{"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":"2026-07-28T14:34:29Z","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":12.66097},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6981,"mean":0.5046499999999999,"median":0.511355,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":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":80.38733150378229,"medium":67.29684314035639},"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":"2026-07-28T14:25:37Z","match_totals_all":{"draws":130,"losses":191,"wins":597},"match_totals_tracks":{"highest":{"draws":67,"losses":81,"wins":340},"medium":{"draws":63,"losses":110,"wins":257}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":74.62309235404214,"min":51.78455451097985},"per_game":{"GB2-01":62.704408645378294,"GB2-02":73.7853774932965,"GB2-03":69.97359637011016,"GB2-04":100.0,"GB2-05":93.05084396084196,"GB2-06":81.83872215206208,"GB2-07":61.74570340856937,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":44,"wins":78},"GB2-02":{"draws":58,"losses":12,"wins":56},"GB2-03":{"draws":21,"losses":4,"wins":19},"GB2-04":{"draws":34,"losses":16,"wins":70},"GB2-05":{"draws":0,"losses":33,"wins":93},"GB2-06":{"draws":16,"losses":24,"wins":76},"GB2-07":{"draws":0,"losses":42,"wins":86},"GB2-08":{"draws":1,"losses":16,"wins":119}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":24,"wins":38},"GB2-02":{"draws":27,"losses":3,"wins":32},"GB2-03":{"draws":21,"losses":4,"wins":19},"GB2-04":{"draws":9,"losses":1,"wins":48},"GB2-05":{"draws":0,"losses":8,"wins":58},"GB2-06":{"draws":9,"losses":11,"wins":40},"GB2-07":{"draws":0,"losses":26,"wins":40},"GB2-08":{"draws":1,"losses":4,"wins":65}},"medium":{"GB2-01":{"draws":0,"losses":20,"wins":40},"GB2-02":{"draws":31,"losses":9,"wins":24},"GB2-04":{"draws":25,"losses":15,"wins":22},"GB2-05":{"draws":0,"losses":25,"wins":35},"GB2-06":{"draws":7,"losses":13,"wins":36},"GB2-07":{"draws":0,"losses":16,"wins":46},"GB2-08":{"draws":0,"losses":12,"wins":54}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1623.8224065469774,"GB2-02":1675.2224541849737,"GB2-03":1646.2996143800208,"GB2-04":1828.795087741824,"GB2-05":1911.0343695647828,"GB2-06":1718.7719507864515,"GB2-07":1607.2707269530913,"GB2-08":1927.1900602587184},"medium":{"GB2-01":1683.5740198568387,"GB2-02":1636.8022098052088,"GB2-04":1581.0598602467503,"GB2-05":1576.0871543127037,"GB2-06":1680.7525107491392,"GB2-07":1732.9026765072072,"GB2-08":1763.0396484548678}},"per_game_tracks":{"highest":{"GB2-01":62.704408645378294,"GB2-02":73.7853774932965,"GB2-03":69.97359637011016,"GB2-04":100.0,"GB2-05":93.05084396084196,"GB2-06":81.83872215206208,"GB2-07":61.74570340856937,"GB2-08":100.0},"medium":{"GB2-01":69.93910267106604,"GB2-02":64.91511947130134,"GB2-04":51.78455451097985,"GB2-05":55.065570137094625,"GB2-06":76.68664750233343,"GB2-07":76.98200491889094,"GB2-08":75.70490277082847}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":84.15881738036836,"medium":65.08736732771592},"reasoning_agg":{"highest":{"max":100.0,"mean":84.15881738036836,"min":61.74570340856937},"medium":{"max":76.98200491889094,"mean":65.08736732771592,"min":51.78455451097985}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":19.071450052652438},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":76.10480871808986,"reliability_score":79.85685254467585,"uncertainty_avg":20.14314745532415,"uncertainty_penalty":-8.054008662278505},"medium":{"ceiling_score":76.98200491889094,"expected_score":81.79437071968256,"reliability_score":80.41375072447894,"uncertainty_avg":19.58624927552106,"uncertainty_penalty":16.707003391966637}}},{"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":7.138875},"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":4.570124999999999}},"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":72.09051748873722,"highest":80.20818917067336,"medium":73.06844747533235,"none":66.42978277273602},"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":"2026-07-28T14:18:41Z","match_totals_all":{"draws":323,"losses":464,"wins":1249},"match_totals_tracks":{"highest":{"draws":40,"losses":100,"wins":380},"medium":{"draws":110,"losses":187,"wins":487},"none":{"draws":173,"losses":177,"wins":382}},"model_slug":"claude-opus-5","overall":{"max":99.02178558841968,"mean":67.82700699982587,"min":43.031718018905565},"per_game":{"GB2-01":63.5580052854085,"GB2-02":77.81176707216713,"GB2-03":99.02178558841968,"GB2-04":72.51837780315306,"GB2-05":86.60887405745,"GB2-07":98.00725670704736,"GB2-08":63.931257681067805},"per_game_all":{"GB2-01":65.01291684613346,"GB2-02":68.21894556872807,"GB2-03":80.89964501810233,"GB2-04":54.50197632509555,"GB2-05":84.61034645220742,"GB2-07":89.72410637274292,"GB2-08":61.66568583815083},"per_game_match_totals_all":{"GB2-01":{"draws":57,"losses":80,"wins":161},"GB2-02":{"draws":122,"losses":46,"wins":134},"GB2-03":{"draws":18,"losses":51,"wins":185},"GB2-04":{"draws":113,"losses":70,"wins":125},"GB2-05":{"draws":0,"losses":69,"wins":261},"GB2-06":{"draws":13,"losses":8,"wins":39},"GB2-07":{"draws":0,"losses":46,"wins":170},"GB2-08":{"draws":0,"losses":94,"wins":174}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":30,"wins":50},"GB2-02":{"draws":19,"losses":14,"wins":47},"GB2-03":{"draws":1,"losses":6,"wins":73},"GB2-04":{"draws":20,"losses":11,"wins":49},"GB2-05":{"draws":0,"losses":12,"wins":68},"GB2-07":{"draws":0,"losses":1,"wins":39},"GB2-08":{"draws":0,"losses":26,"wins":54}},"medium":{"GB2-01":{"draws":7,"losses":36,"wins":65},"GB2-02":{"draws":50,"losses":17,"wins":43},"GB2-03":{"draws":2,"losses":13,"wins":71},"GB2-04":{"draws":51,"losses":27,"wins":34},"GB2-05":{"draws":0,"losses":28,"wins":96},"GB2-07":{"draws":0,"losses":25,"wins":93},"GB2-08":{"draws":0,"losses":41,"wins":85}},"none":{"GB2-01":{"draws":50,"losses":14,"wins":46},"GB2-02":{"draws":53,"losses":15,"wins":44},"GB2-03":{"draws":15,"losses":32,"wins":41},"GB2-04":{"draws":42,"losses":32,"wins":42},"GB2-05":{"draws":0,"losses":29,"wins":97},"GB2-06":{"draws":13,"losses":8,"wins":39},"GB2-07":{"draws":0,"losses":20,"wins":38},"GB2-08":{"draws":0,"losses":27,"wins":35}}},"per_game_raw_elo_all":{"GB2-01":1648.8530894885353,"GB2-02":1657.510479860519,"GB2-03":1712.8256806100414,"GB2-04":1600.3900174706648,"GB2-05":1841.508098452917,"GB2-07":1841.6925767805842,"GB2-08":1672.7983530987606},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1642.849846697788,"GB2-02":1704.3817428101302,"GB2-03":1822.8828293617457,"GB2-04":1698.9437508475796,"GB2-05":1867.433954839337,"GB2-07":1916.2342017734409,"GB2-08":1696.415694488106},"medium":{"GB2-01":1629.885059755668,"GB2-02":1642.4683990952587,"GB2-03":1788.4865800158111,"GB2-04":1539.0025601678449,"GB2-05":1814.0825093123558,"GB2-07":1848.840737027007,"GB2-08":1748.7093955874852},"none":{"GB2-01":1673.8243620121498,"GB2-02":1625.6812976761676,"GB2-03":1527.1076324525677,"GB2-04":1563.2237413965695,"GB2-05":1843.0078312070582,"GB2-06":1785.4552045796995,"GB2-07":1760.002791541305,"GB2-08":1573.2699692206909}},"per_game_tracks":{"highest":{"GB2-01":63.5580052854085,"GB2-02":77.81176707216713,"GB2-03":99.02178558841968,"GB2-04":72.51837780315306,"GB2-05":86.60887405745,"GB2-07":98.00725670704736,"GB2-08":63.931257681067805},"medium":{"GB2-01":63.01400841641588,"GB2-02":65.34437395588908,"GB2-03":93.63142007950454,"GB2-04":43.031718018905565,"GB2-05":81.96033299327031,"GB2-07":91.0622676929581,"GB2-08":73.43501117038298},"none":{"GB2-01":68.46673683657603,"GB2-02":61.500695678128025,"GB2-03":50.04572938638278,"GB2-04":47.95583315322803,"GB2-05":85.26183230590198,"GB2-06":90.4738514404464,"GB2-07":80.1027947182233,"GB2-08":47.63078866300169}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":73.33436600851381,"medium":70.6694795619753,"none":59.47717542898852},"reasoning_agg":{"highest":{"max":99.02178558841968,"mean":73.33436600851381,"min":63.5580052854085},"medium":{"max":93.63142007950454,"mean":70.6694795619753,"min":43.031718018905565},"none":{"max":85.26183230590198,"mean":59.47717542898852,"min":47.95583315322803}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":99.02178558841968,"expected_score":83.01953214459755,"reasoning_variance":13.857190579525295,"reliability_score":73.47096794934797,"uncertainty_avg":26.52903205065203,"uncertainty_penalty":15.192525144771679},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.02178558841968,"expected_score":77.93733495941987,"reliability_score":65.66311905569697,"uncertainty_avg":34.33688094430304,"uncertainty_penalty":4.60296895090606},"medium":{"ceiling_score":93.63142007950454,"expected_score":88.52142080951928,"reliability_score":77.18582842847614,"uncertainty_avg":22.81417157152386,"uncertainty_penalty":17.85194124754399},"none":{"ceiling_score":85.26183230590198,"expected_score":84.47225510138824,"reliability_score":77.83490682258096,"uncertainty_avg":22.165093177419042,"uncertainty_penalty":24.995079672399726}}},{"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":0.7485200000000001}},"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":25.878315000000004},"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":58.5246253055008,"highest":72.47604047855889,"medium":49.63045599352372,"none":53.4673794444198},"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":"2026-07-28T14:20:36Z","match_totals_all":{"draws":503,"losses":351,"wins":745},"match_totals_tracks":{"highest":{"draws":106,"losses":87,"wins":315},"medium":{"draws":185,"losses":133,"wins":192},"none":{"draws":212,"losses":131,"wins":238}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":58.5246253055008,"min":23.37882885928049},"per_game":{"GB2-01":100.0,"GB2-02":57.0207132983657,"GB2-03":39.257429797226955,"GB2-04":60.07708164277407,"GB2-05":97.41208001073208,"GB2-06":91.4951323889829,"GB2-07":92.41708874989084,"GB2-08":42.12879794049859},"per_game_all":{"GB2-01":87.04211284440312,"GB2-02":36.796593617775734,"GB2-03":41.56880829179471,"GB2-04":45.31560752101541,"GB2-05":75.31227058190512,"GB2-06":86.4958424202768,"GB2-07":62.01284070596004,"GB2-08":33.65292646087547},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":21,"wins":151},"GB2-02":{"draws":166,"losses":14,"wins":24},"GB2-03":{"draws":71,"losses":47,"wins":40},"GB2-04":{"draws":124,"losses":28,"wins":56},"GB2-05":{"draws":0,"losses":63,"wins":161},"GB2-06":{"draws":25,"losses":28,"wins":124},"GB2-07":{"draws":0,"losses":79,"wins":133},"GB2-08":{"draws":89,"losses":71,"wins":56}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":62},"GB2-02":{"draws":39,"losses":7,"wins":20},"GB2-03":{"draws":14,"losses":18,"wins":14},"GB2-04":{"draws":28,"losses":13,"wins":29},"GB2-05":{"draws":0,"losses":4,"wins":62},"GB2-06":{"draws":8,"losses":9,"wins":39},"GB2-07":{"draws":0,"losses":6,"wins":62},"GB2-08":{"draws":17,"losses":28,"wins":27}},"medium":{"GB2-01":{"draws":26,"losses":13,"wins":27},"GB2-02":{"draws":59,"losses":6,"wins":3},"GB2-03":{"draws":25,"losses":19,"wins":12},"GB2-04":{"draws":43,"losses":7,"wins":16},"GB2-05":{"draws":0,"losses":34,"wins":36},"GB2-06":{"draws":11,"losses":4,"wins":43},"GB2-07":{"draws":0,"losses":24,"wins":36},"GB2-08":{"draws":21,"losses":26,"wins":19}},"none":{"GB2-01":{"draws":2,"losses":6,"wins":62},"GB2-02":{"draws":68,"losses":1,"wins":1},"GB2-03":{"draws":32,"losses":10,"wins":14},"GB2-04":{"draws":53,"losses":8,"wins":11},"GB2-05":{"draws":0,"losses":25,"wins":63},"GB2-06":{"draws":6,"losses":15,"wins":42},"GB2-07":{"draws":0,"losses":49,"wins":35},"GB2-08":{"draws":51,"losses":17,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1820.3273654562527,"GB2-02":1516.0383585506233,"GB2-03":1471.5467660409352,"GB2-04":1545.37051769354,"GB2-05":1750.901404404245,"GB2-06":1755.2066033271788,"GB2-07":1608.1639280434647,"GB2-08":1474.5253954642149},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1926.8421962372731,"GB2-02":1602.558018732674,"GB2-03":1461.2984840176907,"GB2-04":1620.454608682286,"GB2-05":1949.760418649385,"GB2-06":1795.1084078077092,"GB2-07":1856.3853633771,"GB2-08":1532.2005706493428},"medium":{"GB2-01":1666.0791613055155,"GB2-02":1459.0930765758949,"GB2-03":1400.8815780438904,"GB2-04":1521.843945614986,"GB2-05":1535.7359811804806,"GB2-06":1815.6398626593548,"GB2-07":1590.5823542815288,"GB2-08":1454.5300578111446},"none":{"GB2-01":1868.06073882597,"GB2-02":1486.4639803433008,"GB2-03":1552.4602360612246,"GB2-04":1493.812998783348,"GB2-05":1767.2078133828695,"GB2-06":1654.8715395144725,"GB2-07":1377.5240664717653,"GB2-08":1436.845557932157}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-02":57.0207132983657,"GB2-03":39.257429797226955,"GB2-04":60.07708164277407,"GB2-05":97.41208001073208,"GB2-06":91.4951323889829,"GB2-07":92.41708874989084,"GB2-08":42.12879794049859},"medium":{"GB2-01":68.07950047101149,"GB2-02":23.37882885928049,"GB2-03":30.053178186490474,"GB2-04":40.48027638959632,"GB2-05":50.942898959824795,"GB2-06":94.2711346278566,"GB2-07":59.4087344158915,"GB2-08":30.42909603823807},"none":{"GB2-01":93.0468380621979,"GB2-02":29.99023869568103,"GB2-03":55.3958168916667,"GB2-04":35.38946453067582,"GB2-05":77.5818327751585,"GB2-06":73.72126024399091,"GB2-07":34.212698952097796,"GB2-08":28.40088540388973}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.47604047855889,"medium":49.63045599352372,"none":53.4673794444198},"reasoning_agg":{"highest":{"max":100.0,"mean":72.47604047855889,"min":39.257429797226955},"medium":{"max":94.2711346278566,"mean":49.63045599352372,"min":23.37882885928049},"none":{"max":93.0468380621979,"mean":53.4673794444198,"min":28.40088540388973}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":56.87718357148253,"reasoning_variance":22.845584485035168,"reliability_score":82.54431423446314,"uncertainty_avg":17.455685765536863,"uncertainty_penalty":-1.6474417340182654},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":65.81517302659519,"reliability_score":81.07518646203107,"uncertainty_avg":18.924813537968934,"uncertainty_penalty":-6.660867451963696},"medium":{"ceiling_score":94.2711346278566,"expected_score":47.312308226982026,"reliability_score":81.4842888378566,"uncertainty_avg":18.515711162143404,"uncertainty_penalty":-2.318147766541692},"none":{"ceiling_score":93.0468380621979,"expected_score":57.504069460870376,"reliability_score":85.07346740350175,"uncertainty_avg":14.926532596498255,"uncertainty_penalty":4.036690016450578}}},{"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":4.11992},"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":57.00071474862776,"highest":65.92857554596691,"medium":58.3496660036598,"none":46.723902696256566},"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":"2026-07-28T14:25:47Z","match_totals_all":{"draws":343,"losses":478,"wins":783},"match_totals_tracks":{"highest":{"draws":60,"losses":151,"wins":313},"medium":{"draws":118,"losses":145,"wins":245},"none":{"draws":165,"losses":182,"wins":225}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":57.000714748627765,"min":15.76739369307706},"per_game":{"GB2-01":74.74012604307732,"GB2-02":100.0,"GB2-03":61.27330594787659,"GB2-04":65.31698730595153,"GB2-05":72.72864039076802,"GB2-06":78.34793491234177,"GB2-07":59.254216074642976,"GB2-08":15.76739369307706},"per_game_all":{"GB2-01":64.28646149103531,"GB2-02":59.87187885122464,"GB2-03":56.02765386186278,"GB2-04":43.65966214855288,"GB2-05":64.98650297435215,"GB2-06":66.46713834306064,"GB2-07":61.573227239397454,"GB2-08":39.1331930795362},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":65,"wins":116},"GB2-02":{"draws":92,"losses":21,"wins":75},"GB2-03":{"draws":53,"losses":48,"wins":71},"GB2-04":{"draws":142,"losses":13,"wins":35},"GB2-05":{"draws":0,"losses":79,"wins":149},"GB2-06":{"draws":17,"losses":85,"wins":102},"GB2-07":{"draws":0,"losses":86,"wins":134},"GB2-08":{"draws":24,"losses":81,"wins":101}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":17,"wins":45},"GB2-02":{"draws":11,"losses":4,"wins":45},"GB2-03":{"draws":5,"losses":16,"wins":29},"GB2-04":{"draws":26,"losses":2,"wins":26},"GB2-05":{"draws":0,"losses":25,"wins":55},"GB2-06":{"draws":6,"losses":21,"wins":31},"GB2-07":{"draws":0,"losses":30,"wins":62},"GB2-08":{"draws":12,"losses":36,"wins":20}},"medium":{"GB2-01":{"draws":0,"losses":29,"wins":33},"GB2-02":{"draws":30,"losses":11,"wins":23},"GB2-03":{"draws":14,"losses":12,"wins":24},"GB2-04":{"draws":59,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":29,"wins":45},"GB2-06":{"draws":10,"losses":13,"wins":37},"GB2-07":{"draws":0,"losses":25,"wins":35},"GB2-08":{"draws":5,"losses":19,"wins":44}},"none":{"GB2-01":{"draws":15,"losses":19,"wins":38},"GB2-02":{"draws":51,"losses":6,"wins":7},"GB2-03":{"draws":34,"losses":20,"wins":18},"GB2-04":{"draws":57,"losses":4,"wins":5},"GB2-05":{"draws":0,"losses":25,"wins":49},"GB2-06":{"draws":1,"losses":51,"wins":34},"GB2-07":{"draws":0,"losses":31,"wins":37},"GB2-08":{"draws":7,"losses":26,"wins":37}}},"per_game_raw_elo_all":{"GB2-01":1635.5165040515421,"GB2-02":1615.9360115502652,"GB2-03":1556.2043553331544,"GB2-04":1539.2930099306616,"GB2-05":1658.5731864417278,"GB2-06":1597.5778094908483,"GB2-07":1603.947130272841,"GB2-08":1512.8986937317861},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1721.8625437609876,"GB2-02":1787.2775916050075,"GB2-03":1590.6444127760449,"GB2-04":1653.6598205873045,"GB2-05":1726.1579161055558,"GB2-06":1692.6757781194096,"GB2-07":1579.5870696464758,"GB2-08":1353.9117026482218},"medium":{"GB2-01":1603.5304016092489,"GB2-02":1557.8041669293343,"GB2-03":1582.5689592229082,"GB2-04":1483.3945244178965,"GB2-05":1637.7720719272563,"GB2-06":1699.206178915541,"GB2-07":1620.732869774357,"GB2-08":1669.960028561512},"none":{"GB2-01":1581.1565667843893,"GB2-02":1502.7262761164538,"GB2-03":1495.3996940005095,"GB2-04":1480.824684786784,"GB2-05":1611.7895712923712,"GB2-06":1400.8514714375945,"GB2-07":1611.5214513976898,"GB2-08":1514.8243499856248}},"per_game_tracks":{"highest":{"GB2-01":74.74012604307732,"GB2-02":100.0,"GB2-03":61.27330594787659,"GB2-04":65.31698730595153,"GB2-05":72.72864039076802,"GB2-06":78.34793491234177,"GB2-07":59.254216074642976,"GB2-08":15.76739369307706},"medium":{"GB2-01":60.21329792477527,"GB2-02":46.29785153237801,"GB2-03":59.92316006022683,"GB2-04":33.21961073407453,"GB2-05":62.57847814892709,"GB2-06":79.30505799919712,"GB2-07":63.110312337324274,"GB2-08":62.149559292375265},"none":{"GB2-01":57.90596050525336,"GB2-02":33.31778502129591,"GB2-03":46.88649557748494,"GB2-04":32.44238840563259,"GB2-05":59.65239038336131,"GB2-06":41.748422117643045,"GB2-07":62.35515330622509,"GB2-08":39.48262625315627}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.92857554596692,"medium":58.3496660036598,"none":46.723902696256566},"reasoning_agg":{"highest":{"max":100.0,"mean":65.92857554596692,"min":15.76739369307706},"medium":{"max":79.30505799919712,"mean":58.3496660036598,"min":33.21961073407453},"none":{"max":62.35515330622509,"mean":46.723902696256566,"min":32.44238840563259}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":55.47314206778246,"reasoning_variance":19.204672849710356,"reliability_score":82.56323758366474,"uncertainty_avg":17.43676241633525,"uncertainty_penalty":-1.527572680845303},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":57.99182433996336,"reliability_score":81.60787105319784,"uncertainty_avg":18.392128946802156,"uncertainty_penalty":-7.936751206003564},"medium":{"ceiling_score":79.30505799919712,"expected_score":60.038905364017616,"reliability_score":81.20882917058603,"uncertainty_avg":18.791170829413968,"uncertainty_penalty":1.689239360357817},"none":{"ceiling_score":62.35515330622509,"expected_score":48.38869649936643,"reliability_score":84.87301252721038,"uncertainty_avg":15.126987472789624,"uncertainty_penalty":1.6647938031098661}}},{"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":0.1445437333333333,"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":2.2045856},"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":0.1445437333333333,"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":52.981291040061954,"highest":50.39021