"losses":7,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":6},"claude-opus-5":{"draws":2,"losses":5,"wins":3},"claude-sonnet-5":{"draws":1,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":6},"gpt-5.4":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":9},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":10},"gpt-5.5":{"draws":0,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":1,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":7},"o3":{"draws":0,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":15},"z-ai/glm-5.2":{"draws":4,"losses":3,"wins":13}},"claude-opus-5":{"claude-fable-5":{"draws":4,"losses":6,"wins":6},"claude-opus-4-8":{"draws":2,"losses":3,"wins":5},"claude-opus-5":{"draws":2,"losses":11,"wins":11},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":3,"wins":11},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":0,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":7},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":8}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-opus-4-5":{"draws":4,"losses":4,"wins":4},"claude-opus-4-8":{"draws":1,"losses":10,"wins":3},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":8,"losses":5,"wins":3},"gpt-5.4":{"draws":3,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":2},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":15,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"o3":{"draws":0,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":13,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":12,"losses":14,"wins":6}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":2,"losses":9,"wins":1},"claude-opus-4-8":{"draws":0,"losses":9,"wins":3},"claude-sonnet-5":{"draws":3,"losses":14,"wins":1},"deepseek/deepseek-v4-flash":{"draws":0,"losses":6,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"gpt-5":{"draws":5,"losses":9,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":15,"losses":8,"wins":9},"gpt-5.5":{"draws":0,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":15,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":10},"o3":{"draws":0,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":2,"losses":25,"wins":7},"z-ai/glm-5.2":{"draws":12,"losses":13,"wins":11}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":1,"losses":6,"wins":3},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":6},"gpt-5.4":{"draws":0,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":12},"gpt-5.5":{"draws":1,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":1,"losses":2,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":1,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":13}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":1,"losses":3,"wins":0},"claude-sonnet-5":{"draws":2,"losses":5,"wins":1},"deepseek/deepseek-v4-flash":{"draws":2,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":1},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":1},"o3":{"draws":0,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":3},"x-ai/grok-4.5":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":10,"wins":2}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-8":{"draws":1,"losses":3,"wins":4},"claude-sonnet-5":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4":{"draws":2,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":4},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":5}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":7,"losses":2,"wins":3},"claude-opus-4-8":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":8,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"gpt-5.4":{"draws":2,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":6,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":15},"gpt-5.5":{"draws":3,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":8,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":3},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":8}},"gpt-5.4":{"claude-fable-5":{"draws":2,"losses":6,"wins":6},"claude-opus-4-5":{"draws":2,"losses":1,"wins":7},"claude-opus-4-8":{"draws":2,"losses":5,"wins":5},"claude-opus-5":{"draws":0,"losses":11,"wins":3},"claude-sonnet-5":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":3,"wins":7},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":13},"gpt-5.5":{"draws":5,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":8},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":5},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":9,"losses":8,"wins":21},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":17}},"gpt-5.4-mini":{"claude-fable-5":{"draws":1,"losses":7,"wins":4},"claude-opus-4-5":{"draws":6,"losses":2,"wins":6},"claude-opus-4-8":{"draws":1,"losses":9,"wins":6},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":7},"gpt-5":{"draws":6,"losses":4,"wins":8},"gpt-5.4":{"draws":1,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":7},"gpt-5.5":{"draws":2,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":7},"o3":{"draws":0,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":26,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":17}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":13,"wins":3},"claude-opus-4-5":{"draws":7,"losses":8,"wins":7},"claude-opus-4-8":{"draws":0,"losses":10,"wins":4},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":6,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":15,"losses":9,"wins":8},"deepseek/deepseek-v4-pro":{"draws":6,"losses":12,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"gpt-5":{"draws":10,"losses":15,"wins":3},"gpt-5.4":{"draws":6,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":6},"gpt-5.5":{"draws":1,"losses":10,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":1,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":22,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":2,"wins":2},"o3":{"draws":0,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":17,"wins":19},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":13}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":3,"wins":6},"claude-opus-4-5":{"draws":1,"losses":3,"wins":6},"claude-opus-4-8":{"draws":0,"losses":1,"wins":7},"claude-opus-5":{"draws":0,"losses":7,"wins":3},"claude-sonnet-5":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":3,"losses":2,"wins":8},"gpt-5.4":{"draws":5,"losses":4,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":10},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":6},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":12},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":11}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":3,"losses":3,"wins":8},"claude-opus-4-8":{"draws":2,"losses":8,"wins":4},"claude-sonnet-5":{"draws":3,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":3,"losses":2,"wins":1},"gpt-5.4":{"draws":5,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":7},"gpt-5.5":{"draws":1,"losses":7,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":7,"losses":7,"wins":8}},"gpt-5.6-sol":{"claude-fable-5":{"draws":4,"losses":6,"wins":4},"claude-opus-4-5":{"draws":2,"losses":1,"wins":7},"claude-opus-4-8":{"draws":1,"losses":3,"wins":8},"claude-opus-5":{"draws":3,"losses":7,"wins":6},"claude-sonnet-5":{"draws":1,"losses":4,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":0,"losses":3,"wins":7},"gpt-5.4":{"draws":2,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":3,"wins":14},"gpt-5.5":{"draws":0,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":8},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":4,"wins":4},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":17}},"gpt-5.6-terra":{"claude-fable-5":{"draws":3,"losses":10,"wins":1},"claude-opus-4-5":{"draws":0,"losses":0,"wins":8},"claude-opus-4-8":{"draws":1,"losses":9,"wins":2},"claude-opus-5":{"draws":2,"losses":3,"wins":1},"claude-sonnet-5":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":8},"gpt-5.4":{"draws":3,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":7,"wins":9},"gpt-5.4-nano":{"draws":1,"losses":11,"wins":6},"gpt-5.5":{"draws":1,"losses":5,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":7},"o3":{"draws":0,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":11,"wins":12},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":6}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":8,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":3},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":15,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":7,"wins":1},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":12,"wins":0}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":4,"losses":25,"wins":3},"claude-opus-4-5":{"draws":9,"losses":4,"wins":9},"claude-opus-4-8":{"draws":6,"losses":13,"wins":9},"claude-sonnet-5":{"draws":8,"losses":8,"wins":10},"deepseek/deepseek-v4-flash":{"draws":12,"losses":7,"wins":15},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":11},"gpt-5":{"draws":12,"losses":8,"wins":6},"gpt-5.4":{"draws":2,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":22},"gpt-5.5":{"draws":6,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":12,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":12},"o3":{"draws":0,"losses":4,"wins":10},"openai/gpt-oss-120b":{"draws":13,"losses":0,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":23},"z-ai/glm-5.2":{"draws":26,"losses":17,"wins":19}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":7,"losses":8,"wins":1},"claude-opus-4-8":{"draws":1,"losses":7,"wins":2},"claude-sonnet-5":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"gpt-5":{"draws":7,"losses":3,"wins":0},"gpt-5.4":{"draws":3,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":20,"losses":2,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":19,"losses":12,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":0,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":6}},"o3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":3,"wins":3},"claude-opus-4-8":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":0,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":4,"wins":2},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":5,"wins":1},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":10,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":1,"losses":11,"wins":4},"z-ai/glm-5.2":{"draws":0,"losses":9,"wins":5}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":6,"losses":2,"wins":2},"claude-opus-4-8":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":4,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":4},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":11,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":2},"o3":{"draws":1,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":5}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":7,"wins":1},"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":9,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":9,"wins":1},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":2,"losses":11,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":4},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":0,"losses":15,"wins":1},"z-ai/glm-5.2":{"draws":2,"losses":9,"wins":5}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":5,"losses":5,"wins":2},"claude-opus-4-8":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":0,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":1,"losses":4,"wins":3},"gpt-5.4":{"draws":1,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":1},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":4},"gpt-5.5":{"draws":4,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":14,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":6},"o3":{"draws":0,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":3,"wins":10}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":3,"losses":26,"wins":5},"claude-opus-4-5":{"draws":11,"losses":5,"wins":16},"claude-opus-4-8":{"draws":5,"losses":15,"wins":8},"claude-sonnet-5":{"draws":13,"losses":8,"wins":15},"deepseek/deepseek-v4-flash":{"draws":2,"losses":7,"wins":25},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":15},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":2},"gpt-5":{"draws":5,"losses":7,"wins":8},"gpt-5.4":{"draws":9,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":4,"losses":8,"wins":26},"gpt-5.4-nano":{"draws":8,"losses":19,"wins":17},"gpt-5.5":{"draws":6,"losses":12,"wins":12},"gpt-5.6-luna":{"draws":5,"losses":12,"wins":13},"gpt-5.6-sol":{"draws":0,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":1,"losses":12,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":23,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":11},"o3":{"draws":1,"losses":4,"wins":11},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":15},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":16},"x-ai/grok-4.5":{"draws":8,"losses":26,"wins":26},"z