644914183,"medium":60.99204288781914,"none":47.5616137832249},"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":"2026-07-28T14:25:47Z","match_totals_all":{"draws":1007,"losses":1205,"wins":2032},"match_totals_tracks":{"highest":{"draws":269,"losses":495,"wins":752},"medium":{"draws":383,"losses":447,"wins":824},"none":{"draws":355,"losses":263,"wins":456}},"model_slug":"x-ai-grok-4-5","overall":{"max":86.61059058414996,"mean":52.981291040061954,"min":20.06411053869428},"per_game":{"GB2-01":65.72459535642689,"GB2-02":36.887230400044366,"GB2-03":44.48085335142255,"GB2-04":23.01874596426968,"GB2-05":50.706212366897766,"GB2-06":56.045641036495276,"GB2-07":60.45462370250504,"GB2-08":65.80382941507308},"per_game_all":{"GB2-01":63.15525569642055,"GB2-02":33.90782025720524,"GB2-03":38.78364208289905,"GB2-04":28.740075533247307,"GB2-05":59.188926441140346,"GB2-06":57.77778699697436,"GB2-07":68.32261752474955,"GB2-08":73.97420378785922},"per_game_match_totals_all":{"GB2-01":{"draws":139,"losses":140,"wins":307},"GB2-02":{"draws":288,"losses":72,"wins":76},"GB2-03":{"draws":155,"losses":121,"wins":84},"GB2-04":{"draws":374,"losses":96,"wins":68},"GB2-05":{"draws":0,"losses":196,"wins":336},"GB2-06":{"draws":49,"losses":252,"wins":303},"GB2-07":{"draws":0,"losses":212,"wins":400},"GB2-08":{"draws":2,"losses":116,"wins":458}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":51,"wins":135},"GB2-02":{"draws":81,"losses":32,"wins":37},"GB2-03":{"draws":28,"losses":16,"wins":18},"GB2-04":{"draws":111,"losses":52,"wins":25},"GB2-05":{"draws":0,"losses":71,"wins":87},"GB2-06":{"draws":13,"losses":113,"wins":124},"GB2-07":{"draws":0,"losses":105,"wins":147},"GB2-08":{"draws":0,"losses":55,"wins":179}},"medium":{"GB2-01":{"draws":25,"losses":72,"wins":127},"GB2-02":{"draws":87,"losses":23,"wins":34},"GB2-03":{"draws":77,"losses":40,"wins":51},"GB2-04":{"draws":167,"losses":32,"wins":31},"GB2-05":{"draws":0,"losses":79,"wins":153},"GB2-06":{"draws":26,"losses":88,"wins":114},"GB2-07":{"draws":0,"losses":81,"wins":141},"GB2-08":{"draws":1,"losses":32,"wins":173}},"none":{"GB2-01":{"draws":78,"losses":17,"wins":45},"GB2-02":{"draws":120,"losses":17,"wins":5},"GB2-03":{"draws":50,"losses":65,"wins":15},"GB2-04":{"draws":96,"losses":12,"wins":12},"GB2-05":{"draws":0,"losses":46,"wins":96},"GB2-06":{"draws":10,"losses":51,"wins":65},"GB2-07":{"draws":0,"losses":26,"wins":112},"GB2-08":{"draws":1,"losses":29,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1633.56731513838,"GB2-02":1517.4459666001667,"GB2-03":1462.4225734415586,"GB2-04":1487.2079413762433,"GB2-05":1631.767604429334,"GB2-06":1552.454338480679,"GB2-07":1667.3823466438116,"GB2-08":1759.2117919305722},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1663.127142294277,"GB2-02":1533.4752294950556,"GB2-03":1507.1323125710758,"GB2-04":1455.4390079146517,"GB2-05":1550.369504829626,"GB2-06":1530.5492972977293,"GB2-07":1609.3010651060551,"GB2-08":1710.3540516958967},"medium":{"GB2-01":1644.5260306020293,"GB2-02":1549.0166075465095,"GB2-03":1524.8855862121954,"GB2-04":1500.510290400215,"GB2-05":1719.484226583034,"GB2-06":1579.195747736713,"GB2-07":1646.2295132227264,"GB2-08":1836.5603873772036},"none":{"GB2-01":1593.0487725188343,"GB2-02":1469.8460627589345,"GB2-03":1355.2498215414046,"GB2-04":1505.6745258138637,"GB2-05":1625.4490818753422,"GB2-06":1547.6179704075944,"GB2-07":1746.6164616026535,"GB2-08":1730.720936718617}},"per_game_tracks":{"highest":{"GB2-01":65.72459535642689,"GB2-02":36.887230400044366,"GB2-03":44.48085335142255,"GB2-04":23.01874596426968,"GB2-05":50.706212366897766,"GB2-06":56.045641036495276,"GB2-07":60.45462370250504,"GB2-08":65.80382941507308},"medium":{"GB2-01":65.7709894643359,"GB2-02":44.77211983287708,"GB2-03":50.701240605907714,"GB2-04":36.956930719369936,"GB2-05":71.86873515540026,"GB2-06":64.42879546936034,"GB2-07":66.82694127115185,"GB2-08":86.61059058414996},"none":{"GB2-01":57.97018226849887,"GB2-02":20.06411053869428,"GB2-03":21.168832291366886,"GB2-04":26.244549916102308,"GB2-05":54.991831801123,"GB2-06":52.858924485067476,"GB2-07":77.68628760059177,"GB2-08":69.50819136435463}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.39021644914183,"medium":60.992042887819146,"none":47.5616137832249},"reasoning_agg":{"highest":{"max":65.80382941507308,"mean":50.39021644914183,"min":23.01874596426968},"medium":{"max":86.61059058414996,"mean":60.992042887819146,"min":36.956930719369936},"none":{"max":77.68628760059177,"mean":47.5616137832249,"min":20.06411053869428}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":86.61059058414996,"expected_score":52.54897110108642,"reasoning_variance":13.430429104594246,"reliability_score":68.90821548858057,"uncertainty_avg":31.09178451141944,"uncertainty_penalty":-0.43231993897553167},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.80382941507308,"expected_score":39.358508621912776,"reliability_score":61.52040437540823,"uncertainty_avg":38.47959562459177,"uncertainty_penalty":-11.031707827229056},"medium":{"ceiling_score":86.61059058414996,"expected_score":62.79573813472609,"reliability_score":84.62104038470034,"uncertainty_avg":15.378959615299665,"uncertainty_penalty":1.8036952469069476},"none":{"ceiling_score":77.68628760059177,"expected_score":55.492666546620384,"reliability_score":60.58320170563311,"uncertainty_avg":39.41679829436689,"uncertainty_penalty":7.931052763395485}}},{"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":26.56635},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":53.9035987896573,"highest":68.7855806469871,"medium":49.16424774014156,"none":43.20325003699843},"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":"2026-07-28T14:25:45Z","match_totals_all":{"draws":529,"losses":372,"wins":562},"match_totals_tracks":{"highest":{"draws":105,"losses":101,"wins":257},"medium":{"draws":163,"losses":160,"wins":177},"none":{"draws":261,"losses":111,"wins":128}},"model_slug":"gpt-5-5","overall":{"max":89.33624367595237,"mean":52.49209488925097,"min":26.067793284414353},"per_game":{"GB2-01":76.88892728812435,"GB2-03":48.1183769229996,"GB2-04":30.607667525230426,"GB2-05":84.55237440881977,"GB2-06":85.09250284379188,"GB2-07":89.33624367595237,"GB2-08":66.90297186399128},"per_game_all":{"GB2-01":60.99268147282209,"GB2-03":46.682779626909216,"GB2-04":30.9818765093524,"GB2-05":69.27428198686731,"GB2-07":68.9366787632974,"GB2-08":46.55329437869542},"per_game_match_totals_all":{"GB2-01":{"draws":122,"losses":28,"wins":62},"GB2-02":{"draws":104,"losses":14,"wins":16},"GB2-03":{"draws":66,"losses":39,"wins":38},"GB2-04":{"draws":137,"losses":39,"wins":26},"GB2-05":{"draws":0,"losses":75,"wins":141},"GB2-06":{"draws":8,"losses":58,"wins":68},"GB2-07":{"draws":0,"losses":66,"wins":142},"GB2-08":{"draws":92,"losses":53,"wins":69}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":12,"wins":31},"GB2-03":{"draws":21,"losses":15,"wins":11},"GB2-04":{"draws":44,"losses":13,"wins":11},"GB2-05":{"draws":0,"losses":17,"wins":55},"GB2-06":{"draws":8,"losses":20,"wins":42},"GB2-07":{"draws":0,"losses":8,"wins":62},"GB2-08":{"draws":11,"losses":16,"wins":45}},"medium":{"GB2-01":{"draws":39,"losses":3,"wins":18},"GB2-02":{"draws":34,"losses":12,"wins":16},"GB2-03":{"draws":23,"losses":14,"wins":9},"GB2-04":{"draws":41,"losses":14,"wins":9},"GB2-05":{"draws":0,"losses":27,"wins":43},"GB2-06":{"draws":0,"losses":38,"wins":26},"GB2-07":{"draws":0,"losses":29,"wins":37},"GB2-08":{"draws":26,"losses":23,"wins":19}},"none":{"GB2-01":{"draws":62,"losses":13,"wins":13},"GB2-02":{"draws":70,"losses":2,"wins":0},"GB2-03":{"draws":22,"losses":10,"wins":18},"GB2-04":{"draws":52,"losses":12,"wins":6},"GB2-05":{"draws":0,"losses":31,"wins":43},"GB2-07":{"draws":0,"losses":29,"wins":43},"GB2-08":{"draws":55,"losses":14,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1607.2266681950398,"GB2-03":1504.7288507939168,"GB2-04":1472.916733381882,"GB2-05":1697.8653858654382,"GB2-07":1664.6942044196958,"GB2-08":1562.5855948523022},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1738.5848065889888,"GB2-03":1513.6863551335346,"GB2-04":1470.7482297231588,"GB2-05":1833.5200064511591,"GB2-06":1740.1552092126217,"GB2-07":1830.6078371029448,"GB2-08":1701.0119250403293},"medium":{"GB2-01":1590.4682109147573,"GB2-02":1542.631132430455,"GB2-03":1468.040920087715,"GB2-04":1449.039720517403,"GB2-05":1666.0116361417768,"GB2-06":1439.3647361655196,"GB2-07":1671.308501921656,"GB2-08":1551.251508726565},"none":{"GB2-01":1492.6269870813733,"GB2-02":1500.601598880668,"GB2-03":1532.4592771605007,"GB2-04":1498.9622499050838,"GB2-05":1594.0645150033788,"GB2-07":1492.1662742344863,"GB2-08":1435.4933507900123}},"per_game_tracks":{"highest":{"GB2-01":76.88892728812435,"GB2-03":48.1183769229996,"GB2-04":30.607667525230426,"GB2-05":84.55237440881977,"GB2-06":85.09250284379188,"GB2-07":89.33624367595237,"GB2-08":66.90297186399128},"medium":{"GB2-01":58.50913902194425,"GB2-02":42.53791776371207,"GB2-03":40.38470670777879,"GB2-04":26.067793284414353,"GB2-05":65.61423508293475,"GB2-06":45.864265764444326,"GB2-07":69.6076192029346,"GB2-08":44.7283050929694},"none":{"GB2-01":47.579978108397675,"GB2-02":33.47633212325143,"GB2-03":51.54525524994926,"GB2-04":36.27016871841243,"GB2-05":57.656236468847425,"GB2-07":47.8661734110052,"GB2-08":28.028606179125585}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.52722691736305,"medium":49.16424774014156,"none":41.78481001024829},"reasoning_agg":{"highest":{"max":89.33624367595237,"mean":66.52722691736305,"min":30.607667525230426},"medium":{"max":69.6076192029346,"mean":49.16424774014156,"min":26.067793284414353},"none":{"max":57.656236468847425,"mean":41.78481001024829,"min":28.028606179125585}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":89.33624367595237,"expected_score":50.69721077406684,"reasoning_variance":24.74241690711476,"reliability_score":82.26733606776965,"uncertainty_avg":17.732663932230352,"uncertainty_penalty":-1.7948841151841322},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.33624367595237,"expected_score":60.72428958454484,"reliability_score":82.30737278547029,"uncertainty_avg":17.692627214529708,"uncertainty_penalty":-5.80293733281821},"medium":{"ceiling_score":69.6076192029346,"expected_score":44.60690794213204,"reliability_score":80.6754399037244,"uncertainty_avg":19.3245600962756,"uncertainty_penalty":-4.557339798009522},"none":{"ceiling_score":57.656236468847425,"expected_score":44.62761282102929,"reliability_score":84.4836882649333,"uncertainty_avg":15.516311735066697,"uncertainty_penalty":2.842802810780995}}},{"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":7.107715},"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":{"none":47.922122724611484},"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":{"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}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-07-28T14:25:39Z","match_totals_all":{"draws":196,"losses":158,"wins":212},"match_totals_tracks":{"none":{"draws":196,"losses":158,"wins":212}},"model_slug":"claude-opus-4-5","overall":{"max":61.56795396592303,"mean":47.92212272461148,"min":33.709793544320256},"per_game_match_totals_all":{"GB2-01":{"draws":42,"losses":15,"wins":11},"GB2-02":{"draws":65,"losses":6,"wins":3},"GB2-03":{"draws":40,"losses":9,"wins":9},"GB2-04":{"draws":40,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":27,"wins":51},"GB2-06":{"draws":3,"losses":36,"wins":39},"GB2-07":{"draws":0,"losses":34,"wins":34},"GB2-08":{"draws":6,"losses":20,"wins":56}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":42,"losses":15,"wins":11},"GB2-02":{"draws":65,"losses":6,"wins":3},"GB2-03":{"draws":40,"losses":9,"wins":9},"GB2-04":{"draws":40,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":27,"wins":51},"GB2-06":{"draws":3,"losses":36,"wins":39},"GB2-07":{"draws":0,"losses":34,"wins":34},"GB2-08":{"draws":6,"losses":20,"wins":56}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1424.8775888544635,"GB2-02":1500.9638007338544,"GB2-03":1548.522194338608,"GB2-04":1533.6903460135152,"GB2-05":1525.0054661960344,"GB2-06":1491.4086342006274,"GB2-07":1503.5474590816427,"GB2-08":1661.7483294998035}},"per_game_tracks":{"none":{"GB2-01":38.55641611027493,"GB2-02":33.709793544320256,"GB2-03":54.88884061800323,"GB2-04":42.34172688645558,"GB2-05":50.01236594378325,"GB2-06":53.20069535861266,"GB2-07":49.099189369518875,"GB2-08":61.56795396592303}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":47.92212272461148},"reasoning_agg":{"none":{"max":61.56795396592303,"mean":47.92212272461148,"min":33.709793544320256}},"reasoning_labels":{"highest":"Extended thinking (legacy shared budget)","medium":"Extended thinking (legacy shared budget)","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":61.56795396592303},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":61.56795396592303,"expected_score":55.2632379242144,"reliability_score":84.42191305637009,"uncertainty_avg":15.57808694362991,"uncertainty_penalty":7.341115199602925}}},{"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":53.97967371240111,"highest":66.76147745764041,"medium":45.8960185527516,"none":48.16693819379286},"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":"2026-07-28T14:20:19Z","match_totals_all":{"draws":359,"losses":422,"wins":643},"match_totals_tracks":{"highest":{"draws":61,"losses":130,"wins":259},"medium":{"draws":178,"losses":127,"wins":165},"none":{"draws":120,"losses":165,"wins":219}},"model_slug":"claude-opus-4-8","overall":{"max":80.54297967705504,"mean":47.316220903559866,"min":25.370766045966345},"per_game":{"GB2-01":59.935555530461315,"GB2-02":90.47270926865744,"GB2-04":51.78950505760701,"GB2-05":51.146338598706805,"GB2-06":81.37204287643961,"GB2-07":65.67069489296186,"GB2-08":66.94349597864887},"per_game_all":{"GB2-01":54.75401245377091,"GB2-02":47.846258231112785,"GB2-04":37.33482028365513,"GB2-05":45.92534989891596,"GB2-06":72.73232111964406,"GB2-07":66.41305360027094,"GB2-08":52.851900399438044},"per_game_match_totals_all":{"GB2-01":{"draws":34,"losses":66,"wins":90},"GB2-02":{"draws":121,"losses":13,"wins":42},"GB2-03":{"draws":25,"losses":10,"wins":7},"GB2-04":{"draws":119,"losses":26,"wins":35},"GB2-05":{"draws":0,"losses":118,"wins":104},"GB2-06":{"draws":9,"losses":70,"wins":125},"GB2-07":{"draws":0,"losses":67,"wins":127},"GB2-08":{"draws":51,"losses":52,"wins":113}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":20,"wins":38},"GB2-02":{"draws":20,"losses":3,"wins":37},"GB2-04":{"draws":30,"losses":10,"wins":26},"GB2-05":{"draws":0,"losses":40,"wins":30},"GB2-06":{"draws":3,"losses":16,"wins":39},"GB2-07":{"draws":0,"losses":21,"wins":39},"GB2-08":{"draws":0,"losses":20,"wins":50}},"medium":{"GB2-01":{"draws":9,"losses":26,"wins":23},"GB2-02":{"draws":45,"losses":3,"wins":2},"GB2-03":{"draws":25,"losses":10,"wins":7},"GB2-04":{"draws":47,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":30,"wins":40},"GB2-06":{"draws":1,"losses":21,"wins":42},"GB2-07":{"draws":0,"losses":21,"wins":43},"GB2-08":{"draws":51,"losses":9,"wins":4}},"none":{"GB2-01":{"draws":17,"losses":20,"wins":29},"GB2-02":{"draws":56,"losses":7,"wins":3},"GB2-04":{"draws":42,"losses":9,"wins":5},"GB2-05":{"draws":0,"losses":48,"wins":34},"GB2-06":{"draws":5,"losses":33,"wins":44},"GB2-07":{"draws":0,"losses":25,"wins":45},"GB2-08":{"draws":0,"losses":23,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1558.6021166851297,"GB2-02":1566.791820849261,"GB2-04":1508.2323667600401,"GB2-05":1489.9936116790288,"GB2-06":1645.7663533360771,"GB2-07":1645.8532874107905,"GB2-08":1605.4483443323797},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1599.7404917395845,"GB2-02":1746.8507510957204,"GB2-04":1579.5576387423876,"GB2-05":1537.5424446121715,"GB2-06":1716.028915302819,"GB2-07":1641.587990360725,"GB2-08":1701.9428640249134},"medium":{"GB2-01":1487.721422135228,"GB2-02":1475.402260482471,"GB2-03":1456.992704704807,"GB2-04":1466.485643264073,"GB2-05":1537.236926140518,"GB2-06":1707.1649512901192,"GB2-07":1663.2800319802798,"GB2-08":1443.6592609728195},"none":{"GB2-01":1588.3444361805764,"GB2-02":1478.1224509695917,"GB2-04":1478.6538182736597,"GB2-05":1395.2014642843967,"GB2-06":1514.105193415293,"GB2-07":1632.6918398913665,"GB2-08":1670.7429079994065}},"per_game_tracks":{"highest":{"GB2-01":59.935555530461315,"GB2-02":90.47270926865744,"GB2-04":51.78950505760701,"GB2-05":51.146338598706805,"GB2-06":81.37204287643961,"GB2-07":65.67069489296186,"GB2-08":66.94349597864887},"medium":{"GB2-01":45.78994213262309,"GB2-02":25.370766045966345,"GB2-03":38.09391002162233,"GB2-04":29.004017345869457,"GB2-05":51.11193183106644,"GB2-06":80.54297967705504,"GB2-07":68.53036352739291,"GB2-08":28.724237840417203},"none":{"GB2-01":58.53653969822832,"GB2-02":27.69529937871457,"GB2-04":31.21093844748892,"GB2-05":35.51777926697464,"GB2-06":56.281940805437515,"GB2-07":65.03810238045806,"GB2-08":62.88796737924806}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.46711275741033,"medium":45.8960185527516,"none":46.58553140051769},"reasoning_agg":{"highest":{"max":51.146338598706805,"mean":49.46711275741033,"min":51.146338598706805},"medium":{"max":80.54297967705504,"mean":45.8960185527516,"min":25.370766045966345},"none":{"max":65.03810238045806,"mean":46.58553140051769,"min":27.69529937871457}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":80.54297967705504,"expected_score":51.40390019815825,"reasoning_variance":3.5710942046587277,"reliability_score":82.22835330102315,"uncertainty_avg":17.77164669897685,"uncertainty_penalty":4.087679294598381},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.146338598706805,"expected_score":59.596356387306855,"reliability_score":81.75300777157165,"uncertainty_avg":18.24699222842835,"uncertainty_penalty":10.129243629896528},"medium":{"ceiling_score":80.54297967705504,"expected_score":40.24377358932524,"reliability_score":78.519576857246,"uncertainty_avg":21.48042314275401,"uncertainty_penalty":-5.652244963426362},"none":{"ceiling_score":65.03810238045806,"expected_score":50.69051268347833,"reliability_score":84.83835212803064,"uncertainty_avg":15.16164787196937,"uncertainty_penalty":4.104981282960644}}},{"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":2.7596773499999996},"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":{"all":49.80843438484977,"highest":57.79807410203307,"medium":49.465375886743224,"none":38.71492248510732},"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},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-07"],"model_code_failure_rate":0.5,"model_code_failures":8,"repaired_admitted":8,"repaired_rate":0.5}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-07-28T14:18:42Z","match_totals_all":{"draws":791,"losses":552,"wins":763},"match_totals_tracks":{"highest":{"draws":106,"losses":59,"wins":173},"medium":{"draws":413,"losses":285,"wins":410},"none":{"draws":272,"losses":208,"wins":180}},"model_slug":"google-gemini-3-6-flash","overall":{"max":89.6854314765684,"mean":47.06992261609213,"min":23.660092040960166},"per_game":{"GB2-01":37.629900139408186,"GB2-03":35.52688846527977,"GB2-04":67.40362246573818,"GB2-05":80.10198872940181,"GB2-06":89.6854314765684,"GB2-08":36.44061333580206},"per_game_all":{"GB2-01":44.500128098125714,"GB2-03":47.6822250745926,"GB2-04":43.40942003781647,"GB2-05":67.22221763608214,"GB2-06":67.51639684383389,"GB2-08":28.520218618647814},"per_game_match_totals_all":{"GB2-01":{"draws":94,"losses":69,"wins":91},"GB2-02":{"draws":208,"losses":8,"wins":0},"GB2-03":{"draws":93,"losses":63,"wins":74},"GB2-04":{"draws":171,"losses":36,"wins":55},"GB2-05":{"draws":0,"losses":99,"wins":191},"GB2-06":{"draws":29,"losses":98,"wins":177},"GB2-07":{"draws":0,"losses":99,"wins":135},"GB2-08":{"draws":196,"losses":80,"wins":40}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":27,"losses":11,"wins":4},"GB2-03":{"draws":23,"losses":11,"wins":6},"GB2-04":{"draws":15,"losses":5,"wins":26},"GB2-05":{"draws":0,"losses":2,"wins":40},"GB2-06":{"draws":3,"losses":7,"wins":74},"GB2-08":{"draws":38,"losses":23