-ai/glm-5.2":{"draws":7,"losses":14,"wins":27}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":15,"wins":2},"claude-opus-4-5":{"draws":8,"losses":12,"wins":10},"claude-opus-4-8":{"draws":4,"losses":13,"wins":3},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":12,"losses":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":6},"gpt-5":{"draws":9,"losses":8,"wins":9},"gpt-5.4":{"draws":3,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":23,"losses":13,"wins":16},"gpt-5.5":{"draws":4,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":17,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":26,"losses":19,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":9},"o3":{"draws":0,"losses":5,"wins":9},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":7,"losses":10,"wins":3},"x-ai/grok-4.5":{"draws":7,"losses":27,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":13,"wins":13}}},"medium":{"claude-fable-5":{"claude-opus-4-5":{"draws":1,"losses":1,"wins":6},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":4,"losses":5,"wins":7},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":5,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":5},"gpt-5.4":{"draws":2,"losses":3,"wins":5},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":13},"gpt-5.5":{"draws":2,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":8},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":5,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6}},"claude-opus-4-5":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"claude-opus-5":{"draws":2,"losses":1,"wins":1},"claude-sonnet-5":{"draws":1,"losses":3,"wins":6},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":1,"losses":4,"wins":1},"gpt-5.4":{"draws":1,"losses":4,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":13},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":3},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":3,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":17,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":2}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":2,"losses":2,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":6,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":6},"gpt-5.4":{"draws":2,"losses":2,"wins":6},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":8},"gpt-5.5":{"draws":3,"losses":2,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":4},"o3":{"draws":4,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6}},"claude-opus-5":{"claude-fable-5":{"draws":4,"losses":7,"wins":5},"claude-opus-4-5":{"draws":2,"losses":1,"wins":1},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":4,"losses":12,"wins":12},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":7,"wins":7},"gpt-5":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":0,"losses":1,"wins":3},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":3,"wins":8},"gpt-5.5":{"draws":2,"losses":0,"wins":4},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":4,"wins":7},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":29}},"claude-sonnet-5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":1,"losses":6,"wins":3},"claude-opus-4-8":{"draws":6,"losses":2,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":2,"losses":6,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":11},"gpt-5.5":{"draws":2,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":0},"o3":{"draws":3,"losses":1,"wins":6},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":1,"losses":3,"wins":2},"claude-opus-4-8":{"draws":3,"losses":1,"wins":2},"claude-sonnet-5":{"draws":2,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":3,"losses":5,"wins":0},"gpt-5.4":{"draws":1,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":3,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":5},"gpt-5.5":{"draws":2,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":7,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":0},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":10},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":2},"o3":{"draws":6,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":9,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":3,"losses":2,"wins":5},"claude-opus-4-5":{"draws":3,"losses":2,"wins":7},"claude-opus-4-8":{"draws":4,"losses":0,"wins":4},"claude-opus-5":{"draws":1,"losses":6,"wins":5},"claude-sonnet-5":{"draws":3,"losses":2,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":4,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":8},"gpt-5.5":{"draws":1,"losses":0,"wins":5},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":9},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":2,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":5,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2}},"google/gemini-3.5-flash-lite":{"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.6-flash":{"draws":18,"losses":18,"wins":10},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":16},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":2,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":16,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-8":{"draws":1,"losses":0,"wins":1},"claude-opus-5":{"draws":0,"losses":7,"wins":7},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":10,"wins":18},"google/gemini-3.6-flash":{"draws":10,"losses":11,"wins":11},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":8},"gpt-5.5":{"draws":0,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":9,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":16}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":0,"wins":1},"claude-opus-4-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":0,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":5},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":1,"losses":1,"wins":4},"claude-opus-4-8":{"draws":3,"losses":6,"wins":1},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":2,"losses":2,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":10,"losses":10,"wins":6},"gpt-5.5":{"draws":0,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":1},"o3":{"draws":2,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":3,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3}},"gpt-5.4":{"claude-fable-5":{"draws":2,"losses":5,"wins":3},"claude-opus-4-5":{"draws":1,"losses":3,"wins":4},"claude-opus-4-8":{"draws":2,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":15},"gpt-5.5":{"draws":4,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":3},"o3":{"draws":1,"losses":3,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":6},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":6}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":6,"wins":2},"claude-opus-4-5":{"draws":4,"losses":9,"wins":5},"claude-opus-4-8":{"draws":4,"losses":4,"wins":6},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":4,"losses":8,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":7},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":2,"wins":2},"gpt-5.4":{"draws":9,"losses":14,"wins":7},"gpt-5.4-mini":{"draws":32,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":22,"losses":18,"wins":43},"gpt-5.5":{"draws":9,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":4},"gpt-5.6-terra":{"draws":16,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":10,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":4,"losses":9,"wins":11},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":19,"losses":30,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":17,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":5}},"gpt-5.4-nano":{"claude-fable-5":{"draws":1,"losses":13,"wins":4},"claude-opus-4-5":{"draws":2,"losses":13,"wins":3},"claude-opus-4-8":{"draws":5,"losses":8,"wins":1},"claude-opus-5":{"draws":3,"losses":8,"wins":3},"claude-sonnet-5":{"draws":5,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":7,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":3,"losses":16,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":6},"gpt-5":{"draws":10,"losses":6,"wins":10},"gpt-5.4":{"draws":10,"losses":15,"wins":5},"gpt-5.4-mini":{"draws":22,"losses":43,"wins":18},"gpt-5.4-nano":{"draws":18,"losses":27,"wins":27},"gpt-5.5":{"draws":0,"losses":4,"wins":10},"gpt-5.6-luna":{"draws":8,"losses":12,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":13,"losses":14,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":12,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":2,"losses":12,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":13,"wins":4},"o3":{"draws":4,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":15,"wins":1},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":3,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":16},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":4},"xiaomi/mimo-v2.5":{"draws":14,"losses":25,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":6}},"gpt-5.5":{"claude-fable-5":{"draws":2,"losses":4,"wins":4},"claude-opus-4-5":{"draws":4,"losses":3,"wins":7},"claude-opus-4-8":{"draws":3,"losses":1,"wins":2},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":4,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":1,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":0,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":12},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":3}},"gpt-5.6-luna":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":2,"losses":3,"wins":1},"claude-opus-4-8":{"draws":3,"losses":4,"wins":3},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":12},"gpt-5.5":{"draws":1,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":2,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2}},"gpt-5.6-sol":{"claude-fable-5":{"draws":1,"losses":8,"wins":3},"claude-opus-4-5":{"draws":1,"losses":1,"wins":6},"claude-opus-4-8":{"draws":1,"losses":2,"wins":5},"claude-opus-5":{"draws":1,"losses":7,"wins":4},"claude-sonnet-5":{"draws":2,"losses":0,"wins":6},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":0,"losses":5,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":11},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":10},"gpt-5.5":{"draws":4,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":1,"losses":7,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":7,"losses":15,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":5,"wins":1},"claude-opus-4-5":{"draws":1,"losses":3,"wins":2},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":1,"losses":4,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":5,"losses":1,"wins":4},"gpt-5.4":{"draws":7,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":13,"losses":7,"wins":14},"gpt-5.5":{"draws":4,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":3,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-sonnet-5":{"draws":4,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":6,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":3,"losses":5,"wins":2},"gpt-5.4":{"draws":3,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":12},"gpt-5.5":{"draws":2,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":0}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":2,"losses":3,"wins":1},"claude-opus-4-8":{"draws":2,"losses":1,"wins":3},"claude-sonnet-5":{"draws":1,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":3,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":5},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":21,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":5,"losses":3,"wins":8}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":5,"losses":7,"wins":2},"claude-opus-4-5":{"draws":9,"losses":4,"wins":7},"claude-opus-4-8":{"draws":5,"losses":4,"wins":9},"claude-sonnet-5":{"draws":6,"losses":0,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":8,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4":{"draws":4,"losses":3,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":9,"wins":13},"gpt-5.5":{"draws":8,"losses":3,"wins":5},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":12,"wins":7},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":5},"o3":{"draws":3,"losses":3,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":15},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":4}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":3,"losses":1,"wins":0},"claude-sonnet-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":12},"gpt-5.5":{"draws":0,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":7,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":4,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":5,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":4,"wins":13},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":4},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":3,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0}},"o3":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