,"wins":23}},"medium":{"GB2-01":{"draws":37,"losses":27,"wins":68},"GB2-02":{"draws":131,"losses":5,"wins":0},"GB2-03":{"draws":38,"losses":31,"wins":39},"GB2-04":{"draws":90,"losses":22,"wins":24},"GB2-05":{"draws":0,"losses":57,"wins":101},"GB2-06":{"draws":16,"losses":44,"wins":80},"GB2-07":{"draws":0,"losses":62,"wins":84},"GB2-08":{"draws":101,"losses":37,"wins":14}},"none":{"GB2-01":{"draws":30,"losses":31,"wins":19},"GB2-02":{"draws":77,"losses":3,"wins":0},"GB2-03":{"draws":32,"losses":21,"wins":29},"GB2-04":{"draws":66,"losses":9,"wins":5},"GB2-05":{"draws":0,"losses":40,"wins":50},"GB2-06":{"draws":10,"losses":47,"wins":23},"GB2-07":{"draws":0,"losses":37,"wins":51},"GB2-08":{"draws":57,"losses":20,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1482.5849046821866,"GB2-03":1512.731539764084,"GB2-04":1544.247567886798,"GB2-05":1687.8065389396443,"GB2-06":1613.9356492449015,"GB2-08":1449.0227548681203},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1430.1754934861804,"GB2-03":1443.1089862019785,"GB2-04":1668.718425438251,"GB2-05":1808.185313213967,"GB2-06":1789.1514474583742,"GB2-08":1507.6737833517823},"medium":{"GB2-01":1591.979256849529,"GB2-02":1475.989687596188,"GB2-03":1559.879933466906,"GB2-04":1485.365386512397,"GB2-05":1714.4236091773764,"GB2-06":1697.0755271109128,"GB2-07":1467.603248862896,"GB2-08":1405.122481000175},"none":{"GB2-01":1425.5999637108494,"GB2-02":1478.689206590389,"GB2-03":1535.2056996233666,"GB2-04":1478.658891709746,"GB2-05":1540.8106944275896,"GB2-06":1355.5799731654176,"GB2-07":1594.2908035675873,"GB2-08":1434.272000252403}},"per_game_tracks":{"highest":{"GB2-01":37.629900139408186,"GB2-03":35.52688846527977,"GB2-04":67.40362246573818,"GB2-05":80.10198872940181,"GB2-06":89.6854314765684,"GB2-08":36.44061333580206},"medium":{"GB2-01":58.98276178242768,"GB2-02":27.357232603811255,"GB2-03":56.47223347602109,"GB2-04":33.47195777677865,"GB2-05":71.37566983926048,"GB2-06":79.5139114660505,"GB2-07":44.88914810863602,"GB2-08":23.660092040960166},"none":{"GB2-01":36.88772237254127,"GB2-02":24.623380807710774,"GB2-03":51.047553282476954,"GB2-04":29.352679870932583,"GB2-05":50.18899433958414,"GB2-06":33.34984758888278,"GB2-07":58.80925113954886,"GB2-08":25.45995047918121}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.02946947642583,"medium":49.46537588674323,"none":38.714922485107316},"reasoning_agg":{"highest":{"max":89.6854314765684,"mean":53.02946947642583,"min":36.44061333580206},"medium":{"max":79.5139114660505,"mean":49.46537588674323,"min":23.660092040960166},"none":{"max":58.80925113954886,"mean":38.714922485107316,"min":24.623380807710774}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":89.6854314765684,"expected_score":46.99676400874958,"reasoning_variance":14.314546991318515,"reliability_score":72.60555740166959,"uncertainty_avg":27.394442598330414,"uncertainty_penalty":-0.07315860734254898},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.6854314765684,"expected_score":49.368727105555685,"reliability_score":67.73692128511578,"uncertainty_avg":32.26307871488422,"uncertainty_penalty":-3.660742370870146},"medium":{"ceiling_score":79.5139114660505,"expected_score":46.57542363334835,"reliability_score":83.83810651528599,"uncertainty_avg":16.161893484714014,"uncertainty_penalty":-2.889952253394881},"none":{"ceiling_score":58.80925113954886,"expected_score":39.184269170319325,"reliability_score":66.69866793298664,"uncertainty_avg":33.30133206701336,"uncertainty_penalty":0.4693466852120096}}},{"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":5.0801327999999994},"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":45.55118371869646,"highest":45.83120268487471,"medium":42.44845398767817,"none":51.28817970040543},"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":"2026-07-28T14:25:46Z","match_totals_all":{"draws":1135,"losses":933,"wins":1325},"match_totals_tracks":{"highest":{"draws":424,"losses":443,"wins":556},"medium":{"draws":382,"losses":227,"wins":278},"none":{"draws":329,"losses":263,"wins":491}},"model_slug":"moonshotai-kimi-k3","overall":{"max":70.64188697668526,"mean":46.994459394587444,"min":20.4833116279375},"per_game":{"GB2-01":51.37602419083462,"GB2-02":26.316280268343217,"GB2-04":45.83967550776018,"GB2-05":48.21834016013898,"GB2-06":72.69687122250753,"GB2-07":53.56163219475513,"GB2-08":22.809595249783325},"per_game_all":{"GB2-01":51.192823700084894,"GB2-02":23.898403253815143,"GB2-04":36.47038370734756,"GB2-05":50.09502726306088,"GB2-06":71.12469189335985,"GB2-07":50.00273340088509,"GB2-08":36.0742228123218},"per_game_match_totals_all":{"GB2-01":{"draws":203,"losses":143,"wins":176},"GB2-02":{"draws":392,"losses":50,"wins":30},"GB2-03":{"draws":51,"losses":53,"wins":106},"GB2-04":{"draws":254,"losses":98,"wins":135},"GB2-05":{"draws":0,"losses":135,"wins":204},"GB2-06":{"draws":33,"losses":114,"wins":258},"GB2-07":{"draws":0,"losses":235,"wins":289},"GB2-08":{"draws":202,"losses":105,"wins":127}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":98,"wins":113},"GB2-02":{"draws":171,"losses":29,"wins":20},"GB2-04":{"draws":84,"losses":44,"wins":88},"GB2-05":{"draws":0,"losses":74,"wins":85},"GB2-06":{"draws":13,"losses":35,"wins":86},"GB2-07":{"draws":0,"losses":116,"wins":154},"GB2-08":{"draws":105,"losses":47,"wins":10}},"medium":{"GB2-01":{"draws":77,"losses":21,"wins":26},"GB2-02":{"draws":105,"losses":9,"wins":4},"GB2-03":{"draws":22,"losses":29,"wins":37},"GB2-04":{"draws":85,"losses":34,"wins":22},"GB2-05":{"draws":0,"losses":21,"wins":19},"GB2-06":{"draws":12,"losses":39,"wins":81},"GB2-07":{"draws":0,"losses":46,"wins":70},"GB2-08":{"draws":81,"losses":28,"wins":19}},"none":{"GB2-01":{"draws":75,"losses":24,"wins":37},"GB2-02":{"draws":116,"losses":12,"wins":6},"GB2-03":{"draws":29,"losses":24,"wins":69},"GB2-04":{"draws":85,"losses":20,"wins":25},"GB2-05":{"draws":0,"losses":40,"wins":100},"GB2-06":{"draws":8,"losses":40,"wins":91},"GB2-07":{"draws":0,"losses":73,"wins":65},"GB2-08":{"draws":16,"losses":30,"wins":98}}},"per_game_raw_elo_all":{"GB2-01":1540.027587338606,"GB2-02":1490.6745462825638,"GB2-04":1519.1239058247163,"GB2-05":1570.8310267504994,"GB2-06":1647.4054676706867,"GB2-07":1537.7082041824597,"GB2-08":1510.4349820527225},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1541.4255223205,"GB2-02":1488.7805028667178,"GB2-04":1566.6169713855695,"GB2-05":1528.8898595656972,"GB2-06":1665.7301362588205,"GB2-07":1551.0878371933761,"GB2-08":1417.4843277494867},"medium":{"GB2-01":1513.4850939151636,"GB2-02":1491.6486403402896,"GB2-03":1540.2984005392661,"GB2-04":1467.0581887577116,"GB2-05":1518.9915804591635,"GB2-06":1641.3232965168784,"GB2-07":1585.177792689917,"GB2-08":1471.0588744912395},"none":{"GB2-01":1565.1721457801543,"GB2-02":1491.594495640684,"GB2-03":1616.2959890212232,"GB2-04":1523.6965573308678,"GB2-05":1664.6116402266373,"GB2-06":1635.1629702363616,"GB2-07":1476.858982664086,"GB2-08":1642.7617439174417}},"per_game_tracks":{"highest":{"GB2-01":51.37602419083462,"GB2-02":26.316280268343217,"GB2-04":45.83967550776018,"GB2-05":48.21834016013898,"GB2-06":72.69687122250753,"GB2-07":53.56163219475513,"GB2-08":22.809595249783325},"medium":{"GB2-01":47.744457850073424,"GB2-02":20.4833116279375,"GB2-03":49.6008740192731,"GB2-04":24.958123881962113,"GB2-05":37.7926707560472,"GB2-06":70.64188697668526,"GB2-07":57.2340093799493,"GB2-08":31.13229740949744},"none":{"GB2-01":54.45798905934664,"GB2-02":24.895617865164713,"GB2-03":64.53575618689302,"GB2-04":38.61335173232039,"GB2-05":64.27407087299648,"GB2-06":70.03531748088676,"GB2-07":39.21255862795084,"GB2-08":54.28077577768462}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.27167231378149,"medium":42.42352616957542,"none":51.288179700405436},"reasoning_agg":{"highest":{"max":53.56163219475513,"mean":47.27167231378149,"min":45.83967550776018},"medium":{"max":70.64188697668526,"mean":42.42352616957542,"min":20.4833116279375},"none":{"max":70.03531748088676,"mean":51.288179700405436,"min":24.895617865164713}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"score_diagnostics":{"ceiling_score":70.64188697668526,"expected_score":45.788258174360976,"reasoning_variance":8.864653530830019,"reliability_score":60.94994371546092,"uncertainty_avg":39.05005628453908,"uncertainty_penalty":-1.2062012202264683},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.56163219475513,"expected_score":35.953883485707934,"reliability_score":63.639262749859135,"uncertainty_avg":36.360737250140865,"uncertainty_penalty":-11.317788828073553},"medium":{"ceiling_score":70.64188697668526,"expected_score":41.86067265401981,"reliability_score":55.99925499803122,"uncertainty_avg":44.00074500196878,"uncertainty_penalty":-0.5628535155556094},"none":{"ceiling_score":70.03531748088676,"expected_score":63.86995553782567,"reliability_score":62.742881396381044,"uncertainty_avg":37.257118603618956,"uncertainty_penalty":12.581775837420231}}},{"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":67.27386999999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":309143,"mean_ms":97936.92,"min_ms":13711,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":309143,"mean_ms":245541.25,"min_ms":194014,"run_count":8},"medium":{"attempt_count":11,"max_ms":70195,"mean_ms":41737.375,"min_ms":27719,"run_count":8},"none":{"attempt_count":10,"max_ms":27196,"mean_ms":16688.222222222223,"min_ms":13711,"run_count":9}},"codegen_output_tokens":{"attempt_count":32,"output_max":806490,"output_mean":177703.68,"output_min":2382,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":806490,"output_mean":542498.625,"output_min":312998,"run_count":8},"medium":{"attempt_count":11,"output_max":13756,"output_mean":9389.25,"output_min":6044,"run_count":8},"none":{"attempt_count":10,"output_max":5458,"output_mean":3054.3333333333335,"output_min":2382,"run_count":9}},"display_name":"GPT-5.6 Terra","economics":{"all":46.942196650413884,"highest":55.407498848345874,"medium":42.493195953202076,"none":42.9258951496937},"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":"2026-07-28T14:25:28Z","match_totals_all":{"draws":563,"losses":509,"wins":558},"match_totals_tracks":{"highest":{"draws":103,"losses":184,"wins":243},"medium":{"draws":202,"losses":140,"wins":152},"none":{"draws":258,"losses":185,"wins":163}},"model_slug":"gpt-5-6-terra","overall":{"max":73.14660395348105,"mean":46.942196650413884,"min":27.87064582839924},"per_game":{"GB2-01":40.69073946920973,"GB2-02":45.52265222263585,"GB2-03":54.81316137358737,"GB2-04":48.288709971644074,"GB2-05":62.08711787214945,"GB2-06":73.14660395348105,"GB2-07":73.14639726550367,"GB2-08":45.56460865855579},"per_game_all":{"GB2-01":48.374706324426995,"GB2-02":34.14687660817215,"GB2-03":49.549225205710876,"GB2-04":42.15261385848839,"GB2-05":57.820412296908025,"GB2-06":53.95345444748184,"GB2-07":53.13923264908836,"GB2-08":36.40105181303445},"per_game_match_totals_all":{"GB2-01":{"draws":58,"losses":76,"wins":62},"GB2-02":{"draws":165,"losses":15,"wins":16},"GB2-03":{"draws":64,"losses":43,"wins":41},"GB2-04":{"draws":156,"losses":21,"wins":33},"GB2-05":{"draws":0,"losses":84,"wins":128},"GB2-06":{"draws":13,"losses":96,"wins":113},"GB2-07":{"draws":0,"losses":99,"wins":113},"GB2-08":{"draws":107,"losses":75,"wins":52}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":30,"wins":19},"GB2-02":{"draws":41,"losses":10,"wins":13},"GB2-03":{"draws":11,"losses":13,"wins":20},"GB2-04":{"draws":27,"losses":13,"wins":20},"GB2-05":{"draws":0,"losses":26,"wins":46},"GB2-06":{"draws":0,"losses":29,"wins":49},"GB2-07":{"draws":0,"losses":28,"wins":44},"GB2-08":{"draws":11,"losses":35,"wins":32}},"medium":{"GB2-01":{"draws":22,"losses":20,"wins":20},"GB2-02":{"draws":54,"losses":2,"wins":0},"GB2-03":{"draws":25,"losses":9,"wins":6},"GB2-04":{"draws":54,"losses":7,"wins":9},"GB2-05":{"draws":0,"losses":31,"wins":35},"GB2-06":{"draws":12,"losses":20,"wins":34},"GB2-07":{"draws":0,"losses":30,"wins":32},"GB2-08":{"draws":35,"losses":21,"wins":16}},"none":{"GB2-01":{"draws":23,"losses":26,"wins":23},"GB2-02":{"draws":70,"losses":3,"wins":3},"GB2-03":{"draws":28,"losses":21,"wins":15},"GB2-04":{"draws":75,"losses":1,"wins":4},"GB2-05":{"draws":0,"losses":27,"wins":47},"GB2-06":{"draws":1,"losses":47,"wins":30},"GB2-07":{"draws":0,"losses":41,"wins":37},"GB2-08":{"draws":61,"losses":19,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1505.9030702774774,"GB2-02":1506.0235790057823,"GB2-03":1521.746769263809,"GB2-04":1529.220659370467,"GB2-05":1596.6250625268901,"GB2-06":1498.509769937072,"GB2-07":1535.7056193820397,"GB2-08":1491.4239076715064},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1444.5042092762435,"GB2-02":1554.51478910498,"GB2-03":1555.6224588373111,"GB2-04":1564.0392200957288,"GB2-05":1634.0374245901774,"GB2-06":1645.4373743096698,"GB2-07":1698.0816425356322,"GB2-08":1553.7992605242216},"medium":{"GB2-01":1498.983410367778,"GB2-02":1486.2662373624098,"GB2-03":1500.0753756097706,"GB2-04":1505.8676356462586,"GB2-05":1556.1844675568093,"GB2-06":1504.8244147827002,"GB2-07":1415.0011967486844,"GB2-08":1488.8573843513443},"none":{"GB2-01":1574.221591188411,"GB2-02":1477.289710549957,"GB2-03":1509.542473344345,"GB2-04":1517.755122369414,"GB2-05":1599.653295433683,"GB2-06":1345.2675207188454,"GB2-07":1494.0340188618018,"GB2-08":1431.615078138953}},"per_game_tracks":{"highest":{"GB2-01":40.69073946920973,"GB2-02":45.52265222263585,"GB2-03":54.81316137358737,"GB2-04":48.288709971644074,"GB2-05":62.08711787214945,"GB2-06":73.14660395348105,"GB2-07":73.14639726550367,"GB2-08":45.56460865855579},"medium":{"GB2-01":47.378778542011254,"GB2-02":28.645102829320255,"GB2-03":45.05117535357613,"GB2-04":37.623306633454085,"GB2-05":53.08848731670678,"GB2-06":54.43756662250657,"GB2-07":37.95324937589321,"GB2-08":35.7679009521483},"none":{"GB2-01":57.05460096205999,"GB2-02":28.272874772560343,"GB2-03":48.7833388899691,"GB2-04":40.54582497036699,"GB2-05":58.28563170186785,"GB2-06":34.27619276645788,"GB2-07":48.318051305868195,"GB2-08":27.87064582839924}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.407498848345874,"medium":42.493195953202076,"none":42.9258951496937},"reasoning_agg":{"highest":{"max":73.14660395348105,"mean":55.407498848345874,"min":40.69073946920973},"medium":{"max":54.43756662250657,"mean":42.493195953202076,"min":28.645102829320255},"none":{"max":58.28563170186785,"mean":42.9258951496937,"min":27.87064582839924}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":73.14660395348105,"expected_score":41.583898789771546,"reasoning_variance":12.914302895143798,"reliability_score":82.87515016207153,"uncertainty_avg":17.12484983792847,"uncertainty_penalty":-5.358297860642338},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.14660395348105,"expected_score":43.564435801036595,"reliability_score":82.11057217066883,"uncertainty_avg":17.889427829331172,"uncertainty_penalty":-11.843063047309279},"medium":{"ceiling_score":54.43756662250657,"expected_score":37.856857465919326,"reliability_score":79.9586553335799,"uncertainty_avg":20.041344666420102,"uncertainty_penalty":-4.6363384872827496},"none":{"ceiling_score":58.28563170186785,"expected_score":43.33040310235873,"reliability_score":86.55622298196587,"uncertainty_avg":13.443777018034133,"uncertainty_penalty":0.40450795266502837}}},{"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":6.7026405},"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":42.17318510517482,"medium":52.874155790598564},"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":"2026-07-28T14:20:36Z","match_totals_all":{"draws":295,"losses":279,"wins":338},"match_totals_tracks":{"highest":{"draws":119,"losses":141,"wins":130},"medium":{"draws":176,"losses":138,"wins":208}},"model_slug":"google-gemini-3-5-flash","overall":{"max":89.7552146103392,"mean":46.06036338664327,"min":18.496744122226392},"per_game":{"GB2-03":44.512342496762926,"GB2-04":18.496744122226392,"GB2-05":42.664779841098394,"GB2-06":70.29125368951648,"GB2-07":57.8800361043894,"GB2-08":19.193954377055277},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":9,"wins":51},"GB2-02":{"draws":53,"losses":2,"wins":7},"GB2-03":{"draws":53,"losses":19,"wins":30},"GB2-04":{"draws":50,"losses":37,"wins":25},"GB2-05":{"draws":0,"losses":81,"wins":69},"GB2-06":{"draws":20,"losses":28,"wins":74},"GB2-07":{"draws":0,"losses":78,"wins":82},"GB2-08":{"draws":119,"losses":25,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":37,"losses":4,"wins":7},"GB2-04":{"draws":16,"losses":28,"wins":12},"GB2-05":{"draws":0,"losses":35,"wins":33},"GB2-06":{"draws":8,"losses":19,"wins":39},"GB2-07":{"draws":0,"losses":37,"wins":39},"GB2-08":{"draws":58,"losses":18,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":9,"wins":51},"GB2-02":{"draws":53,"losses":2,"wins":7},"GB2-03":{"draws":16,"losses":15,"wins":23},"GB2-04":{"draws":34,"losses":9,"wins":13},"GB2-05":{"draws":0,"losses":46,"wins":36},"GB2-06":{"draws":12,"losses":9,"wins":35},"GB2-07":{"draws":0,"losses":41,"wins":43},"GB2-08":{"draws":61,"losses":7,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1514.57592010515,"GB2-04":1435.6044869751163,"GB2-05":1483.748027205122,"GB2-06":1647.5486208821435,"GB2-07":1591.2217583813213,"GB2-08":1393.4118486038897},"medium":{"GB2-01":1844.99143016808,"GB2-02":1491.9455099224035,"GB2-03":1584.4380808026062,"GB2-04":1533.857806977198,"GB2-05":1474.9857181649531,"GB2-06":1754.720265023284,"GB2-07":1491.1934866603465,"GB2-08":1390.2358564476272}},"per_game_tracks":{"highest":{"GB2-03":44.512342496762926,"GB2-04":18.496744122226392,"GB2-05":42.664779841098394,"GB2-06":70.29125368951648,"GB2-07":57.8800361043894,"GB2-08":19.193954377055277},"medium":{"GB2-01":89.7552146103392,"GB2-02":30.592965958181995,"GB2-03":60.58261886572101,"GB2-04":42.028380510266544,"GB2-05":44.502893226762005,"GB2-06":86.26508114189525,"GB2-07":48.1678904051992,"GB2-08":21.098201606423295}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.24657098268797,"medium":52.874155790598564},"reasoning_agg":{"highest":{"max":70.29125368951648,"mean":39.24657098268797,"min":18.496744122226392},"medium":{"max":89.7552146103392,"mean":52.874155790598564,"min":21.098201606423295}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":89.7552146103392,"reasoning_variance":13.627584807910594},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.29125368951648,"expected_score":31.066134305673845,"reliability_score":55.88028523567155,"uncertainty_avg":44.11971476432845,"uncertainty_penalty":-8.180436677014125},"medium":{"ceiling_score":89.7552146103392,"expected_score":54.325637739859744,"reliability_score":81.7258235316823,"uncertainty_avg":18.2741764683177,"uncertainty_penalty":1.4514819492611792}}},{"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":0.7288237500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.0216425,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875000000003}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.121855,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112225000000002},"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":41.82387093837293,"none":46.807695535430966},"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":"2026-07-28T14:25:54Z","match_totals_all":{"draws":348,"losses":319,"wins":317},"match_totals_tracks":{"medium":{"draws":175,"losses":163,"wins":152},"none":{"draws":173,"losses":156,"wins":165}},"model_slug":"qwen-qwen3-7-max","overall":{"max":83.25544957333192,"mean":42.860816753913454,"min":27.61707592207255},"per_game_match_totals_all":{"GB2-01":{"draws":47,"losses":45,"wins":52},"GB2-02":{"draws":113,"losses":8,"wins":9},"GB2-03":{"draws":48,"losses":8,"wins":4},"GB2-04":{"draws":36,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":82,"wins":70},"GB2-06":{"draws":11,"losses":78,"wins":59},"GB2-07":{"draws":0,"losses":45,"wins":101},"GB2-08":{"draws":93,"losses":42,"wins":13}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":26,"losses":27,"wins":15},"GB2-02":{"draws":59,"losses":2,"wins":3},"GB2-04":{"draws":36,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