":3,"losses":2,"wins":5},"claude-opus-4-8":{"draws":4,"losses":3,"wins":1},"claude-sonnet-5":{"draws":3,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":3},"gpt-5.4":{"draws":1,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":11,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":5},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":14,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":3,"losses":2,"wins":1},"claude-sonnet-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":10},"gpt-5.5":{"draws":0,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":3,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":6,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":3,"losses":3,"wins":2},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":2,"losses":3,"wins":3},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":11},"gpt-5.5":{"draws":2,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":4,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":2,"losses":5,"wins":3},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-sonnet-5":{"draws":4,"losses":1,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":6,"losses":1,"wins":15},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":7,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":1}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":4,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":1,"losses":0,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"o3":{"draws":1,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":2,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":2}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":16},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":9},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":7},"gpt-5.5":{"draws":1,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":9,"wins":2}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":10,"losses":15,"wins":11},"claude-opus-4-5":{"draws":7,"losses":6,"wins":17},"claude-opus-4-8":{"draws":0,"losses":1,"wins":11},"claude-opus-5":{"draws":5,"losses":29,"wins":14},"claude-sonnet-5":{"draws":2,"losses":2,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":5},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":21},"google/gemini-3.6-flash":{"draws":6,"losses":16,"wins":10},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":7},"gpt-5":{"draws":4,"losses":2,"wins":12},"gpt-5.4":{"draws":10,"losses":6,"wins":14},"gpt-5.4-mini":{"draws":19,"losses":13,"wins":30},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":29},"gpt-5.5":{"draws":6,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":21},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":24},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":4,"wins":2},"o3":{"draws":2,"losses":6,"wins":14},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":21,"wins":21},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":4,"losses":3,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":6}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":5,"losses":6,"wins":1},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"claude-sonnet-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":3,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":3,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":4,"wins":12},"gpt-5.5":{"draws":3,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":1},"o3":{"draws":3,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":11,"losses":5,"wins":2},"claude-opus-4-8":{"draws":9,"losses":7,"wins":0},"claude-sonnet-5":{"draws":13,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":5,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":6,"losses":1,"wins":3},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":19,"losses":10,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":13,"wins":25},"gpt-5.5":{"draws":8,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":3},"o3":{"draws":8,"losses":14,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":17,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":9,"wins":4},"xiaomi/mimo-v2.5":{"draws":14,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":1,"losses":2,"wins":3},"claude-opus-4-8":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":3,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":10},"gpt-5.5":{"draws":1,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":2}}},"none":{"claude-opus-4-5":{"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":1,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":4,"losses":4,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":10},"gpt-5.5":{"draws":5,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":0},"o3":{"draws":2,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3}},"claude-opus-4-8":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-5.4":{"draws":0,"losses":4,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":11},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":14},"gpt-5.5":{"draws":1,"losses":2,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"o3":{"draws":1,"losses":2,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":6},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2}},"claude-opus-5":{"claude-opus-4-5":{"draws":1,"losses":1,"wins":2},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":8,"losses":6,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":7},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":5},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"o3":{"draws":0,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":7,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0}},"deepseek/deepseek-v4-flash":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":0},"claude-opus-4-8":{"draws":2,"losses":8,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":15},"deepseek/deepseek-v4-pro":{"draws":8,"losses":2,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":8},"gpt-5.4":{"draws":8,"losses":11,"wins":1},"gpt-5.4-mini":{"draws":33,"losses":22,"wins":19},"gpt-5.4-nano":{"draws":26,"losses":15,"wins":19},"gpt-5.5":{"draws":15,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":17,"losses":7,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":18,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":26,"wins":3},"nex-agi/nex-n2-pro":{"draws":14,"losses":11,"wins":5},"o3":{"draws":5,"losses":7,"wins":6},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":18,"losses":21,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":21,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":3}},"deepseek/deepseek-v4-pro":{"claude-opus-4-5":{"draws":2,"losses":5,"wins":5},"claude-opus-4-8":{"draws":3,"losses":3,"wins":4},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":3,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":1,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":7,"wins":10},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":3},"o3":{"draws":2,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":9,"wins":6},"xiaomi/mimo-v2.5":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3}},"google/gemma-4-31b-it":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":10},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"o3":{"draws":2,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":6,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2}},"gpt-5.4":{"claude-opus-4-5":{"draws":4,"losses":6,"wins":4},"claude-opus-4-8":{"draws":0,"losses":4,"wins":4},"claude-opus-5":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":3},"gpt-5.4-mini":{"draws":18,"losses":1,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":2,"wins":10},"gpt-5.5":{"draws":2,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":7},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"o3":{"draws":4,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":10,"losses":12,"wins":4},"claude-opus-4-8":{"draws":8,"losses":11,"wins":3},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":12,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":33,"losses":19,"wins":22},"deepseek/deepseek-v4-pro":{"draws":14,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":12,"wins":8},"gpt-5.4":{"draws":18,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":36,"losses":24,"wins":24},"gpt-5.4-nano":{"draws":38,"losses":34,"wins":26},"gpt-5.5":{"draws":23,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":6,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":11},"moonshotai/kimi-k3":{"draws":19,"losses":17,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":8,"wins":4},"o3":{"draws":4,"losses":13,"wins":3},"openai/gpt-oss-120b":{"draws":7,"losses":13,"wins":12},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":10,"losses":13,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":12,"wins":13},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":21,"losses":16,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":31,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":3,"wins":4}},"gpt-5.4-nano":{"claude-opus-4-5":{"draws":10,"losses":10,"wins":4},"claude-opus-4-8":{"draws":8,"losses":14,"wins":8},"claude-opus-5":{"draws":1,"losses":7,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":26,"losses":19,"wins":15},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":10,"wins":9},"gpt-5.4":{"draws":10,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":38,"losses":26,"wins":34},"gpt-5.4-nano":{"draws":32,"losses":24,"wins":24},"gpt-5.5":{"draws":17,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":7,"wins":12},"gpt-5.6-sol":{"draws":3,"losses":12,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":7,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":10},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":6},"o3":{"draws":13,"losses":7,"wins":10},"openai/gpt-oss-120b":{"draws":23,"losses":8,"wins":11},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":17,"losses":8,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":12,"wins":2},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":5,"wins":2},"x-ai/grok-4.5":{"draws":17,"losses":21,"wins":14},"xiaomi/mimo-v2.5":{"draws":24,"losses":26,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":9}},"gpt-5.5":{"claude-opus-4-5":{"draws":5,"losses":2,"wins":3},"claude-opus-4-8":{"draws":1,"losses":1,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":15,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":23,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":17,"losses":2,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"o3":{"draws":2,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":1},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":4,"losses":2,"wins":0},"claude-opus-4-8":{"draws":3,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":7},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":1},"gpt-5.4":{"draws":5,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":10,"losses":18,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":12,"wins":7},"gpt-5.5":{"draws":7,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":0},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":7,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":17,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":0}},"gpt-5.6-sol":{"claude-opus-4-5":{"draws":4,"losses":3,"wins":5},"claude-opus-4-8":{"draws":4,"losses":3,"wins":5},"claude-opus-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":9},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":12},"gpt-5.5":{"draws":5,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":3},"o3":{"draws":2,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.5":{"draws":4,"losses":6,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":4}},"gpt-5.6-terra":{"claude-opus-4-5":{"draws":5,"losses":3,"wins":2},"claude-opus-4-8":{"draws":6,"losses":3,"wins":3},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":2,"wins":18},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":6},"gpt-5.4":{"draws":0,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":4,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":6,"wins":2},"gpt-5.5":{"draws":6,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":9,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"o3":{"draws":4,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":12,"losses":8,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-5":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":10,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1}},"meituan/longcat-2.0":{"claude-opus-4-5":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":3,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":2,"losses":4,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0}},"minimax/minimax-m3":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":7,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":2,"losses":