":44,"wins":32},"GB2-06":{"draws":11,"losses":37,"wins":34},"GB2-07":{"draws":0,"losses":23,"wins":51},"GB2-08":{"draws":43,"losses":19,"wins":8}},"none":{"GB2-01":{"draws":21,"losses":18,"wins":37},"GB2-02":{"draws":54,"losses":6,"wins":6},"GB2-03":{"draws":48,"losses":8,"wins":4},"GB2-05":{"draws":0,"losses":38,"wins":38},"GB2-06":{"draws":0,"losses":41,"wins":25},"GB2-07":{"draws":0,"losses":22,"wins":50},"GB2-08":{"draws":50,"losses":23,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1397.4252865321264,"GB2-02":1498.941615293707,"GB2-04":1500.1802235942246,"GB2-05":1524.197050319894,"GB2-06":1520.9132891105182,"GB2-07":1675.5043669133365,"GB2-08":1473.8673952811569},"none":{"GB2-01":1600.9936984199935,"GB2-02":1500.6469304986908,"GB2-03":1434.9623243276997,"GB2-05":1546.3265864598327,"GB2-06":1331.436946958018,"GB2-07":1780.423050630861,"GB2-08":1451.3049117986232}},"per_game_tracks":{"medium":{"GB2-01":32.79755909993713,"GB2-02":27.61707592207255,"GB2-04":31.255922495257053,"GB2-05":47.589352931063644,"GB2-06":54.84117338476251,"GB2-07":68.15380353856463,"GB2-08":30.512209196952995},"none":{"GB2-01":60.49250178392132,"GB2-02":33.0035862085153,"GB2-03":36.04653434402484,"GB2-05":52.348101378726525,"GB2-06":31.98480499971793,"GB2-07":83.25544957333192,"GB2-08":30.52289045977884}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.45071839633466,"none":45.27091511149225},"reasoning_agg":{"medium":{"max":68.15380353856463,"mean":40.45071839633466,"min":27.61707592207255},"none":{"max":83.25544957333192,"mean":45.27091511149225,"min":30.52289045977884}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":83.25544957333192,"reasoning_variance":4.820196715157593},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":68.15380353856463,"expected_score":42.10578119779372,"reliability_score":59.4635861897397,"uncertainty_avg":40.5364138102603,"uncertainty_penalty":1.65506280145906},"none":{"ceiling_score":83.25544957333192,"expected_score":44.508614017498516,"reliability_score":84.47522436760606,"uncertainty_avg":15.524775632393945,"uncertainty_penalty":-0.7623010939937345}}},{"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":4.168736000000001},"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":{"all":43.28241178995072,"highest":45.38638959966826,"medium":40.959864994647305,"none":43.02487537728549},"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":"2026-07-28T14:20:21Z","match_totals_all":{"draws":521,"losses":482,"wins":521},"match_totals_tracks":{"highest":{"draws":203,"losses":234,"wins":223},"medium":{"draws":170,"losses":144,"wins":182},"none":{"draws":148,"losses":104,"wins":116}},"model_slug":"claude-sonnet-5","overall":{"max":59.33049896491237,"mean":42.6754480970501,"min":26.21063543593213},"per_game":{"GB2-01":59.33049896491237,"GB2-02":38.687839752916766,"GB2-03":42.36140514628463,"GB2-04":44.315516442451184,"GB2-05":52.76318675006037,"GB2-06":55.09510200081964,"GB2-07":37.459792671933386,"GB2-08":33.07777506796782},"per_game_all":{"GB2-01":53.33494344137912,"GB2-02":31.42139026369988,"GB2-04":39.771346049801856,"GB2-05":47.40437802296628,"GB2-06":54.05970035562252,"GB2-07":47.53326247461237,"GB2-08":29.451861921572988},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":54,"wins":105},"GB2-02":{"draws":133,"losses":16,"wins":9},"GB2-03":{"draws":61,"losses":61,"wins":48},"GB2-04":{"draws":126,"losses":19,"wins":33},"GB2-05":{"draws":0,"losses":100,"wins":108},"GB2-06":{"draws":15,"losses":95,"wins":102},"GB2-07":{"draws":0,"losses":97,"wins":99},"GB2-08":{"draws":151,"losses":40,"wins":17}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":19,"wins":44},"GB2-02":{"draws":39,"losses":10,"wins":7},"GB2-03":{"draws":48,"losses":46,"wins":38},"GB2-04":{"draws":43,"losses":9,"wins":16},"GB2-05":{"draws":0,"losses":41,"wins":39},"GB2-06":{"draws":10,"losses":39,"wins":41},"GB2-07":{"draws":0,"losses":42,"wins":28},"GB2-08":{"draws":48,"losses":28,"wins":10}},"medium":{"GB2-01":{"draws":8,"losses":26,"wins":32},"GB2-02":{"draws":56,"losses":3,"wins":1},"GB2-04":{"draws":48,"losses":8,"wins":12},"GB2-05":{"draws":0,"losses":31,"wins":45},"GB2-06":{"draws":3,"losses":33,"wins":40},"GB2-07":{"draws":0,"losses":33,"wins":45},"GB2-08":{"draws":55,"losses":10,"wins":7}},"none":{"GB2-01":{"draws":12,"losses":9,"wins":29},"GB2-02":{"draws":38,"losses":3,"wins":1},"GB2-03":{"draws":13,"losses":15,"wins":10},"GB2-04":{"draws":35,"losses":2,"wins":5},"GB2-05":{"draws":0,"losses":28,"wins":24},"GB2-06":{"draws":2,"losses":23,"wins":21},"GB2-07":{"draws":0,"losses":22,"wins":26},"GB2-08":{"draws":48,"losses":2,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1547.0665050346781,"GB2-02":1500.1306306886206,"GB2-04":1521.7943640114875,"GB2-05":1505.1683503813372,"GB2-06":1501.6591720565066,"GB2-07":1492.510697655239,"GB2-08":1447.5741227515202},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1590.9475808519617,"GB2-02":1528.8802538058603,"GB2-03":1481.3446071296682,"GB2-04":1540.7026544738983,"GB2-05":1548.872594045111,"GB2-06":1502.9657308011708,"GB2-07":1408.057840072436,"GB2-08":1466.5948946196706},"medium":{"GB2-01":1453.4311708784803,"GB2-02":1487.5573627493632,"GB2-04":1495.0551444554867,"GB2-05":1532.0402550957847,"GB2-06":1485.0135108536388,"GB2-07":1495.9673153967922,"GB2-08":1438.7650526278594},"none":{"GB2-01":1596.8207633735929,"GB2-02":1483.9542755106384,"GB2-03":1487.6967601875272,"GB2-04":1529.625293105078,"GB2-05":1434.5922020031153,"GB2-06":1516.9982745147104,"GB2-07":1573.5069374964892,"GB2-08":1437.362421007031}},"per_game_tracks":{"highest":{"GB2-01":59.33049896491237,"GB2-02":38.687839752916766,"GB2-03":42.36140514628463,"GB2-04":44.315516442451184,"GB2-05":52.76318675006037,"GB2-06":55.09510200081964,"GB2-07":37.459792671933386,"GB2-08":33.07777506796782},"medium":{"GB2-01":41.974160447041655,"GB2-02":29.365695602250742,"GB2-04":35.3707045451438,"GB2-05":50.73920853170654,"GB2-06":52.29736118277051,"GB2-07":48.555402065964,"GB2-08":28.416522587653844},"none":{"GB2-01":58.70017091218334,"GB2-02":26.21063543593213,"GB2-03":42.71712204291151,"GB2-04":39.62781716181058,"GB2-05":38.71073878713191,"GB2-06":54.78663788327743,"GB2-07":56.58459268593973,"GB2-08":26.861288109097305}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.38638959966827,"medium":39.61507931419654,"none":43.02487537728549},"reasoning_agg":{"highest":{"max":59.33049896491237,"mean":45.38638959966827,"min":33.07777506796782},"medium":{"max":52.29736118277051,"mean":39.61507931419654,"min":28.416522587653844},"none":{"max":58.70017091218334,"mean":43.02487537728549,"min":26.21063543593213}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":59.33049896491237,"expected_score":38.01687257068112,"reasoning_variance":5.771310285471728,"reliability_score":80.74104723026522,"uncertainty_avg":19.258952769734776,"uncertainty_penalty":-4.658575526368978},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.33049896491237,"expected_score":29.893292182295077,"reliability_score":83.95352042629077,"uncertainty_avg":16.046479573709227,"uncertainty_penalty":-15.493097417373193},"medium":{"ceiling_score":52.29736118277051,"expected_score":36.77976239668793,"reliability_score":84.60262374407291,"uncertainty_avg":15.397376255927087,"uncertainty_penalty":-2.8353169175086137},"none":{"ceiling_score":58.70017091218334,"expected_score":46.63339577660745,"reliability_score":70.54599940127345,"uncertainty_avg":29.45400059872655,"uncertainty_penalty":3.608520399321961}}},{"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":2.2561125000000004},"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":1.42050125}},"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":42.62189542754262,"medium":43.951142329494964},"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":"2026-07-28T14:25:46Z","match_totals_all":{"draws":331,"losses":354,"wins":352},"match_totals_tracks":{"highest":{"draws":175,"losses":194,"wins":198},"medium":{"draws":156,"losses":160,"wins":154}},"model_slug":"gpt-5","overall":{"max":64.56457751195452,"mean":42.565021543848836,"min":26.012636169807294},"per_game":{"GB2-01":42.26838049059354,"GB2-02":26.012636169807294,"GB2-03":40.266725645019946,"GB2-04":28.91657816666402,"GB2-05":60.07362755919349,"GB2-06":64.56457751195452,"GB2-07":52.40882676709475,"GB2-08":26.463811110013335},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":68,"wins":44},"GB2-02":{"draws":50,"losses":10,"wins":4},"GB2-03":{"draws":47,"losses":29,"wins":17},"GB2-04":{"draws":99,"losses":19,"wins":20},"GB2-05":{"draws":0,"losses":64,"wins":82},"GB2-06":{"draws":13,"losses":64,"wins":77},"GB2-07":{"draws":0,"losses":73,"wins":89},"GB2-08":{"draws":94,"losses":27,"wins":19}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":39,"wins":28},"GB2-02":{"draws":50,"losses":10,"wins":4},"GB2-03":{"draws":18,"losses":17,"wins":12},"GB2-04":{"draws":49,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":32,"wins":48},"GB2-06":{"draws":5,"losses":28,"wins":43},"GB2-07":{"draws":0,"losses":46,"wins":48},"GB2-08":{"draws":44,"losses":15,"wins":11}},"medium":{"GB2-01":{"draws":19,"losses":29,"wins":16},"GB2-03":{"draws":29,"losses":12,"wins":5},"GB2-04":{"draws":50,"losses":12,"wins":16},"GB2-05":{"draws":0,"losses":32,"wins":34},"GB2-06":{"draws":8,"losses":36,"wins":34},"GB2-07":{"draws":0,"losses":27,"wins":41},"GB2-08":{"draws":50,"losses":12,"wins":8}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1472.0540994596254,"GB2-02":1492.630332287944,"GB2-03":1490.1194197836826,"GB2-04":1485.9184546972276,"GB2-05":1631.8673138972754,"GB2-06":1599.2547404971037,"GB2-07":1540.8674324975682,"GB2-08":1446.2815889377978},"medium":{"GB2-01":1357.5991262730408,"GB2-03":1431.7303930296262,"GB2-04":1548.0131095292184,"GB2-05":1594.6561013740363,"GB2-06":1505.6333421063478,"GB2-07":1569.3972507863089,"GB2-08":1431.2215797734218}},"per_game_tracks":{"highest":{"GB2-01":42.26838049059354,"GB2-02":26.012636169807294,"GB2-03":40.266725645019946,"GB2-04":28.91657816666402,"GB2-05":60.07362755919349,"GB2-06":64.56457751195452,"GB2-07":52.40882676709475,"GB2-08":26.463811110013335},"medium":{"GB2-01":30.11791991138669,"GB2-03":34.31390109131504,"GB2-04":46.365446088704815,"GB2-05":57.42107172094892,"GB2-06":55.04271992802316,"GB2-07":57.18356640655226,"GB2-08":27.21337115953385}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.62189542754261,"medium":42.50814766015507},"reasoning_agg":{"highest":{"max":64.56457751195452,"mean":42.62189542754261,"min":26.012636169807294},"medium":{"max":57.42107172094892,"mean":42.50814766015507,"min":27.21337115953385}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":64.56457751195452,"reasoning_variance":0.11374776738754377},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.56457751195452,"expected_score":30.77999508553829,"reliability_score":58.98922959495387,"uncertainty_avg":41.01077040504613,"uncertainty_penalty":-11.841900342004323},"medium":{"ceiling_score":57.42107172094892,"expected_score":41.66215435153357,"reliability_score":82.59637360473089,"uncertainty_avg":17.40362639526911,"uncertainty_penalty":-0.8459933086214946}}},{"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":0.3909760000000001},"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":47.46883860014374,"highest":46.047612975022176,"medium":45.42681241650121,"none":38.45207468210363},"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":"2026-07-28T14:25:30Z","match_totals_all":{"draws":242,"losses":400,"wins":441},"match_totals_tracks":{"highest":{"draws":12,"losses":144,"wins":150},"medium":{"draws":108,"losses":147,"wins":155},"none":{"draws":122,"losses":109,"wins":136}},"model_slug":"o3","overall":{"max":91.1514098096587,"mean":42.25803334181381,"min":20.608607619672682},"per_game":{"GB2-05":44.22280492979549,"GB2-06":48.747739576185836,"GB2-07":36.61883222856595,"GB2-08":54.60107516554143},"per_game_all":{"GB2-05":45.73584963061956,"GB2-06":66.37799813166254,"GB2-07":42.53266664235116,"GB2-08":35.228839995941705},"per_game_match_totals_all":{"GB2-01":{"draws":24,"losses":44,"wins":52},"GB2-02":{"draws":38,"losses":1,"wins":1},"GB2-03":{"draws":23,"losses":12,"wins":5},"GB2-04":{"draws":69,"losses":17,"wins":10},"GB2-05":{"draws":0,"losses":88,"wins":114},"GB2-06":{"draws":23,"losses":63,"wins":103},"GB2-07":{"draws":0,"losses":107,"wins":89},"GB2-08":{"draws":65,"losses":68,"wins":67}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":42,"wins":42},"GB2-06":{"draws":10,"losses":29,"wins":33},"GB2-07":{"draws":0,"losses":43,"wins":29},"GB2-08":{"draws":2,"losses":30,"wins":46}},"medium":{"GB2-01":{"draws":10,"losses":24,"wins":34},"GB2-04":{"draws":47,"losses":8,"wins":3},"GB2-05":{"draws":0,"losses":32,"wins":36},"GB2-06":{"draws":12,"losses":30,"wins":34},"GB2-07":{"draws":0,"losses":30,"wins":36},"GB2-08":{"draws":39,"losses":23,"wins":12}},"none":{"GB2-01":{"draws":14,"losses":20,"wins":18},"GB2-02":{"draws":38,"losses":1,"wins":1},"GB2-03":{"draws":23,"losses":12,"wins":5},"GB2-04":{"draws":22,"losses":9,"wins":7},"GB2-05":{"draws":0,"losses":14,"wins":36},"GB2-06":{"draws":1,"losses":4,"wins":36},"GB2-07":{"draws":0,"losses":34,"wins":24},"GB2-08":{"draws":24,"losses":15,"wins":9}}},"per_game_raw_elo_all":{"GB2-05":1526.8560013292342,"GB2-06":1605.876957944479,"GB2-07":1471.8936667112332,"GB2-08":1523.104622950765},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1490.8805849871474,"GB2-06":1477.8497581746362,"GB2-07":1420.1574611103608,"GB2-08":1633.749787406372},"medium":{"GB2-01":1526.8363065441854,"GB2-04":1453.38347630081,"GB2-05":1511.7322847617274,"GB2-06":1538.5869987807794,"GB2-07":1570.054537336516,"GB2-08":1452.1756101546605},"none":{"GB2-01":1442.2859213259474,"GB2-02":1474.570314492858,"GB2-03":1463.5783961255534,"GB2-04":1478.3686604298084,"GB2-05":1577.9551342388274,"GB2-06":1801.1941168780218,"GB2-07":1425.469001686823,"GB2-08":1483.3884712912622}},"per_game_tracks":{"highest":{"GB2-05":44.22280492979549,"GB2-06":48.747739576185836,"GB2-07":36.61883222856595,"GB2-08":54.60107516554143},"medium":{"GB2-01":51.07319084373484,"GB2-04":26.43659540135972,"GB2-05":48.16273316433884,"GB2-06":59.23484500914308,"GB2-07":57.17667287781976,"GB2-08":30.47683720261099},"none":{"GB2-01":39.85997039408309,"GB2-02":23.652691977966807,"GB2-03":24.733555700275605,"GB2-04":28.985856336779992,"GB2-05":44.82201079772438,"GB2-06":91.1514098096587,"GB2-07":33.80249482066777,"GB2-08":20.608607619672682}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.047612975022176,"medium":42.27441236831561,"none":38.45207468210363},"reasoning_agg":{"highest":{"max":54.60107516554143,"mean":46.047612975022176,"min":36.61883222856595},"medium":{"max":59.23484500914308,"mean":42.27441236831561,"min":26.43659540135972},"none":{"max":91.1514098096587,"mean":38.45207468210363,"min":20.608607619672682}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":91.1514098096587,"expected_score":47.097864296324275,"reasoning_variance":7.5955382929185475,"reliability_score":63.886930149712164,"uncertainty_avg":36.113069850287836,"uncertainty_penalty":4.839830954510468},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.60107516554143,"expected_score":35.54635357976447,"reliability_score":63.15008408421757,"uncertainty_avg":36.84991591578243,"uncertainty_penalty":-10.501259395257705},"medium":{"ceiling_score":59.23484500914308,"expected_score":41.23455798145787,"reliability_score":83.53660901614745,"uncertainty_avg":16.46339098385255,"uncertainty_penalty":-1.0398543868577406},"none":{"ceiling_score":91.1514098096587,"expected_score":43.83546336423147,"reliability_score":51.412188882128945,"uncertainty_avg":48.587811117871055,"uncertainty_penalty":5.383388682127844}}},{"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":1.2846227783999995},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":44.43715965293561,"none":42.63566979221104},"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":"2026-07-28T14:11:51Z","match_totals_all":{"draws":218,"losses":333,"wins":317},"match_totals_tracks":{"medium":{"draws":98,"losses":162,"wins":150},"none":{"draws":120,"losses":171,"wins":167}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":69.72301913548274,"mean":41.18864226445867,"min":26.27874691249746},"per_game_match_totals_all":{"GB2-01":{"draws":33,"losses":61,"wins":50},"GB2-02":{"draws":56,"losses":4,"wins":4},"GB2-03":{"draws":35,"losses":9,"wins":10},"GB2-04":{"draws":28,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":94,"wins":74},"GB2-06":{"draws":2,"losses":74,"wins":78},"GB2-07":{"draws":0,"losses":66,"wins":82},"GB2-08":{"draws":64,"losses":6,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":21,"wins":25},"GB2-04":{"draws":28,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":39,"wins":31},"GB2-06":{"draws":2,"losses":33,"wins":35},"GB2-07":{"draws":0,"losses":44,"wins":40},"GB2-08":{"draws":64,"losses":6,"wins":2}},"none":{"GB2-01":{"draws":29,"losses":40,"wins":25},"GB2-02":{"draws":56,"losses":4,"wins":4},"GB2-03":{"draws":35,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":55,"wins":43},"GB2-06":{"draws":0,"losses":41,"wins":43},"GB2-07":{"draws":0,"losses":22,"wins":42}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1623.0706040801538,"GB2-04":1522.8019351982393,"GB2-05":1407.3138342682005,"GB2-06":1584.2437571066848,"GB2-07":1484.101832265876,"GB2-08":1443.2135797485712},"none":{"GB2-01":1427.9370306043306,"GB2-02":1476.1302139151496,"GB2-03":1447.7436441756136,"GB2-05":1350.1016690927315,"GB2-06":1470.1028400149814,"GB2-07":1672.9945867330275}},"per_game_tracks":{"medium":{"GB2-01":61.922684399584234,"GB2-04":36.5993497239437,"GB2-05":34.2989086991669,"GB2-06":62.39449377262991,"GB2-07":45.128774409791504,"GB2-08":26.27874691249746},"none":{"GB2-01":39.80548819718096,"GB2-02":27.04995865374969,"GB2-03":37.72849305567903,"GB2-05":30.855904278592035,"GB2-06":50.65115543258182,"GB2-07":69.72301913548274}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.35343669771765,"none":41.023847831199696},"reasoning_agg":{"medium":{"max":62.39449377262991,"mean":41.35343669771765,"min":26.27874691249746},"none":{"max":69.72301913548274,"mean":41.023847831199696,"min":27.04995865374969}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":69.72301913548274,"reasoning_variance":0.32958886651795183},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":62.39449377262991,"expected_score":47.84437837319965,"reliability_score":63.290545275918745,"uncertainty_avg":36.709454724081255,"uncertainty_penalty":6.490941675482006},"none":{"ceiling_score":69.72301913548274,"expected_score":38.815185367427596,"reliability_score":85.8769760570975,"uncertainty_avg":14.123023942902504,"uncertainty_penalty":-2.2086624637721}}},{"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":{"all":43.39494415325101,"highest":45.24528786438645,"medium":44.631159242381614,"none":40.30838535298497},"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":"2026-07-28T14:25:47Z","match_totals_all":{"draws":1110,"losses":1111,"wins":1104},"match_totals_tracks":{"highest":{"draws":459,"losses":422,"wins":406},"medium":{"draws":275,"losses":222,"wins":257},"none":{"draws":376,"losses":467,"wins":441}},"model_slug":"z-ai-glm-5-2","overall":{"max":72.39801553734948,"mean":41.161537044647964,"min":22.65396867615027},"per_game":{"GB2-01":46.58581332555055,"GB2-02":27.783928237656962,"GB2-03":44.02826574890922,"GB2-04":31.427136910344064,"GB2-05":49.22585382145784,"GB2-06":71.58340912876453,"GB2-07":58.163872089932404,"GB2-08":33.164023652476},"per_game_all":{"GB2-01":43.71576461803144,"GB2-02":25.174838251237762,"GB2-03":40.46140915854525,"GB2-04":33.19715265252288,"GB2-05":48.89194393275458,"GB2-06":62.96500749598666,"GB2-07":57.790964117819804,"GB2-08":34.962472999109714},"per_game_match_totals_all":{"GB2-01":{"draws":148,"losses":148,"wins":142},"GB2-02":{"draws":307,"losses":31,"wins":13},"GB2-03":{"draws":115,"losses":69,"wins":54},"GB2-04":{"draws":247,"losses":79,"wins":66},"GB2-05":{"draws":0,"losses":279,"wins":259},"GB2-06":{"draws":33,"losses":144,"wins":155},"GB2-07":{"draws":0,"losses":231,"wins":297},"GB2-08":{"draws":260,"losses":130,"wins":118}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":84,"losses":31,"wins":29},"GB2-02":{"draws":149,"losses":20,"wins":10},"GB2-03":{"draws":44,"losses":35,"wins":29},"GB2-04":{"draws":82,"losses":28,"wins":20},"GB2-05":{"draws":0,"losses":118,"wins":104},"GB2-06":{"draws":6,"losses":17,"wins":33},"GB2-07":{"draws":0,"losses":104,"wins":134},"GB2-08":{"draws":94,"losses":69,"wins":47}},"medium":{"GB2-01":{"draws":38,"losses":27,"wins":33},"GB2-02":{"draws":40,"losses":2,"wins":0},"GB2-03":{"draws":21,"losses":6,"wins":5},"GB2-04":{"draws":39,"losses":26,"wins":21},"GB2-05":{"draws":0,"losses":52,"wins":56},"GB2-06":{"draws":14,"losses":28,"wins":50},"GB2-07":{"draws":0,"losses":61,"wins":85},"GB2-08":{"draws":123,"losses":20,"wins":7}},"none":{"GB2-01":{"draws":26,"losses":90,"wins":80},"GB2-02":{"draws":118,"losses":9,"wins":3},"GB2-03":{"draws":50,"losses":28,"wins":20},"GB2-04":{"draws":126,"losses":25,"wins":25},"GB2-05":{"draws":0,"losses":109,"wins":99},"GB2-06":{"draws":13,"losses":99,"wins":72},"GB2-07":{"draws":0,"losses":66,"wins":78},"GB2-08":{"draws":43,"losses":41,"wins":64}}},"per_game_raw_elo_all":{"GB2-01":1472.1445030081989,"GB2-02":1476.0569859590917,"GB2-03":1474.3645610719695,"GB2-04":1492.5534244303042,"GB2-05":1521.759789055003,"GB2-06":1578.3660486501888,"GB2-07":1579.1595942124138,"GB2-08":1489.8644265689852},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1489.1580073635612,"GB2-02":1481.0082785544455,"GB2-03":1485.5310573739334,"GB2-04":1477.0036602510422,"GB2-05":1519.2312764680391,"GB2-06":1641.3436578799765,"GB2-07":1574.2270293047713,"GB2-08":1471.833541398546},"medium":{"GB2-01":1453.4934512538966,"GB2-02":1468.8623880163934,"GB2-03":1483.3794346590705,"GB2-04":1492.4500199157155,"GB2-05":1592.7351013425762,"GB2-06":1652.9990136507138,"GB2-07":1614.640699451135,"GB2-08":1452.6861732137231},"none":{"GB2-01":1473.7820504071387,"GB2-02":1478.3002913064363,"GB2-03":1454.183191182905,"GB2-04":1508.206593124155,"GB2-05":1453.3129893543937,"GB2-06":1440.7554744198758,"GB2-07":1548.6110538813343,"GB2-08":1545.073565094686}},"per_game_tracks":{"highest":{"GB2-01":46.58581332555055,"GB2-02":27.783928237656962,"GB2-03":44.02826574890922,"GB2-04":31.427136910344064,"GB2-05":49.22585382145784,"GB2-06":71.58340912876453,"GB2-07":58.163872089932404,"GB2-08":33.164023652476},"medium":{"GB2-01":41.03539395640931,"GB2-02":22.65396867615027,"GB2-03":41.06240823577625,"GB2-04":32.47749534777884,"GB2-05":56.630948398109965,"GB2-06":72.39801553734948,"GB2-07":61.68089449425867,"GB2-08":29.110149293220164},"none":{"GB2-01":43.52608657213447,"GB2-02":25.08661783990605,"GB2-03":36.293553490950266,"GB2-04":35.686825699445755,"GB2-05":40.819029578695925,"GB2-06":44.913597821845975,"GB2-07":53.52812576926832,"GB2-08":42.61324605163298}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.545066538577316,"medium":44.63115924238162,"none":40.30838535298496},"reasoning_agg":{"highest":{"max":58.163872089932404,"mean":38.545066538577316,"min":27.783928237656962},"medium":{"max":72.39801553734948,"mean":44.63115924238162,"min":22.65396867615027},"none":{"max":53.52812576926832,"mean":40.30838535298496,"min":25.08661783990605}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":72.39801553734948,"expected_score":38.07694374507957,"reasoning_variance":6.0860927038043044,"reliability_score":74.00112637862887,"uncertainty_avg":25.99887362137113,"uncertainty_penalty":-3.0845932995683967},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.163872089932404,"expected_score":30.50224289593362,"reliability_score":82.12388830893805,"uncertainty_avg":17.87611169106195,"uncertainty_penalty":-8.042823642643697},"medium":{"ceiling_score":72.39801553734948,"expected_score":41.2067223776738,"reliability_score":69.90514474363182,"uncertainty_avg":30.09485525636818,"uncertainty_penalty":-3.424436864707822},"none":{"ceiling_score":53.52812576926832,"expected_score":42.5218659616313,"reliability_score":69.97434608331675,"uncertainty_avg":30.025653916683257,"uncertainty_penalty":2.2134806086463357}}},{"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":0.787281562},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214284,"mean_ms":465438.125,"min_ms":42870,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":1214284,"mean_ms":845698.625,"min_ms":162422,"run_count":8},"none":{"attempt_count":12,"max_ms":162843,"mean_ms":85177.625,"min_ms":42870,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":80681,"output_mean":29459.75,"output_min":2689,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":80681,"output_mean":54027.75,"output_min":8210,"run_count":8},"none":{"attempt_count":12,"output_max":7681,"output_mean":4891.75,"output_min":2689,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"highest":45.81369629876389,"none":40.85061000218519},"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":"2026-07-28T14:25:47Z","match_totals_all":{"draws":272,"losses":335,"wins":327},"match_totals_tracks":{"highest":{"draws":95,"losses":164,"wins":159},"none":{"draws":177,"losses":171,"wins":168}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":79.03501098478921,"mean":41.07192987387316,"min":20.31688929088188},"per_game":{"GB2-01":45.905068931277405,"GB2-04":22.67071339758295,"GB2-05":77.55050909177413,"GB2-06":42.19407690153233,"GB2-07":59.10196667088018,"GB2-08":27.45984279953629},"per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":59,"wins":56},"GB2-02":{"draws":55,"losses":2,"wins":1},"GB2-03":{"draws":18,"losses":31,"wins":9},"GB2-04":{"draws":25,"losses":20,"wins":7},"GB2-05":{"draws":0,"losses":72,"wins":90},"GB2-06":{"draws":8,"losses":50,"wins":74},"GB2-07":{"draws":0,"losses":78,"wins":80},"GB2-08":{"draws":121,"losses":23,"wins":10}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":14,"losses":24,"wins":28},"GB2-04":{"draws":25,"losses":20,"wins":7},"GB2-05":{"draws":0,"losses":24,"wins":52},"GB2-06":{"draws":2,"losses":36,"wins":26},"GB2-07":{"draws":0,"losses":46,"wins":40},"GB2-08":{"draws":54,"losses":14,"wins":6}},"none":{"GB2-01":{"draws":31,"losses":35,"wins":28},"GB2-02":{"draws":55,"losses":2,"wins":1},"GB2-03":{"draws":18,"losses":31,"wins":9},"GB2-05":{"draws":0,"losses":48,"wins":38},"GB2-06":{"draws":6,"losses":14,"wins":48},"GB2-07":{"draws":0,"losses":32,"wins":40},"GB2-08":{"draws":67,"losses":9,"wins":4}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1485.451431444242,"GB2-04":1437.033942799334,"GB2-05":1770.1139868621165,"GB2-06":1411.0223538755488,"GB2-07":1579.7533840085564,"GB2-08":1431.6177940617447},"none":{"GB2-01":1489.9089544458643,"GB2-02":1492.0797054118812,"GB2-03":1341.7414384682531,"GB2-05":1400.7555461917282,"GB2-06":1694.0603780225329,"GB2-07":1455.8188321632083,"GB2-08":1442.4017586919488}},"per_game_tracks":{"highest":{"GB2-01":45.905068931277405,"GB2-04":22.67071339758295,"GB2-05":77.55050909177413,"GB2-06":42.19407690153233,"GB2-07":59.10196667088018,"GB2-08":27.45984279953629},"none":{"GB2-01":47.413357618255546,"GB2-02":30.228599126505976,"GB2-03":20.31688929088188,"GB2-05":36.25827225605603,"GB2-06":79.03501098478921,"GB2-07":43.40379899145002,"GB2-08":29.298341747357632}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.634448389057546,"none":39.50941135868877},"reasoning_agg":{"highest":{"max":77.55050909177413,"mean":42.634448389057546,"min":22.67071339758295},"none":{"max":79.03501098478921,"mean":39.50941135868877,"min":20.31688929088188}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":79.03501098478921,"reasoning_variance":3.125037030368773},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.55050909177413,"expected_score":31.467710563649323,"reliability_score":83.73278111037123,"uncertainty_avg":16.267218889628772,"uncertainty_penalty":-11.166737825408223},"none":{"ceiling_score":79.03501098478921,"expected_score":33.881262195948025,"reliability_score":85.26964128236047,"uncertainty_avg":14.730358717639536,"uncertainty_penalty":-5.628149162740748}}},{"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":28.806540999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.046574,"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":29.297330999999996},"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":40.505978424900064,"highest":50.91463559655228,"medium":47.5595845000269,"none":23.043715178121012},"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":"2026-07-28T14:25:46Z","match_totals_all":{"draws":581,"losses":548,"wins":416},"match_totals_tracks":{"highest":{"draws":137,"losses":167,"wins":206},"medium":{"draws":220,"losses":135,"wins":143},"none":{"draws":224,"losses":246,"wins":67}},"model_slug":"gpt-5-6-luna","overall":{"max":78.57326201623226,"mean":40.505978424900064,"min":0.0},"per_game":{"GB2-01":66.009467280089,"GB2-02":26.66670849023619,"GB2-03":29.94096545666281,"GB2-04":39.41495254390206,"GB2-05":56.78769509728259,"GB2-06":78.57326201623226,"GB2-07":64.63907337067556,"GB2-08":45.28496051733778},"per_game_all":{"GB2-01":53.58136527665567,"GB2-02":28.266110526282077,"GB2-03":38.46160635812697,"GB2-04":37.503876411110404,"GB2-05":37.496292092010975,"GB2-06":52.01590390825098,"GB2-07":42.13847389577887,"GB2-08":34.58419893098458},"per_game_match_totals_all":{"GB2-01":{"draws":30,"losses":86,"wins":87},"GB2-02":{"draws":191,"losses":7,"wins":0},"GB2-03":{"draws":75,"losses":42,"wins":29},"GB2-04":{"draws":149,"losses":34,"wins":23},"GB2-05":{"draws":0,"losses":127,"wins":73},"GB2-06":{"draws":19,"losses":92,"wins":75},"GB2-07":{"draws":0,"losses":116,"wins":84},"GB2-08":{"draws":117,"losses":44,"wins":45}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":20,"wins":40},"GB2-02":{"draws":66,"losses":6,"wins":0},"GB2-03":{"draws":17,"losses":20,"wins":9},"GB2-04":{"draws":36,"losses":18,"wins":14},"GB2-05":{"draws":0,"losses":33,"wins":39},"GB2-06":{"draws":13,"losses":16,"wins":31},"GB2-07":{"draws":0,"losses":23,"wins":37},"GB2-08":{"draws":5,"losses":31,"wins":36}},"medium":{"GB2-01":{"draws":8,"losses":26,"wins":34},"GB2-02":{"draws":59,"losses":1,"wins":0},"GB2-03":{"draws":35,"losses":4,"wins":5},"GB2-04":{"draws":59,"losses":1,"wins":2},"GB2-05":{"draws":0,"losses":33,"wins":29},"GB2-06":{"draws":6,"losses":24,"wins":34},"GB2-07":{"draws":0,"losses":40,"wins":32},"GB2-08":{"draws":53,"losses":6,"wins":7}},"none":{"GB2-01":{"draws":22,"losses":40,"wins":13},"GB2-02":{"draws":66,"losses":0,"wins":0},"GB2-03":{"draws":23,"losses":18,"wins":15},"GB2-04":{"draws":54,"losses":15,"wins":7},"GB2-05":{"draws":0,"losses":61,"wins":5},"GB2-06":{"draws":0,"losses":52,"wins":10},"GB2-07":{"draws":0,"losses":53,"wins":15},"GB2-08":{"draws":59,"losses":7,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1547.530380581935,"GB2-02":1480.6431069929404,"GB2-03":1455.17778803087,"GB2-04":1505.8315000175164,"GB2-05":1417.5573372517363,"GB2-06":1487.6637460320235,"GB2-07":1447.4244200792446,"GB2-08":1481.921366151211},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1651.564129610822,"GB2-02":1471.706546099867,"GB2-03":1405.5751168246516,"GB2-04":1515.6939072556113,"GB2-05":1586.9806489073471,"GB2-06":1693.5550142801062,"GB2-07":1633.1851088462413,"GB2-08":1553.7066794269651},"medium":{"GB2-01":1645.9200434293616,"GB2-02":1485.1956413229286,"GB2-03":1489.5459265778684,"GB2-04":1512.2196063935532,"GB2-05":1580.9116397569835,"GB2-06":1618.383682351255,"GB2-07":1495.1492778934935,"GB2-08":1457.9749247725908},"none":{"GB2-01":1345.106968705622,"GB2-02":1485.0271335560255,"GB2-03":1470.4123206900906,"GB2-04":1489.5809864033852,"GB2-05":1084.779723090878,"GB2-06":1151.0525414647095,"GB2-07":1213.9388734979989,"GB2-08":1434.0824942540764}},"per_game_tracks":{"highest":{"GB2-01":66.009467280089,"GB2-02":26.66670849023619,"GB2-03":29.94096545666281,"GB2-04":39.41495254390206,"GB2-05":56.78769509728259,"GB2-06":78.57326201623226,"GB2-07":64.63907337067556,"GB2-08":45.28496051733778},"medium":{"GB2-01":65.69228710920916,"GB2-02":28.80911471755574,"GB2-03":43.76573750900555,"GB2-04":38.29503183096133,"GB2-05":55.70118117875034,"GB2-06":69.04627410160604,"GB2-07":48.232396684579456,"GB2-08":30.93465286854758},"none":{"GB2-01":29.04234144066881,"GB2-02":29.322508371054298,"GB2-03":41.67811610871256,"GB2-04":34.80164485846782,"GB2-05":0.0,"GB2-06":8.428175606914639,"GB2-07":13.543951632081598,"GB2-08":27.53298340706836}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.91463559655228,"medium":47.5595845000269,"none":23.043715178121012},"reasoning_agg":{"highest":{"max":78.57326201623226,"mean":50.91463559655228,"min":26.66670849023619},"medium":{"max":69.04627410160604,"mean":47.5595845000269,"min":28.80911471755574},"none":{"max":41.67811610871256,"mean":23.043715178121012,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":78.57326201623226,"expected_score":33.334479159749066,"reasoning_variance":27.870920418431268,"reliability_score":81.53289727862837,"uncertainty_avg":18.467102721371628,"uncertainty_penalty":-7.171499265150999},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.57326201623226,"expected_score":37.61372506239692,"reliability_score":81.15719212682853,"uncertainty_avg":18.842807873171466,"uncertainty_penalty":-13.300910534155364},"medium":{"ceiling_score":69.04627410160604,"expected_score":45.189718273748674,"reliability_score":80.45527668751373,"uncertainty_avg":19.544723312486266,"uncertainty_penalty":-2.3698662262782264},"none":{"ceiling_score":41.67811610871256,"expected_score":17.199994143101605,"reliability_score":82.98622302154284,"uncertainty_avg":17.013776978457155,"uncertainty_penalty":-5.843721035019406}}},{"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":12.214043999999998},"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":39.49287821132025,"highest":46.03675013303301,"medium":42.36750343993721,"none":33.466649898263285},"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":"2026-07-28T14:25:44Z","match_totals_all":{"draws":1468,"losses":1422,"wins":1193},"match_totals_tracks":{"highest":{"draws":219,"losses":301,"wins":326},"medium":{"draws":551,"losses":502,"wins":454},"none":{"draws":698,"losses":619,"wins":413}},"model_slug":"gpt-5-4-mini","overall":{"max":67.12045058181131,"mean":40.324653477455705,"min":20.66360040789551},"per_game":{"GB2-01":49.96443638296805,"GB2-02":28.0061974253885,"GB2-04":32.26121816995966,"GB2-05":48.45558701478667,"GB2-06":60.47931423585722,"GB2-07":67.12045058181131,"GB2-08":35.97004712045967},"per_game_all":{"GB2-01":43.412249225560146,"GB2-02":29.315747179701077,"GB2-04":36.936373385000046,"GB2-05":38.28948824648438,"GB2-06":53.546976836584925,"GB2-07":44.45794816684491,"GB2-08":30.491364439066285},"per_game_match_totals_all":{"GB2-01":{"draws":120,"losses":222,"wins":178},"GB2-02":{"draws":457,"losses":25,"wins":12},"GB2-03":{"draws":198,"losses":57,"wins":79},"GB2-04":{"draws":319,"losses":60,"wins":85},"GB2-05":{"draws":0,"losses":333,"wins":257},"GB2-06":{"draws":26,"losses":237,"wins":243},"GB2-07":{"draws":0,"losses":317,"wins":244},"GB2-08":{"draws":348,"losses":171,"wins":95}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":25,"wins":37},"GB2-02":{"draws":107,"losses":8,"wins":5},"GB2-04":{"draws":41,"losses":15,"wins":10},"GB2-05":{"draws":0,"losses":85,"wins":77},"GB2-06":{"draws":9,"losses":61,"wins":68},"GB2-07":{"draws":0,"losses":53,"wins":83},"GB2-08":{"draws":54,"losses":54,"wins":46}},"medium":{"GB2-01":{"draws":34,"losses":93,"wins":79},"GB2-02":{"draws":165,"losses":10,"wins":3},"GB2-03":{"draws":82,"losses":31,"wins":35},"GB2-04":{"draws":127,"losses":18,"wins":47},"GB2-05":{"draws":0,"losses":113,"wins":87},"GB2-06":{"draws":7,"losses":56,"wins":73},"GB2-07":{"draws":0,"losses":117,"wins":96},"GB2-08":{"draws":136,"losses":64,"wins":34}},"none":{"GB2-01":{"draws":78,"losses":104,"wins":62},"GB2-02":{"draws":185,"losses":7,"wins":4},"GB2-03":{"draws":116,"losses":26,"wins":44},"GB2-04":{"draws":151,"losses":27,"wins":28},"GB2-05":{"draws":0,"losses":135,"wins":93},"GB2-06":{"draws":10,"losses":120,"wins":102},"GB2-07":{"draws":0,"losses":147,"wins":65},"GB2-08":{"draws":158,"losses":53,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":1462.9297855579214,"GB2-02":1486.8309464574531,"GB2-04":1503.735535167416,"GB2-05":1422.1466624163857,"GB2-06":1496.1645923492451,"GB2-07":1465.1461958323962,"GB2-08":1451.5230149668578},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1517.1215772809917,"GB2-02":1481.8714907781737,"GB2-04":1479.9001298332687,"GB2-05":1510.4723381177262,"GB2-06":1550.4257647743148,"GB2-07":1650.3514761340175,"GB2-08":1488.8470294969834},"medium":{"GB2-01":1470.0355610813276,"GB2-02":1484.721730581664,"GB2-03":1517.0359958165827,"GB2-04":1556.355695857208,"GB2-05":1410.1215433047048,"GB2-06":1543.0297368685747,"GB2-07":1473.968923936903,"GB2-08":1437.9257705721557},"none":{"GB2-01":1401.6322183114441,"GB2-02":1493.8996180125216,"GB2-03":1522.0130614979207,"GB2-04":1474.9507798117709,"GB2-05":1345.8461058267255,"GB2-06":1395.038275404846,"GB2-07":1271.1181874262686,"GB2-08":1427.796244831434}},"per_game_tracks":{"highest":{"GB2-01":49.96443638296805,"GB2-02":28.0061974253885,"GB2-04":32.26121816995966,"GB2-05":48.45558701478667,"GB2-06":60.47931423585722,"GB2-07":67.12045058181131,"GB2-08":35.97004712045967},"medium":{"GB2-01":44.0783373251389,"GB2-02":28.609417096591248,"GB2-03":48.880676414607514,"GB2-04":47.09004736191142,"GB2-05":36.66021394048962,"GB2-06":59.47537454152446,"GB2-07":45.589793510827896,"GB2-08":28.556167328406644},"none":{"GB2-01":36.193973968573495,"GB2-02":31.33162701712348,"GB2-03":50.69935878450227,"GB2-04":31.457854623129062,"GB2-05":29.75266378417686,"GB2-06":40.6862417323731,"GB2-07":20.66360040789551,"GB2-08":26.94787886833254}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.00631927566067,"medium":39.50099125844316,"none":33.46664989826329},"reasoning_agg":{"highest":{"max":67.12045058181131,"mean":48.00631927566067,"min":28.0061974253885},"medium":{"max":48.880676414607514,"mean":39.50099125844316,"min":28.556167328406644},"none":{"max":50.69935878450227,"mean":33.46664989826329,"min":20.66360040789551}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":67.12045058181131,"expected_score":32.68667919787453,"reasoning_variance":14.53966937739738,"reliability_score":84.37221911904655,"uncertainty_avg":15.627780880953456,"uncertainty_penalty":-7.637974279581172},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.12045058181131,"expected_score":32.04425484495258,"reliability_score":84.22471227517094,"uncertainty_avg":15.775287724829056,"uncertainty_penalty":-15.96206443070809},"medium":{"ceiling_score":48.880676414607514,"expected_score":39.55703226464595,"reliability_score":82.01073862151893,"uncertainty_avg":17.989261378481075,"uncertainty_penalty":0.056041006202789845},"none":{"ceiling_score":50.69935878450227,"expected_score":30.160138563604658,"reliability_score":84.96507846522671,"uncertainty_avg":15.034921534773286,"uncertainty_penalty":-3.3065113346586337}}},{"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":0.03542156},"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":{"medium":33.50830720968977,"none":41.999446216711824},"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":{"balanced":{"admitted_plugins":11,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.21428571428571427,"model_code_failures":3,"repaired_admitted":4,"repaired_rate":0.2857142857142857},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":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":"2026-07-28T14:05:23Z","match_totals_all":{"draws":490,"losses":422,"wins":372},"match_totals_tracks":{"medium":{"draws":223,"losses":140,"wins":93},"none":{"draws":267,"losses":282,"wins":279}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":57.78007482029295,"mean":38.24632960311852,"min":25.14432619006508},"per_game_match_totals_all":{"GB2-01":{"draws":37,"losses":78,"wins":69},"GB2-02":{"draws":142,"losses":3,"wins":3},"GB2-03":{"draws":82,"losses":66,"wins":52},"GB2-04":{"draws":28,"losses":11,"wins":3},"GB2-05":{"draws":0,"losses":102,"wins":126},"GB2-06":{"draws":4,"losses":59,"wins":45},"GB2-07":{"draws":0,"losses":72,"wins":70},"GB2-08":{"draws":197,"losses":31,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":17,"wins":16},"GB2-02":{"draws":79,"losses":1,"wins":0},"GB2-03":{"draws":35,"losses":34,"wins":23},"GB2-04":{"draws":28,"losses":11,"wins":3},"GB2-05":{"draws":0,"losses":44,"wins":38},"GB2-06":{"draws":2,"losses":25,"wins":13},"GB2-08":{"draws":72,"losses":8,"wins":0}},"none":{"GB2-01":{"draws":30,"losses":61,"wins":53},"GB2-02":{"draws":63,"losses":2,"wins":3},"GB2-03":{"draws":47,"losses":32,"wins":29},"GB2-05":{"draws":0,"losses":58,"wins":88},"GB2-06":{"draws":2,"losses":34,"wins":32},"GB2-07":{"draws":0,"losses":72,"wins":70},"GB2-08":{"draws":125,"losses":23,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1529.2540851627805,"GB2-02":1486.8015103198877,"GB2-03":1466.4133062610467,"GB2-04":1430.9775454210896,"GB2-05":1459.2244791836265,"GB2-06":1329.652340117982,"GB2-08":1447.1389788429522},"none":{"GB2-01":1580.1311314556106,"GB2-02":1479.0793242660857,"GB2-03":1474.2626908622497,"GB2-05":1557.7736742656498,"GB2-06":1339.4494417733786,"GB2-07":1543.8923351018686,"GB2-08":1415.2360604768314}},"per_game_tracks":{"medium":{"GB2-01":49.61263023531744,"GB2-02":26.535186804870882,"GB2-03":40.052249674800194,"GB2-04":20.297397019060018,"GB2-05":40.72006671556793,"GB2-06":29.992356003355756,"GB2-08":27.34826401485616},"none":{"GB2-01":57.78007482029295,"GB2-02":28.088937044196097,"GB2-03":42.157772095744875,"GB2-05":53.53386125944371,"GB2-06":33.11476703447791,"GB2-07":54.17638507276214,"GB2-08":25.14432619006508}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.69429746904836,"none":44.79836173718868},"reasoning_agg":{"medium":{"max":40.72006671556793,"mean":31.69429746904836,"min":26.535186804870882},"none":{"max":57.78007482029295,"mean":44.79836173718868,"min":25.14432619006508}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":57.78007482029295,"reasoning_variance":13.104064268140316},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.72006671556793,"expected_score":21.89422542888818,"reliability_score":66.72878950597988,"uncertainty_avg":33.27121049402013,"uncertainty_penalty":-9.800072040160181},"none":{"ceiling_score":57.78007482029295,"expected_score":37.86990474979848,"reliability_score":83.69317238002219,"uncertainty_avg":16.306827619977817,"uncertainty_penalty":-6.928456987390199}}},{"display_name":"GPT 