4,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":5},"gpt-5.5":{"draws":2,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"o3":{"draws":3,"losses":4,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":11,"wins":3},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":5},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":10,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":7,"losses":4,"wins":13},"claude-opus-4-8":{"draws":5,"losses":5,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":26},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":5},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":6,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":19,"losses":8,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":21},"gpt-5.5":{"draws":8,"losses":6,"wins":6},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":11},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":11},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":6},"o3":{"draws":6,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":12},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":14},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":22,"losses":20,"wins":20},"xiaomi/mimo-v2.5":{"draws":5,"losses":12,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":7}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":4,"losses":0,"wins":2},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":5,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":8},"gpt-5.5":{"draws":4,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":6,"wins":4},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3}},"o3":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":2},"claude-opus-4-8":{"draws":1,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":7},"gpt-5.5":{"draws":2,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.5":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":13},"gpt-5.4-nano":{"draws":23,"losses":11,"wins":8},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":1},"o3":{"draws":4,"losses":11,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":0}},"poolside/laguna-s-2.1":{"claude-opus-4-8":{"draws":0,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":1},"gpt-5.4":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":8,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":18,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2}},"qwen/qwen3.7-max":{"claude-opus-4-5":{"draws":1,"losses":4,"wins":3},"claude-opus-4-8":{"draws":2,"losses":3,"wins":3},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":2,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":5,"wins":8},"gpt-5.5":{"draws":1,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":5},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":8,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":4,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":8},"gpt-5.5":{"draws":5,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":9,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5.4":{"draws":3,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":13,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":12},"gpt-5.5":{"draws":1,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":1},"o3":{"draws":3,"losses":8,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":14,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":8,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":0}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":1,"losses":6,"wins":3},"claude-opus-4-8":{"draws":0,"losses":5,"wins":1},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":5,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":17,"losses":2,"wins":15},"gpt-5.5":{"draws":4,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":0},"o3":{"draws":6,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":2,"losses":1,"wins":1},"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":5},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":7},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":4,"losses":7,"wins":11},"claude-opus-4-8":{"draws":7,"losses":6,"wins":7},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":21},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":9},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":5},"gpt-5.4":{"draws":8,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":21,"losses":1,"wins":16},"gpt-5.4-nano":{"draws":17,"losses":14,"wins":21},"gpt-5.5":{"draws":5,"losses":1,"wins":8},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":9,"losses":10,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":2,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":22,"losses":20,"wins":20},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"o3":{"draws":8,"losses":7,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":11},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":14},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":8,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":8,"losses":7,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":10}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":5,"losses":6,"wins":5},"claude-opus-4-8":{"draws":0,"losses":12,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":21,"wins":21},"deepseek/deepseek-v4-pro":{"draws":1,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":6},"gpt-5.4":{"draws":10,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":29,"losses":18,"wins":31},"gpt-5.4-nano":{"draws":24,"losses":18,"wins":26},"gpt-5.5":{"draws":10,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":5,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":5},"o3":{"draws":4,"losses":4,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":9,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":9},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":8},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":7},"xiaomi/mimo-v2.5":{"draws":4,"losses":6,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":6}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":2,"losses":3,"wins":5},"claude-opus-4-8":{"draws":2,"losses":2,"wins":4},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":5},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":6},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":1},"o3":{"draws":4,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":10,"wins":4},"xiaomi/mimo-v2.5":{"draws":3,"losses":6,"wins":5}}}}}