4.1","economics":{"none":38.229690939088194},"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-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-07-28T14:13:56Z","match_totals_all":{"draws":115,"losses":139,"wins":114},"match_totals_tracks":{"none":{"draws":115,"losses":139,"wins":114}},"model_slug":"gpt-4-1","overall":{"max":58.41725935320175,"mean":38.229690939088194,"min":22.567673997988543},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":24,"wins":23},"GB2-02":{"draws":35,"losses":10,"wins":3},"GB2-03":{"draws":10,"losses":11,"wins":11},"GB2-04":{"draws":27,"losses":9,"wins":2},"GB2-05":{"draws":0,"losses":32,"wins":20},"GB2-06":{"draws":9,"losses":17,"wins":22},"GB2-07":{"draws":0,"losses":22,"wins":26},"GB2-08":{"draws":33,"losses":14,"wins":7}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":1,"losses":24,"wins":23},"GB2-02":{"draws":35,"losses":10,"wins":3},"GB2-03":{"draws":10,"losses":11,"wins":11},"GB2-04":{"draws":27,"losses":9,"wins":2},"GB2-05":{"draws":0,"losses":32,"wins":20},"GB2-06":{"draws":9,"losses":17,"wins":22},"GB2-07":{"draws":0,"losses":22,"wins":26},"GB2-08":{"draws":33,"losses":14,"wins":7}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1595.6478858053922,"GB2-02":1464.639645646619,"GB2-03":1525.6726149306114,"GB2-04":1461.6738793317916,"GB2-05":1322.2740939222144,"GB2-06":1509.3680825685708,"GB2-07":1491.4730488103537,"GB2-08":1419.0289552749614}},"per_game_tracks":{"none":{"GB2-01":58.41725935320175,"GB2-02":22.567673997988543,"GB2-03":48.13346165011627,"GB2-04":25.714447304211713,"GB2-05":26.061739119033867,"GB2-06":53.954368519741806,"GB2-07":46.513294527136985,"GB2-08":24.4752830412746}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":38.229690939088194},"reasoning_agg":{"none":{"max":58.41725935320175,"mean":38.229690939088194,"min":22.567673997988543}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":58.41725935320175},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":58.41725935320175,"expected_score":37.0208760108105,"reliability_score":70.13531764808162,"uncertainty_avg":29.864682351918372,"uncertainty_penalty":-1.2088149282776968}}},{"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":0.6541030000000001},"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":1.2459757},"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":{"all":38.04999466146857,"highest":37.318694787135065,"medium":34.975724003478376,"none":41.85556519379226},"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},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.0625,"model_code_failures":1,"repaired_admitted":6,"repaired_rate":0.375},"intensive":{"admitted_plugins":16,"evaluated_cells":16,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":16,"repaired_rate":1.0}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-07-28T14:20:40Z","match_totals_all":{"draws":835,"losses":793,"wins":653},"match_totals_tracks":{"highest":{"draws":232,"losses":230,"wins":188},"medium":{"draws":375,"losses":361,"wins":276},"none":{"draws":228,"losses":202,"wins":189}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":65.59672084205211,"mean":37.2165744025808,"min":16.104435348457244},"per_game":{"GB2-01":44.32676559611745,"GB2-02":27.313114249541627,"GB2-03":48.182537706309986,"GB2-04":24.65794235582206,"GB2-05":27.718084716562302,"GB2-06":54.416169208957584,"GB2-07":45.39923138366146,"GB2-08":26.535713080108053},"per_game_all":{"GB2-01":46.92690004756427,"GB2-02":27.248702499108592,"GB2-03":50.66435736162763,"GB2-04":32.50535303277079,"GB2-05":25.158249482225333,"GB2-06":53.121120827239885,"GB2-07":43.25252354109582,"GB2-08":25.522750500116217},"per_game_match_totals_all":{"GB2-01":{"draws":70,"losses":125,"wins":107},"GB2-02":{"draws":277,"losses":16,"wins":9},"GB2-03":{"draws":66,"losses":80,"wins":88},"GB2-04":{"draws":221,"losses":45,"wins":33},"GB2-05":{"draws":0,"losses":191,"wins":113},"GB2-06":{"draws":10,"losses":139,"wins":147},"GB2-07":{"draws":0,"losses":156,"wins":150},"GB2-08":{"draws":191,"losses":41,"wins":6}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":31,"wins":34},"GB2-02":{"draws":73,"losses":8,"wins":5},"GB2-03":{"draws":17,"losses":28,"wins":35},"GB2-04":{"draws":54,"losses":20,"wins":6},"GB2-05":{"draws":0,"losses":52,"wins":28},"GB2-06":{"draws":6,"losses":33,"wins":43},"GB2-07":{"draws":0,"losses":45,"wins":35},"GB2-08":{"draws":65,"losses":13,"wins":2}},"medium":{"GB2-01":{"draws":33,"losses":59,"wins":46},"GB2-02":{"draws":128,"losses":4,"wins":4},"GB2-03":{"draws":39,"losses":37,"wins":32},"GB2-04":{"draws":110,"losses":15,"wins":11},"GB2-05":{"draws":0,"losses":74,"wins":70},"GB2-06":{"draws":2,"losses":76,"wins":56},"GB2-07":{"draws":0,"losses":84,"wins":54},"GB2-08":{"draws":63,"losses":12,"wins":3}},"none":{"GB2-01":{"draws":20,"losses":35,"wins":27},"GB2-02":{"draws":76,"losses":4,"wins":0},"GB2-03":{"draws":10,"losses":15,"wins":21},"GB2-04":{"draws":57,"losses":10,"wins":16},"GB2-05":{"draws":0,"losses":65,"wins":15},"GB2-06":{"draws":2,"losses":30,"wins":48},"GB2-07":{"draws":0,"losses":27,"wins":61},"GB2-08":{"draws":63,"losses":16,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1502.0109345698063,"GB2-02":1484.370175547122,"GB2-03":1529.4297695986709,"GB2-04":1489.6075717328893,"GB2-05":1316.5634559616008,"GB2-06":1503.3622948600514,"GB2-07":1464.4663503610211,"GB2-08":1428.877923693429},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1485.461630546597,"GB2-02":1488.0407102716295,"GB2-03":1518.8045895923876,"GB2-04":1454.7005256518378,"GB2-05":1344.507066095575,"GB2-06":1517.5258657548443,"GB2-07":1487.72530199432,"GB2-08":1441.6022524023415},"medium":{"GB2-01":1508.002377032948,"GB2-02":1485.6026896410888,"GB2-03":1514.7661688567837,"GB2-04":1488.7270691853464,"GB2-05":1363.8008431067105,"GB2-06":1400.455016932588,"GB2-07":1256.0968716450686,"GB2-08":1426.8485145766456},"none":{"GB2-01":1512.5687961298731,"GB2-02":1479.4671267286474,"GB2-03":1554.7185503468413,"GB2-04":1525.3951203614834,"GB2-05":1241.3824586825172,"GB2-06":1592.1060018927215,"GB2-07":1649.5768774436744,"GB2-08":1418.1830041013}},"per_game_tracks":{"highest":{"GB2-01":44.32676559611745,"GB2-02":27.313114249541627,"GB2-03":48.182537706309986,"GB2-04":24.65794235582206,"GB2-05":27.718084716562302,"GB2-06":54.416169208957584,"GB2-07":45.39923138366146,"GB2-08":26.535713080108053},"medium":{"GB2-01":48.799407549015086,"GB2-02":29.626281978687146,"GB2-03":48.93407865935556,"GB2-04":34.12994957973507,"GB2-05":31.652228381656457,"GB2-06":40.968473786581654,"GB2-07":18.761618397573876,"GB2-08":26.93375369522216},"none":{"GB2-01":47.65452699756027,"GB2-02":24.806711269097008,"GB2-03":54.87645571921736,"GB2-04":38.728167162755256,"GB2-05":16.104435348457244,"GB2-06":63.978719486180424,"GB2-07":65.59672084205211,"GB2-08":23.09878472501844}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.318694787135065,"medium":34.975724003478376,"none":39.35530441712897},"reasoning_agg":{"highest":{"max":54.416169208957584,"mean":37.318694787135065,"min":24.65794235582206},"medium":{"max":48.93407865935556,"mean":34.975724003478376,"min":18.761618397573876},"none":{"max":65.59672084205211,"mean":39.35530441712897,"min":16.104435348457244}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":65.59672084205211,"expected_score":31.52643067837165,"reasoning_variance":4.379580413650594,"reliability_score":72.2084968288344,"uncertainty_avg":27.791503171165605,"uncertainty_penalty":-5.690143724209147},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.416169208957584,"expected_score":22.32690159441981,"reliability_score":66.21496760265678,"uncertainty_avg":33.785032397343215,"uncertainty_penalty":-14.991793192715257},"medium":{"ceiling_score":48.93407865935556,"expected_score":26.23886519614034,"reliability_score":83.3988114890431,"uncertainty_avg":16.601188510956906,"uncertainty_penalty":-8.736858807338038},"none":{"ceiling_score":65.59672084205211,"expected_score":46.0135252445548,"reliability_score":67.01171139480331,"uncertainty_avg":32.988288605196686,"uncertainty_penalty":6.658220827425829}}},{"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":39.493143233240566},"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":"2026-07-28T14:20:19Z","match_totals_all":{"draws":99,"losses":153,"wins":148},"match_totals_tracks":{"medium":{"draws":99,"losses":153,"wins":148}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":50.08769058988257,"mean":36.75251099406887,"min":22.70566675564503},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":36,"wins":35},"GB2-02":{"draws":50,"losses":8,"wins":4},"GB2-04":{"draws":41,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":32,"wins":32},"GB2-07":{"draws":0,"losses":38,"wins":38},"GB2-08":{"draws":5,"losses":31,"wins":34}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":3,"losses":36,"wins":35},"GB2-02":{"draws":50,"losses":8,"wins":4},"GB2-04":{"draws":41,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":32,"wins":32},"GB2-07":{"draws":0,"losses":38,"wins":38},"GB2-08":{"draws":5,"losses":31,"wins":34}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1485.3202894527853,"GB2-02":1478.818920246194,"GB2-04":1478.3624828489033,"GB2-05":1551.1864518949787,"GB2-07":1505.9951069361296,"GB2-08":1579.5542058306291}},"per_game_tracks":{"medium":{"GB2-01":43.86982638125299,"GB2-02":22.70566675564503,"GB2-04":26.715924950634403,"GB2-05":50.08769058988257,"GB2-07":47.440252674187406,"GB2-08":46.139498047840995}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.75251099406887},"reasoning_agg":{"medium":{"max":50.08769058988257,"mean":36.75251099406887,"min":22.70566675564503}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":50.08769058988257},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":50.08769058988257,"expected_score":40.460760877571765,"reliability_score":57.67660772219112,"uncertainty_avg":42.32339227780888,"uncertainty_penalty":3.7082498835028943}}},{"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":0.7838332080000001},"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":{"medium":35.6039145637046,"none":37.69862788583894},"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":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-07"],"model_code_failure_rate":0.25,"model_code_failures":4,"repaired_admitted":12,"repaired_rate":0.75},"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":"2026-07-28T14:18:34Z","match_totals_all":{"draws":466,"losses":564,"wins":422},"match_totals_tracks":{"medium":{"draws":126,"losses":198,"wins":162},"none":{"draws":340,"losses":366,"wins":260}},"model_slug":"meituan-longcat-2-0","overall":{"max":52.68328320554838,"mean":36.67666434878586,"min":19.110605512666282},"per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":74,"wins":53},"GB2-02":{"draws":105,"losses":2,"wins":1},"GB2-03":{"draws":64,"losses":45,"wins":37},"GB2-04":{"draws":90,"losses":36,"wins":22},"GB2-05":{"draws":0,"losses":152,"wins":80},"GB2-06":{"draws":20,"losses":113,"wins":91},"GB2-07":{"draws":0,"losses":102,"wins":78},"GB2-08":{"draws":134,"losses":40,"wins":60}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":8,"losses":23,"wins":9},"GB2-02":{"draws":38,"losses":1,"wins":1},"GB2-03":{"draws":13,"losses":13,"wins":14},"GB2-04":{"draws":50,"losses":21,"wins":5},"GB2-05":{"draws":0,"losses":44,"wins":36},"GB2-06":{"draws":4,"losses":41,"wins":37},"GB2-07":{"draws":0,"losses":30,"wins":10},"GB2-08":{"draws":13,"losses":25,"wins":50}},"none":{"GB2-01":{"draws":45,"losses":51,"wins":44},"GB2-02":{"draws":67,"losses":1,"wins":0},"GB2-03":{"draws":51,"losses":32,"wins":23},"GB2-04":{"draws":40,"losses":15,"wins":17},"GB2-05":{"draws":0,"losses":108,"wins":44},"GB2-06":{"draws":16,"losses":72,"wins":54},"GB2-07":{"draws":0,"losses":72,"wins":68},"GB2-08":{"draws":121,"losses":15,"wins":10}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1350.7099043205549,"GB2-02":1488.4802759099048,"GB2-03":1485.579958543174,"GB2-04":1428.0361868117898,"GB2-05":1444.2493780275927,"GB2-06":1489.6655927187935,"GB2-07":1338.508430902618,"GB2-08":1609.7478743689626},"none":{"GB2-01":1479.712151375022,"GB2-02":1479.8498057623008,"GB2-03":1435.8645295095275,"GB2-04":1567.8900482908955,"GB2-05":1291.7650957838455,"GB2-06":1489.5533572194072,"GB2-07":1425.6834784375706,"GB2-08":1424.741434099927}},"per_game_tracks":{"medium":{"GB2-01":27.69398176453986,"GB2-02":26.930817223780124,"GB2-03":42.62766717370032,"GB2-04":19.110605512666282,"GB2-05":38.95082796767443,"GB2-06":50.80841094896175,"GB2-07":27.07988040375173,"GB2-08":51.629125514562325},"none":{"GB2-01":45.364984428329535,"GB2-02":28.27051445972222,"GB2-03":35.65812376396222,"GB2-04":49.905158234128194,"GB2-05":23.678689003402724,"GB2-06":52.68328320554838,"GB2-07":39.623691787988626,"GB2-08":26.40457820362962}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.3402803276606,"none":36.013048369911125},"reasoning_agg":{"medium":{"max":51.629125514562325,"mean":37.3402803276606,"min":19.110605512666282},"none":{"max":52.68328320554838,"mean":36.013048369911125,"min":23.678689003402724}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":52.68328320554838,"reasoning_variance":1.3272319577494756},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":51.629125514562325,"expected_score":26.60648916713608,"reliability_score":65.9648407093373,"uncertainty_avg":34.03515929066271,"uncertainty_penalty":-10.733791160524522},"none":{"ceiling_score":52.68328320554838,"expected_score":38.288988047800224,"reliability_score":83.80438359943008,"uncertainty_avg":16.19561640056991,"uncertainty_penalty":2.275939677889099}}},{"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":0.4852846}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.4852846},"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":36.523576553430594},"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":"2026-07-28T14:20:22Z","match_totals_all":{"draws":204,"losses":181,"wins":155},"match_totals_tracks":{"medium":{"draws":204,"losses":181,"wins":155}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":54.36254340229122,"mean":36.523576553430594,"min":26.05177390846129},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":25,"wins":33},"GB2-02":{"draws":62,"losses":3,"wins":3},"GB2-03":{"draws":22,"losses":17,"wins":13},"GB2-04":{"draws":44,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":34,"wins":38},"GB2-06":{"draws":0,"losses":42,"wins":32},"GB2-07":{"draws":0,"losses":48,"wins":28},"GB2-08":{"draws":58,"losses":7,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":18,"losses":25,"wins":33},"GB2-02":{"draws":62,"losses":3,"wins":3},"GB2-03":{"draws":22,"losses":17,"wins":13},"GB2-04":{"draws":44,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":34,"wins":38},"GB2-06":{"draws":0,"losses":42,"wins":32},"GB2-07":{"draws":0,"losses":48,"wins":28},"GB2-08":{"draws":58,"losses":7,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1521.0899764792007,"GB2-02":1499.439284396754,"GB2-03":1476.2061760610338,"GB2-04":1491.0702022455998,"GB2-05":1584.4616042814541,"GB2-06":1412.0398684673114,"GB2-07":1331.7159371543019,"GB2-08":1451.5419532312194}},"per_game_tracks":{"medium":{"GB2-01":48.345177320992626,"GB2-02":28.222704296745306,"GB2-03":38.52676108585284,"GB2-04":29.206053319112105,"GB2-05":54.36254340229122,"GB2-06":40.345666702865955,"GB2-07":26.05177390846129,"GB2-08":27.12793239112333}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.523576553430594},"reasoning_agg":{"medium":{"max":54.36254340229122,"mean":36.523576553430594,"min":26.05177390846129}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":54.36254340229122},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":54.36254340229122,"expected_score":33.24651014819849,"reliability_score":57.97003100576907,"uncertainty_avg":42.02996899423093,"uncertainty_penalty":-3.2770664052321052}}},{"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":0.036200562500000005,"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":0.7792869},"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":0.0089983359375,"median":0.00845865,"min":0.005806287500000001,"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":0.005806287500000001,"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":38.43075354396698,"highest":43.482539842415,"medium":35.12335638236132,"none":36.6863644071246},"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":"2026-07-28T14:25:37Z","match_totals_all":{"draws":1486,"losses":1746,"wins":1232},"match_totals_tracks":{"highest":{"draws":342,"losses":357,"wins":322},"medium":{"draws":447,"losses":741,"wins":446},"none":{"draws":697,"losses":648,"wins":464}},"model_slug":"gpt-5-4-nano","overall":{"max":56.7053357897197,"mean":34.768248001095024,"min":18.627201153602226},"per_game":{"GB2-01":26.454663169959055,"GB2-02":29.107273937099983,"GB2-03":32.99741978352148,"GB2-04":26.762745683873376,"GB2-05":62.31622191250514,"GB2-06":80.10729776560946,"GB2-07":47.03075175978695,"GB2-08":43.08394472696457},"per_game_all":{"GB2-01":27.20688702992963,"GB2-02":27.770358007719384,"GB2-03":34.075824727235805,"GB2-04":35.68649520292076,"GB2-05":42.5478989952294,"GB2-06":66.02766053523531,"GB2-07":35.45817254552018,"GB2-08":38.67273130794535},"per_game_match_totals_all":{"GB2-01":{"draws":186,"losses":348,"wins":146},"GB2-02":{"draws":516,"losses":41,"wins":12},"GB2-03":{"draws":114,"losses":111,"wins":69},"GB2-04":{"draws":222,"losses":91,"wins":85},"GB2-05":{"draws":0,"losses":385,"wins":272},"GB2-06":{"draws":26,"losses":247,"wins":274},"GB2-07":{"draws":0,"losses":359,"wins":194},"GB2-08":{"draws":422,"losses":164,"wins":180}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":44,"losses":68,"wins":16},"GB2-02":{"draws":122,"losses":14,"wins":6},"GB2-03":{"draws":15,"losses":23,"wins":12},"GB2-04":{"draws":41,"losses":48,"wins":39},"GB2-05":{"draws":0,"losses":62,"wins":83},"GB2-06":{"draws":5,"losses":19,"wins":34},"GB2-07":{"draws":0,"losses":75,"wins":63},"GB2-08":{"draws":115,"losses":48,"wins":69}},"medium":{"GB2-01":{"draws":54,"losses":149,"wins":39},"GB2-02":{"draws":166,"losses":12,"wins":3},"GB2-03":{"draws":24,"losses":15,"wins":9},"GB2-04":{"draws":79,"losses":21,"wins":34},"GB2-05":{"draws":0,"losses":158,"wins":120},"GB2-06":{"draws":19,"losses":138,"wins":121},"GB2-07":{"draws":0,"losses":196,"wins":65},"GB2-08":{"draws":105,"losses":52,"wins":55}},"none":{"GB2-01":{"draws":88,"losses":131,"wins":91},"GB2-02":{"draws":228,"losses":15,"wins":3},"GB2-03":{"draws":75,"losses":73,"wins":48},"GB2-04":{"draws":102,"losses":22,"wins":12},"GB2-05":{"draws":0,"losses":165,"wins":69},"GB2-06":{"draws":2,"losses":90,"wins":119},"GB2-07":{"draws":0,"losses":88,"wins":66},"GB2-08":{"draws":202,"losses":64,"wins":56}}},"per_game_raw_elo_all":{"GB2-01":1332.9173471346435,"GB2-02":1479.2825876469353,"GB2-03":1426.1538135504559,"GB2-04":1497.3408641449057,"GB2-05":1460.2203223403387,"GB2-06":1594.6183299896275,"GB2-07":1391.747518913472,"GB2-08":1507.4494147107598},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1327.7590941659082,"GB2-02":1482.4172399788183,"GB2-03":1421.5214998503109,"GB2-04":1452.7457500042349,"GB2-05":1635.9130760534545,"GB2-06":1706.2621455889364,"GB2-07":1486.357847233641,"GB2-08":1537.1465319902456},"medium":{"GB2-01":1265.3944063454137,"GB2-02":1477.5347483291528,"GB2-03":1408.753378227649,"GB2-04":1553.3846151354655,"GB2-05":1426.3118889255838,"GB2-06":1521.4335316601127,"GB2-07":1291.462134846176,"GB2-08":1516.3804905109112},"none":{"GB2-01":1405.5985408926085,"GB2-02":1477.895774632835,"GB2-03":1448.1865625734079,"GB2-04":1485.8922272950165,"GB2-05":1318.4360020419783,"GB2-06":1556.1593127198328,"GB2-07":1397.4225746605987,"GB2-08":1468.8212216311229}},"per_game_tracks":{"highest":{"GB2-01":26.454663169959055,"GB2-02":29.107273937099983,"GB2-03":32.99741978352148,"GB2-04":26.762745683873376,"GB2-05":62.31622191250514,"GB2-06":80.10729776560946,"GB2-07":47.03075175978695,"GB2-08":43.08394472696457},"medium":{"GB2-01":18.627201153602226,"GB2-02":26.990514006288123,"GB2-03":30.673497730348966,"GB2-04":46.72452033118674,"GB2-05":38.5948252431647,"GB2-06":56.7053357897197,"GB2-07":22.930597095678568,"GB2-08":39.74035970890156},"none":{"GB2-01":36.5387967662276,"GB2-02":27.213286079770054,"GB2-03":38.55655666783695,"GB2-04":33.57221959370216,"GB2-05":26.732649830018364,"GB2-06":61.270348050376754,"GB2-07":36.413168781095024,"GB2-08":33.193889487969926}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.75668798962776,"medium":32.16677906187513,"none":30.381276951782198},"reasoning_agg":{"highest":{"max":43.08394472696457,"mean":41.75668798962776,"min":43.08394472696457},"medium":{"max":56.7053357897197,"mean":32.16677906187513,"min":18.627201153602226},"none":{"max":36.5387967662276,"mean":30.381276951782198,"min":27.213286079770054}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":56.7053357897197,"expected_score":30.22735322857696,"reasoning_variance":11.37541103784556,"reliability_score":82.79454875868116,"uncertainty_avg":17.205451241318844,"uncertainty_penalty":-4.540894772518065},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":43.08394472696457,"expected_score":28.307128918269214,"reliability_score":82.12970872172521,"uncertainty_avg":17.870291278274795,"uncertainty_penalty":-13.449559071358543},"medium":{"ceiling_score":56.7053357897197,"expected_score":29.26946521918751,"reliability_score":81.23199247141171,"uncertainty_avg":18.768007528588285,"uncertainty_penalty":-2.8973138426876233},"none":{"ceiling_score":36.5387967662276,"expected_score":33.10546554827417,"reliability_score":85.02194508290656,"uncertainty_avg":14.97805491709345,"uncertainty_penalty":2.7241885964919703}}},{"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":0.0022439992166666664,"min":0.0016912200000000002,"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":0.0016912200000000002,"recorded_attempt_count":81,"run_count":45,"total":0.49297782779999993},"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":{"all":32.438452046219524,"highest":32.31359433900621,"medium":32.46596257175619,"none":38.47534146023609},"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":"2026-07-28T14:25:35Z","match_totals_all":{"draws":959,"losses":869,"wins":667},"match_totals_tracks":{"highest":{"draws":154,"losses":47,"wins":29},"medium":{"draws":424,"losses":360,"wins":256},"none":{"draws":381,"losses":462,"wins":382}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":54.00279670242382,"mean":34.0160882243888,"min":21.31811178953796},"per_game":{"GB2-01":21.31811178953796,"GB2-02":26.556929863045585,"GB2-04":33.18635365584194,"GB2-06":54.00279670242382,"GB2-08":26.503779684181723},"per_game_all":{"GB2-01":36.47915525538282,"GB2-02":25.643484164464322,"GB2-04":31.131297228517624,"GB2-06":44.81745660009733,"GB2-08":24.12086698263551},"per_game_match_totals_all":{"GB2-01":{"draws":109,"losses":193,"wins":148},"GB2-02":{"draws":280,"losses":19,"wins":9},"GB2-03":{"draws":32,"losses":9,"wins":13},"GB2-04":{"draws":297,"losses":48,"wins":31},"GB2-05":{"draws":0,"losses":195,"wins":179},"GB2-06":{"draws":12,"losses":171,"wins":129},"GB2-07":{"draws":0,"losses":155,"wins":137},"GB2-08":{"draws":229,"losses":79,"wins":21}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":33,"losses":13,"wins":2},"GB2-02":{"draws":37,"losses":3,"wins":2},"GB2-04":{"draws":34,"losses":6,"wins":4},"GB2-06":{"draws":7,"losses":20,"wins":19},"GB2-08":{"draws":43,"losses":5,"wins":2}},"medium":{"GB2-01":{"draws":15,"losses":79,"wins":62},"GB2-02":{"draws":182,"losses":13,"wins":7},"GB2-04":{"draws":151,"losses":32,"wins":11},"GB2-05":{"draws":0,"losses":75,"wins":71},"GB2-06":{"draws":4,"losses":43,"wins":19},"GB2-07":{"draws":0,"losses":71,"wins":69},"GB2-08":{"draws":72,"losses":47,"wins":17}},"none":{"GB2-01":{"draws":61,"losses":101,"wins":84},"GB2-02":{"draws":61,"losses":3,"wins":0},"GB2-03":{"draws":32,"losses":9,"wins":13},"GB2-04":{"draws":112,"losses":10,"wins":16},"GB2-05":{"draws":0,"losses":120,"wins":108},"GB2-06":{"draws":1,"losses":108,"wins":91},"GB2-07":{"draws":0,"losses":84,"wins":68},"GB2-08":{"draws":114,"losses":27,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1414.8509004854666,"GB2-02":1480.155776045967,"GB2-04":1484.2285577169623,"GB2-06":1440.4514507058784,"GB2-08":1419.808439644061},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1293.44691203047,"GB2-02":1485.4236953036248,"GB2-04":1495.3820186822695,"GB2-06":1510.9452000729912,"GB2-08":1434.926356676387},"medium":{"GB2-01":1450.6158500453048,"GB2-02":1487.3752085158424,"GB2-04":1467.6696849478947,"GB2-05":1452.437119934852,"GB2-06":1352.2800561719391,"GB2-07":1460.3930939120603,"GB2-08":1425.1532366100796},"none":{"GB2-01":1500.4899393806245,"GB2-02":1467.6684243184336,"GB2-03":1537.4103736250274,"GB2-04":1489.6339695207228,"GB2-05":1440.4746000437187,"GB2-06":1458.1290958727047,"GB2-07":1393.4300130649822,"GB2-08":1399.3457256457168}},"per_game_tracks":{"highest":{"GB2-01":21.31811178953796,"GB2-02":26.556929863045585,"GB2-04":33.18635365584194,"GB2-06":54.00279670242382,"GB2-08":26.503779684181723},"medium":{"GB2-01":39.778720091077076,"GB2-02":25.317732419636,"GB2-04":25.832208736362677,"GB2-05":39.53879167672064,"GB2-06":32.05553353444414,"GB2-07":41.48763391684104,"GB2-08":23.251117627211734},"none":{"GB2-01":48.34063388553343,"GB2-02":25.05579021071138,"GB2-03":52.71999356132024,"GB2-04":34.37532929334826,"GB2-05":40.426434768286235,"GB2-06":48.39403956342402,"GB2-07":35.88280676275207,"GB2-08":22.607703636513072}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.3135943390062,"medium":27.790737369360915,"none":41.94393296479929},"reasoning_agg":{"highest":{"max":54.00279670242382,"mean":32.3135943390062,"min":21.31811178953796},"medium":{"max":39.53879167672064,"mean":27.790737369360915,"min":25.317732419636},"none":{"max":48.39403956342402,"mean":41.94393296479929,"min":40.426434768286235}},"reasoning_labels":{"highest":"Highest","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":54.00279670242382,"expected_score":21.178479042717278,"reasoning_variance":14.153195595438373,"reliability_score":71.36665717419885,"uncertainty_avg":28.63334282580115,"uncertainty_penalty":-12.837609181671525},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.00279670242382,"expected_score":15.995359924934329,"reliability_score":70.7180088409571,"uncertainty_avg":29.2819911590429,"uncertainty_penalty":-16.318234414071874},"medium":{"ceiling_score":39.53879167672064,"expected_score":27.391515491405595,"reliability_score":59.53703973035844,"uncertainty_avg":40.46296026964156,"uncertainty_penalty":-0.3992218779553198},"none":{"ceiling_score":48.39403956342402,"expected_score":36.29175713489998,"reliability_score":83.97955972388449,"uncertainty_avg":16.02044027611551,"uncertainty_penalty":-5.652175829899306}}},{"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":2.89486441},"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":0.8573406100000001},"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":4.173245870000001},"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":{"all":38.323742415291974,"highest":33.472434379472425,"medium":37.59262789303127,"none":39.15618531330332},"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},"intensive":{"admitted_plugins":5,"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":0.6875,"model_code_failures":11,"repaired_admitted":5,"repaired_rate":0.3125}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-07-28T14:25:54Z","match_totals_all":{"draws":539,"losses":712,"wins":499},"match_totals_tracks":{"highest":{"draws":73,"losses":80,"wins":47},"medium":{"draws":201,"losses":307,"wins":250},"none":{"draws":265,"losses":325,"wins":202}},"model_slug":"thinkingmachines-inkling","overall":{"max":56.38461999769895,"mean":33.842373841997734,"min":21.490248857365412},"per_game":{"GB2-02":21.490248857365412,"GB2-05":32.633729875248896,"GB2-06":56.38461999769895,"GB2-07":33.574993196819115,"GB2-08":23.278579970229753},"per_game_all":{"GB2-02":27.144870469098567,"GB2-05":35.37366817389614,"GB2-06":44.52931132539097,"GB2-07":39.34264080252054,"GB2-08":45.22822130555363},"per_game_match_totals_all":{"GB2-01":{"draws":101,"losses":107,"wins":58},"GB2-02":{"draws":170,"losses":11,"wins":1},"GB2-03":{"draws":49,"losses":27,"wins":28},"GB2-04":{"draws":181,"losses":44,"wins":21},"GB2-05":{"draws":0,"losses":200,"wins":138},"GB2-06":{"draws":4,"losses":95,"wins":79},"GB2-07":{"draws":0,"losses":142,"wins":110},"GB2-08":{"draws":34,"losses":86,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":37,"losses":3,"wins":0},"GB2-05":{"draws":0,"losses":26,"wins":14},"GB2-06":{"draws":4,"losses":16,"wins":20},"GB2-07":{"draws":0,"losses":27,"wins":13},"GB2-08":{"draws":32,"losses":8,"wins":0}},"medium":{"GB2-01":{"draws":41,"losses":51,"wins":40},"GB2-02":{"draws":65,"losses":7,"wins":0},"GB2-04":{"draws":94,"losses":20,"wins":10},"GB2-05":{"draws":0,"losses":80,"wins":66},"GB2-06":{"draws":0,"losses":39,"wins":29},"GB2-07":{"draws":0,"losses":70,"wins":70},"GB2-08":{"draws":1,"losses":40,"wins":35}},"none":{"GB2-01":{"draws":60,"losses":56,"wins":18},"GB2-02":{"draws":68,"losses":1,"wins":1},"GB2-03":{"draws":49,"losses":27,"wins":28},"GB2-04":{"draws":87,"losses":24,"wins":11},"GB2-05":{"draws":0,"losses":94,"wins":58},"GB2-06":{"draws":0,"losses":40,"wins":30},"GB2-07":{"draws":0,"losses":45,"wins":27},"GB2-08":{"draws":1,"losses":38,"wins":29}}},"per_game_raw_elo_all":{"GB2-02":1479.1714662620768,"GB2-05":1401.543272114645,"GB2-06":1432.1402643085348,"GB2-07":1428.1942512627502,"GB2-08":1558.572958112047},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1465.3944904719365,"GB2-05":1388.1560485216878,"GB2-06":1533.4619160186658,"GB2-07":1391.4131658701433,"GB2-08":1419.4081298694048},"medium":{"GB2-01":1374.5686769444528,"GB2-02":1474.1670464469105,"GB2-04":1469.7720632989315,"GB2-05":1369.83148176115,"GB2-06":1343.2749498156031,"GB2-07":1537.2218616190091,"GB2-08":1614.2416876518455},"none":{"GB2-01":1323.573017817066,"GB2-02":1497.9528618673835,"GB2-03":1523.5775043253361,"GB2-04":1472.0646112026466,"GB2-05":1446.6422860610978,"GB2-06":1419.683927091336,"GB2-07":1355.947726299098,"GB2-08":1642.069056814891}},"per_game_tracks":{"highest":{"GB2-02":21.490248857365412,"GB2-05":32.633729875248896,"GB2-06":56.38461999769895,"GB2-07":33.574993196819115,"GB2-08":23.278579970229753},"medium":{"GB2-01":32.29275120751978,"GB2-02":27.24656835203928,"GB2-04":29.973531381461957,"GB2-05":32.36538339716046,"GB2-06":33.61015012782225,"GB2-07":53.31030301892844,"GB2-08":54.34970776628676},"none":{"GB2-01":26.076154627904987,"GB2-02":32.69779419789101,"GB2-03":50.23868920571299,"GB2-04":30.32278700302832,"GB2-05":41.121891249279095,"GB2-06":43.593163850651706,"GB2-07":31.142626191814056,"GB2-08":58.05637618014437}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.472434379472425,"medium":33.67825483857925,"none":34.37643230794154},"reasoning_agg":{"highest":{"max":56.38461999769895,"mean":33.472434379472425,"min":21.490248857365412},"medium":{"max":53.31030301892844,"mean":33.67825483857925,"min":29.973531381461957},"none":{"max":50.23868920571299,"mean":34.37643230794154,"min":26.076154627904987}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":56.38461999769895,"expected_score":31.65488900369914,"reasoning_variance":0.9039979284691171,"reliability_score":78.54535283994989,"uncertainty_avg":21.454647160050108,"uncertainty_penalty":-2.1874848382985945},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.38461999769895,"expected_score":19.948659994081652,"reliability_score":65.66311905569697,"uncertainty_avg":34.33688094430304,"uncertainty_penalty":-13.523774385390773},"medium":{"ceiling_score":53.31030301892844,"expected_score":28.8250202727721,"reliability_score":84.12628938603414,"uncertainty_avg":15.873710613965855,"uncertainty_penalty":-4.853234565807149},"none":{"ceiling_score":50.23868920571299,"expected_score":40.32260219661824,"reliability_score":82.83165868241004,"uncertainty_avg":17.16834131758996,"uncertainty_penalty":5.9461698886767}}},{"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":0.7875583200000001},"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":28.99225598065903,"none":42.10136313553267},"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":"2026-07-28T14:25:36Z","match_totals_all":{"draws":292,"losses":367,"wins":295},"match_totals_tracks":{"medium":{"draws":179,"losses":208,"wins":101},"none":{"draws":113,"losses":159,"wins":194}},"model_slug":"minimax-minimax-m3","overall":{"max":52.50654226647922,"mean":33.610060716652335,"min":13.060332078805107},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":68,"wins":73},"GB2-02":{"draws":129,"losses":6,"wins":1},"GB2-03":{"draws":24,"losses":14,"wins":28},"GB2-04":{"draws":53,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":99,"wins":59},"GB2-06":{"draws":0,"losses":45,"wins":25},"GB2-07":{"draws":0,"losses":79,"wins":65},"GB2-08":{"draws":65,"losses":51,"wins":42}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":44,"wins":28},"GB2-02":{"draws":64,"losses":5,"wins":1},"GB2-04":{"draws":53,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":57,"wins":7},"GB2-06":{"draws":0,"losses":45,"wins":25},"GB2-07":{"draws":0,"losses":36,"wins":32},"GB2-08":{"draws":58,"losses":16,"wins":6}},"none":{"GB2-01":{"draws":17,"losses":24,"wins":45},"GB2-02":{"draws":65,"losses":1,"wins":0},"GB2-03":{"draws":24,"losses":14,"wins":28},"GB2-05":{"draws":0,"losses":42,"wins":52},"GB2-07":{"draws":0,"losses":43,"wins":33},"GB2-08":{"draws":7,"losses":35,"wins":36}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1410.1280448316725,"GB2-02":1471.3187980696,"GB2-04":1483.5432274535633,"GB2-05":1222.398171056736,"GB2-06":1357.922477621061,"GB2-07":1479.3824409722706,"GB2-08":1453.5690310099608},"none":{"GB2-01":1508.925857944881,"GB2-02":1471.6428922171287,"GB2-03":1531.065473656246,"GB2-05":1478.69665172829,"GB2-07":1411.2345057212497,"GB2-08":1523.287920626812}},"per_game_tracks":{"medium":{"GB2-01":34.762900908096256,"GB2-02":21.85615803027195,"GB2-04":28.45114290197233,"GB2-05":13.060332078805107,"GB2-06":33.08708302254419,"GB2-07":43.65010596083462,"GB2-08":28.078068962088757},"none":{"GB2-01":49.52138972354479,"GB2-02":26.16827823959424,"GB2-03":52.50654226647922,"GB2-05":45.24363611055831,"GB2-07":38.08146314653779,"GB2-08":41.08686932648167}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":28.040388324555956,"none":39.179733108748714},"reasoning_agg":{"medium":{"max":43.65010596083462,"mean":28.040388324555956,"min":13.060332078805107},"none":{"max":52.50654226647922,"mean":39.179733108748714,"min":26.16827823959424}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":52.50654226647922,"reasoning_variance":11.139344784192758},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.65010596083462,"expected_score":22.34055986757549,"reliability_score":59.32876110847058,"uncertainty_avg":40.67123889152942,"uncertainty_penalty":-5.699828456980466},"none":{"ceiling_score":52.50654226647922,"expected_score":40.2364767887993,"reliability_score":87.0318880035712,"uncertainty_avg":12.968111996428805,"uncertainty_penalty":1.0567436800505874}}},{"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":0.43500895999999994},"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":41.85703117939753,"none":30.450951553691937},"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":"2026-07-28T14:20:43Z","match_totals_all":{"draws":285,"losses":321,"wins":246},"match_totals_tracks":{"medium":{"draws":162,"losses":133,"wins":145},"none":{"draws":123,"losses":188,"wins":101}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":63.07441397885344,"mean":33.14992320575818,"min":15.111213415380366},"per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":71,"wins":46},"GB2-02":{"draws":136,"losses":5,"wins":1},"GB2-04":{"draws":44,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":74,"wins":80},"GB2-06":{"draws":12,"losses":79,"wins":53},"GB2-07":{"draws":0,"losses":85,"wins":63},"GB2-08":{"draws":64,"losses":4,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":10,"losses":29,"wins":29},"GB2-02":{"draws":76,"losses":5,"wins":1},"GB2-05":{"draws":0,"losses":33,"wins":43},"GB2-06":{"draws":12,"losses":20,"wins":34},"GB2-07":{"draws":0,"losses":42,"wins":38},"GB2-08":{"draws":64,"losses":4,"wins":0}},"none":{"GB2-01":{"draws":19,"losses":42,"wins":17},"GB2-02":{"draws":60,"losses":0,"wins":0},"GB2-04":{"draws":44,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":41,"wins":37},"GB2-06":{"draws":0,"losses":59,"wins":19},"GB2-07":{"draws":0,"losses":43,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1509.7629143130875,"GB2-02":1488.1394363857828,"GB2-05":1513.214629268748,"GB2-06":1591.8178567048565,"GB2-07":1449.6619981876688,"GB2-08":1456.0112106882116},"none":{"GB2-01":1363.2762547082637,"GB2-02":1493.0380666605308,"GB2-04":1511.7005114932745,"GB2-05":1403.12799966028,"GB2-06":1329.0543202231288,"GB2-07":1226.7047132781258}},"per_game_tracks":{"medium":{"GB2-01":46.49500002129159,"GB2-02":26.99887675313569,"GB2-05":46.26411990631573,"GB2-06":63.07441397885344,"GB2-07":40.463267207634644,"GB2-08":27.846509209154107},"none":{"GB2-01":31.3808467215317,"GB2-02":30.657319160171507,"GB2-04":37.09284718239884,"GB2-05":36.28681393707585,"GB2-06":32.17666890559334,"GB2-07":15.111213415380366}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.952356603135435,"none":27.347489808380924},"reasoning_agg":{"medium":{"max":63.07441397885344,"mean":38.952356603135435,"min":26.99887675313569},"none":{"max":37.09284718239884,"mean":27.347489808380924,"min":15.111213415380366}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":63.07441397885344,"reasoning_variance":11.60486679475451},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.07441397885344,"expected_score":39.71175551836274,"reliability_score":60.74335831486878,"uncertainty_avg":39.25664168513122,"uncertainty_penalty":0.7593989152273082},"none":{"ceiling_score":37.09284718239884,"expected_score":29.06614700996755,"reliability_score":83.2519073583939,"uncertainty_avg":16.74809264160611,"uncertainty_penalty":1.7186572015866268}}},{"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":0.0533539213}},"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":{"all":33.92166139819212,"highest":35.313056593031895,"medium":34.296535795713304,"none":34.110291283156926},"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":"2026-07-28T14:25:47Z","match_totals_all":{"draws":1005,"losses":1104,"wins":681},"match_totals_tracks":{"highest":{"draws":198,"losses":338,"wins":216},"medium":{"draws":252,"losses":261,"wins":147},"none":{"draws":555,"losses":505,"wins":318}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":51.94406520454458,"mean":33.14940811494054,"min":23.805662478393355},"per_game":{"GB2-01":41.16539523514375,"GB2-02":28.4746954093914,"GB2-05":37.38469725761469,"GB2-06":30.077864389528266,"GB2-07":48.94429787067923,"GB2-08":25.83138939583402},"per_game_all":{"GB2-01":44.447540090052236,"GB2-02":27.87974055204877,"GB2-05":36.482674741670934,"GB2-06":27.11491157360427,"GB2-07":41.43406277979076,"GB2-08":26.17103865198575},"per_game_match_totals_all":{"GB2-01":{"draws":94,"losses":122,"wins":96},"GB2-02":{"draws":323,"losses":24,"wins":9},"GB2-03":{"draws":71,"losses":51,"wins":44},"GB2-04":{"draws":209,"losses":30,"wins":11},"GB2-05":{"draws":0,"losses":307,"wins":203},"GB2-06":{"draws":2,"losses":242,"wins":108},"GB2-07":{"draws":0,"losses":265,"wins":193},"GB2-08":{"draws":306,"losses":63,"wins":17}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":34,"losses":56,"wins":42},"GB2-02":{"draws":114,"losses":15,"wins":7},"GB2-05":{"draws":0,"losses":91,"wins":59},"GB2-06":{"draws":0,"losses":93,"wins":39},"GB2-07":{"draws":0,"losses":67,"wins":65},"GB2-08":{"draws":50,"losses":16,"wins":4}},"medium":{"GB2-01":{"draws":34,"losses":43,"wins":25},"GB2-02":{"draws":77,"losses":6,"wins":1},"GB2-03":{"draws":9,"losses":10,"wins":13},"GB2-04":{"draws":41,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":61,"wins":43},"GB2-06":{"draws":2,"losses":60,"wins":32},"GB2-07":{"draws":0,"losses":66,"wins":30},"GB2-08":{"draws":89,"losses":10,"wins":1}},"none":{"GB2-01":{"draws":26,"losses":23,"wins":29},"GB2-02":{"draws":132,"losses":3,"wins":1},"GB2-03":{"draws":62,"losses":41,"wins":31},"GB2-04":{"draws":168,"losses":25,"wins":9},"GB2-05":{"draws":0,"losses":155,"wins":101},"GB2-06":{"draws":0,"losses":89,"wins":37},"GB2-07":{"draws":0,"losses":132,"wins":98},"GB2-08":{"draws":167,"losses":37,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1474.5199837458713,"GB2-02":1482.4936216544063,"GB2-05":1407.866411417105,"GB2-06":1297.1897046407264,"GB2-07":1443.4677432089854,"GB2-08":1426.7504269994097},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1446.8594985293971,"GB2-02":1480.7162000941285,"GB2-05":1413.7832402083582,"GB2-06":1316.7764234007768,"GB2-07":1503.0155954453644,"GB2-08":1421.8047486009973},"medium":{"GB2-01":1486.8447898822928,"GB2-02":1473.7493325814048,"GB2-03":1548.4644867532702,"GB2-04":1466.5672296334092,"GB2-05":1379.9849056578005,"GB2-06":1311.5137093523335,"GB2-07":1422.426665270465,"GB2-08":1434.802362439193},"none":{"GB2-01":1489.855662825924,"GB2-02":1493.0153322876856,"GB2-03":1464.3296723367484,"GB2-04":1454.4952574304243,"GB2-05":1429.8310883851561,"GB2-06":1263.2789811690684,"GB2-07":1404.9609689111264,"GB2-08":1423.6441699580384}},"per_game_tracks":{"highest":{"GB2-01":41.16539523514375,"GB2-02":28.4746954093914,"GB2-05":37.38469725761469,"GB2-06":30.077864389528266,"GB2-07":48.94429787067923,"GB2-08":25.83138939583402},"medium":{"GB2-01":45.257089734696436,"GB2-02":23.805662478393355,"GB2-03":51.94406520454458,"GB2-04":28.02704826832348,"GB2-05":32.56099423436489,"GB2-06":28.25537172683884,"GB2-07":38.03647200226756,"GB2-08":26.485582716277317},"none":{"GB2-01":46.92013530031653,"GB2-02":31.35886376836155,"GB2-03":41.32805770068991,"GB2-04":27.24387984813706,"GB2-05":39.502332733033235,"GB2-06":23.011498604445705,"GB2-07":37.32141846642549,"GB2-08":26.196143843845913}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.43324140061422,"medium":34.296535795713304,"none":30.718447148494114},"reasoning_agg":{"highest":{"max":48.94429787067923,"mean":34.43324140061422,"min":28.4746954093914},"medium":{"max":51.94406520454458,"mean":34.296535795713304,"min":23.805662478393355},"none":{"max":39.502332733033235,"mean":30.718447148494114,"min":26.196143843845913}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":51.94406520454458,"expected_score":22.6686265028163,"reasoning_variance":3.7147942521201074,"reliability_score":80.60258705179895,"uncertainty_avg":19.39741294820105,"uncertainty_penalty":-10.480781612124243},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.94429787067923,"expected_score":17.547814417792196,"reliability_score":83.70060525257813,"uncertainty_avg":16.29939474742188,"uncertainty_penalty":-16.885426982822025},"medium":{"ceiling_score":51.94406520454458,"expected_score":25.495598770659964,"reliability_score":70.44445567459421,"uncertainty_avg":29.55554432540579,"uncertainty_penalty":-8.80093702505334},"none":{"ceiling_score":39.502332733033235,"expected_score":29.007788624134584,"reliability_score":84.88061359688419,"uncertainty_avg":15.119386403115811,"uncertainty_penalty":-1.7106585243595305}}},{"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":0.93629233},"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":39.55661696001462,"highest":31.59803602969813,"medium":40.55522187712887,"none":36.715568356172824},"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":"2026-07-28T14:20:37Z","match_totals_all":{"draws":254,"losses":410,"wins":266},"match_totals_tracks":{"highest":{"draws":59,"losses":191,"wins":98},"medium":{"draws":97,"losses":79,"wins":68},"none":{"draws":98,"losses":140,"wins":100}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":56.18036928549278,"mean":32.5693132206743,"min":18.70925498097444},"per_game":{"GB2-01":18.70925498097444,"GB2-05":42.12906034826278,"GB2-06":42.14277591917618,"GB2-07":29.331223112083922,"GB2-08":25.67786578799331},"per_game_all":{"GB2-05":42.655369827166254,"GB2-06":36.457864092863},"per_game_match_totals_all":{"GB2-01":{"draws":22,"losses":77,"wins":33},"GB2-02":{"draws":53,"losses":6,"wins":1},"GB2-03":{"draws":24,"losses":10,"wins":12},"GB2-04":{"draws":61,"losses":7,"wins":16},"GB2-05":{"draws":0,"losses":93,"wins":91},"GB2-06":{"draws":2,"losses":110,"wins":64},"GB2-07":{"draws":0,"losses":84,"wins":46},"GB2-08":{"draws":92,"losses":23,"wins":3}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":49,"wins":13},"GB2-05":{"draws":0,"losses":37,"wins":33},"GB2-06":{"draws":1,"losses":39,"wins":28},"GB2-07":{"draws":0,"losses":51,"wins":21},"GB2-08":{"draws":54,"losses":15,"wins":3}},"medium":{"GB2-02":{"draws":53,"losses":6,"wins":1},"GB2-04":{"draws":43,"losses":4,"wins":5},"GB2-05":{"draws":0,"losses":26,"wins":40},"GB2-06":{"draws":1,"losses":43,"wins":22}},"none":{"GB2-01":{"draws":18,"losses":28,"wins":20},"GB2-03":{"draws":24,"losses":10,"wins":12},"GB2-04":{"draws":18,"losses":3,"wins":11},"GB2-05":{"draws":0,"losses":30,"wins":18},"GB2-06":{"draws":0,"losses":28,"wins":14},"GB2-07":{"draws":0,"losses":33,"wins":25},"GB2-08":{"draws":38,"losses":8,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1472.5578768576872,"GB2-06":1376.3828734186616},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1283.8537757397912,"GB2-05":1477.6400999417388,"GB2-06":1428.9589884723573,"GB2-07":1360.7975945248377,"GB2-08":1440.2406789189213},"medium":{"GB2-02":1492.386996118362,"GB2-04":1525.7581685865202,"GB2-05":1583.6391550622056,"GB2-06":1358.4283980930004},"none":{"GB2-01":1469.4983722127108,"GB2-03":1538.934447109512,"GB2-04":1557.208361778728,"GB2-05":1356.3943755691175,"GB2-06":1341.761233690627,"GB2-07":1387.7648759569868,"GB2-08":1404.3431246021992}},"per_game_tracks":{"highest":{"GB2-01":18.70925498097444,"GB2-05":42.12906034826278,"GB2-06":42.14277591917618,"GB2-07":29.331223112083922,"GB2-08":25.67786578799331},"medium":{"GB2-02":30.503883020623825,"GB2-04":40.05657979162075,"GB2-05":56.18036928549278,"GB2-06":35.48005541077814},"none":{"GB2-01":43.94662091196941,"GB2-03":52.23749037369294,"GB2-04":43.34142642641564,"GB2-05":29.656679847743195,"GB2-06":31.75076094863466,"GB2-07":34.40315650889252,"GB2-08":21.672843475861427}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.09506843464011,"medium":34.102740696296685,"none":35.510130531086126},"reasoning_agg":{"highest":{"max":42.14277591917618,"mean":28.09506843464011,"min":18.70925498097444},"medium":{"max":56.18036928549278,"mean":34.102740696296685,"min":30.503883020623825},"none":{"max":52.23749037369294,"mean":35.510130531086126,"min":21.672843475861427}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":56.18036928549278,"expected_score":31.83198603964223,"reasoning_variance":7.415062096446018,"reliability_score":70.52847632724023,"uncertainty_avg":29.471523672759773,"uncertainty_penalty":-0.7373271810320716},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.14277591917618,"expected_score":17.485642830275978,"reliability_score":59.30989686449659,"uncertainty_avg":40.69010313550341,"uncertainty_penalty":-10.60942560436413},"medium":{"ceiling_score":56.18036928549278,"expected_score":38.09399699902207,"reliability_score":80.03295842572557,"uncertainty_avg":19.967041574274432,"uncertainty_penalty":3.9912563027253825},"none":{"ceiling_score":52.23749037369294,"expected_score":42.7799979303312,"reliability_score":71.35559232297403,"uncertainty_avg":28.64440767702597,"uncertainty_penalty":7.269867399245072}}},{"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":0.029176982999999997},"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":32.539305529554206,"none":39.17674151072263},"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":"2026-07-28T14:25:46Z","match_totals_all":{"draws":349,"losses":366,"wins":283},"match_totals_tracks":{"highest":{"draws":137,"losses":228,"wins":159},"none":{"draws":212,"losses":138,"wins":124}},"model_slug":"tencent-hy3-preview","overall":{"max":73.42412117365035,"mean":32.048226730692306,"min":17.447784710329557},"per_game":{"GB2-01":53.47093522593797,"GB2-02":19.794775156970307,"GB2-04":17.447784710329557,"GB2-05":51.191659911057755,"GB2-06":28.169939302617017,"GB2-07":31.1685943001055,"GB2-08":26.531450099861324},"per_game_match_totals_all":{"GB2-01":{"draws":24,"losses":50,"wins":86},"GB2-02":{"draws":136,"losses":13,"wins":1},"GB2-03":{"draws":26,"losses":26,"wins":28},"GB2-04":{"draws":73,"losses":16,"wins":11},"GB2-05":{"draws":0,"losses":105,"wins":81},"GB2-06":{"draws":0,"losses":58,"wins":20},"GB2-07":{"draws":0,"losses":48,"wins":30},"GB2-08":{"draws":90,"losses":50,"wins":26}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":35,"wins":34},"GB2-02":{"draws":70,"losses":7,"wins":1},"GB2-04":{"draws":36,"losses":9,"wins":1},"GB2-05":{"draws":0,"losses":36,"wins":48},"GB2-06":{"draws":0,"losses":58,"wins":20},"GB2-07":{"draws":0,"losses":48,"wins":30},"GB2-08":{"draws":22,"losses":35,"wins":25}},"none":{"GB2-01":{"draws":15,"losses":15,"wins":52},"GB2-02":{"draws":66,"losses":6,"wins":0},"GB2-03":{"draws":26,"losses":26,"wins":28},"GB2-04":{"draws":37,"losses":7,"wins":10},"GB2-05":{"draws":0,"losses":69,"wins":33},"GB2-08":{"draws":68,"losses":15,"wins":1}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1561.833839794575,"GB2-02":1459.3510476208396,"GB2-04":1438.4580799537948,"GB2-05":1552.7612575718463,"GB2-06":1316.3699288823393,"GB2-07":1372.7222973514647,"GB2-08":1441.4812984371338},"none":{"GB2-01":1704.653117005999,"GB2-02":1466.230042358881,"GB2-03":1427.499195255498,"GB2-04":1521.3603548320514,"GB2-05":1351.9190552018522,"GB2-08":1444.6787048624783}},"per_game_tracks":{"highest":{"GB2-01":53.47093522593797,"GB2-02":19.794775156970307,"GB2-04":17.447784710329557,"GB2-05":51.191659911057755,"GB2-06":28.169939302617017,"GB2-07":31.1685943001055,"GB2-08":26.531450099861324},"none":{"GB2-01":73.42412117365035,"GB2-02":25.376074775744662,"GB2-03":35.93070058290421,"GB2-04":39.39237860730228,"GB2-05":31.14935515682644,"GB2-08":29.78781876790787}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.638387447719214,"none":36.45806601366541},"reasoning_agg":{"highest":{"max":53.47093522593797,"mean":27.638387447719214,"min":17.447784710329557},"none":{"max":73.42412117365035,"mean":36.45806601366541,"min":25.376074775744662}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":73.42412117365035,"reasoning_variance":8.819678565946194},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.47093522593797,"expected_score":17.32846823722829,"reliability_score":61.3271122150757,"uncertainty_avg":38.6728877849243,"uncertainty_penalty":-10.309919210490925},"none":{"ceiling_score":73.42412117365035,"expected_score":36.75034588475566,"reliability_score":87.10377937372185,"uncertainty_avg":12.896220626278156,"uncertainty_penalty":0.2922798710902512}}},{"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":37.82492386468688,"none":32.08005332266838},"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":"2026-07-28T14:25:30Z","match_totals_all":{"draws":176,"losses":309,"wins":214},"match_totals_tracks":{"medium":{"draws":50,"losses":124,"wins":100},"none":{"draws":126,"losses":185,"wins":114}},"model_slug":"google-gemma-4-31b-it","overall":{"max":47.81624849186353,"mean":31.876924686584275,"min":22.606477627919652},"per_game_match_totals_all":{"GB2-01":{"draws":22,"losses":30,"wins":34},"GB2-04":{"draws":93,"losses":13,"wins":10},"GB2-05":{"draws":0,"losses":85,"wins":67},"GB2-06":{"draws":2,"losses":92,"wins":42},"GB2-07":{"draws":0,"losses":71,"wins":59},"GB2-08":{"draws":59,"losses":18,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":48,"losses":8,"wins":6},"GB2-05":{"draws":0,"losses":40,"wins":42},"GB2-06":{"draws":2,"losses":46,"wins":18},"GB2-07":{"draws":0,"losses":30,"wins":34}},"none":{"GB2-01":{"draws":22,"losses":30,"wins":34},"GB2-04":{"draws":45,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":45,"wins":25},"GB2-06":{"draws":0,"losses":46,"wins":24},"GB2-07":{"draws":0,"losses":41,"wins":25},"GB2-08":{"draws":59,"losses":18,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1496.2068627614665,"GB2-05":1523.894470037984,"GB2-06":1351.3240358086837,"GB2-07":1455.9022354689878},"none":{"GB2-01":1462.3109351147084,"GB2-04":1488.6170542412904,"GB2-05":1284.119780904192,"GB2-06":1369.8707689668845,"GB2-07":1341.3548030169743,"GB2-08":1426.0434530743848}},"per_game_tracks":{"medium":{"GB2-04":31.047223463773328,"GB2-05":47.81624849186353,"GB2-06":31.931733945050446,"GB2-07":40.504489558060214},"none":{"GB2-01":43.79879432901968,"GB2-04":32.97619808478928,"GB2-05":22.606477627919652,"GB2-06":37.14262287973516,"GB2-07":29.09921306138233,"GB2-08":26.8570139531642}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.88656776741919,"none":30.867281605749366},"reasoning_agg":{"medium":{"max":47.81624849186353,"mean":32.88656776741919,"min":31.047223463773328},"none":{"max":43.79879432901968,"mean":30.867281605749366,"min":22.606477627919652}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":47.81624849186353,"reasoning_variance":2.0192861616698217},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.81624849186353,"expected_score":37.00860679339861,"reliability_score":57.986457592012634,"uncertainty_avg":42.013542407987366,"uncertainty_penalty":4.122039025979426},"none":{"ceiling_score":43.79879432901968,"expected_score":29.261141773286386,"reliability_score":84.30163326279222,"uncertainty_avg":15.69836673720777,"uncertainty_penalty":-1.6061398324629792}}},{"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":0.81977125},"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":3.3391555000000004},"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":26.97228653764561,"none":38.00697191116369},"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":"2026-07-28T14:25:28Z","match_totals_all":{"draws":257,"losses":343,"wins":208},"match_totals_tracks":{"medium":{"draws":49,"losses":194,"wins":81},"none":{"draws":208,"losses":149,"wins":127}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":70.63639989478703,"mean":30.99455140347315,"min":1.2519836889249745},"per_game_match_totals_all":{"GB2-02":{"draws":58,"losses":7,"wins":3},"GB2-03":{"draws":67,"losses":27,"wins":14},"GB2-04":{"draws":55,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":97,"wins":63},"GB2-06":{"draws":9,"losses":95,"wins":42},"GB2-07":{"draws":0,"losses":61,"wins":79},"GB2-08":{"draws":68,"losses":53,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":30,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":50,"wins":20},"GB2-06":{"draws":7,"losses":48,"wins":21},"GB2-07":{"draws":0,"losses":38,"wins":28},"GB2-08":{"draws":12,"losses":46,"wins":4}},"none":{"GB2-02":{"draws":58,"losses":7,"wins":3},"GB2-03":{"draws":37,"losses":15,"wins":6},"GB2-04":{"draws":55,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":47,"wins":43},"GB2-06":{"draws":2,"losses":47,"wins":21},"GB2-07":{"draws":0,"losses":23,"wins":51},"GB2-08":{"draws":56,"losses":7,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1486.2067515622603,"GB2-05":1331.1146096739456,"GB2-06":1325.487759928496,"GB2-07":1438.9548082720535,"GB2-08":1278.8749103188593},"none":{"GB2-02":1476.372168299665,"GB2-03":1418.3320938153308,"GB2-04":1490.7581639196449,"GB2-05":1460.6854546643076,"GB2-06":1316.479215503516,"GB2-07":1677.0084877720944,"GB2-08":1435.7725076009103}},"per_game_tracks":{"medium":{"GB2-03":40.05397049544543,"GB2-05":25.717532257998414,"GB2-06":29.248235707363513,"GB2-07":38.58971053849571,"GB2-08":1.2519836889249745},"none":{"GB2-02":27.45094847961234,"GB2-03":33.122183466475484,"GB2-04":33.928994340568096,"GB2-05":43.1147735572218,"GB2-06":30.228698605833657,"GB2-07":70.63639989478703,"GB2-08":27.5668050336474}},"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":23.98213089578261,"none":38.00697191116369},"reasoning_agg":{"medium":{"max":40.05397049544543,"mean":23.98213089578261,"min":1.2519836889249745},"none":{"max":70.63639989478703,"mean":38.00697191116369,"min":27.45094847961234}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":70.63639989478703,"reasoning_variance":14.024841015381078},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.05397049544543,"expected_score":17.080854351917072,"reliability_score":56.10680735559698,"uncertainty_avg":43.89319264440302,"uncertainty_penalty":-6.901276543865539},"none":{"ceiling_score":70.63639989478703,"expected_score":36.42127913195235,"reliability_score":83.63406557727144,"uncertainty_avg":16.36593442272856,"uncertainty_penalty":-1.5856927792113353}}},{"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":0.101332462},"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":31.164489994260652,"highest":33.626593201617936,"medium":32.55037490368883,"none":30.746506803377823},"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":"2026-07-28T14:20:22Z","match_totals_all":{"draws":492,"losses":393,"wins":253},"match_totals_tracks":{"highest":{"draws":154,"losses":113,"wins":83},"medium":{"draws":200,"losses":137,"wins":85},"none":{"draws":138,"losses":143,"wins":85}},"model_slug":"openai-gpt-oss-120b","overall":{"max":62.216936490328735,"mean":30.70897793275328,"min":15.226133451490124},"per_game":{"GB2-02":17.599139901237052,"GB2-04":28.158592397937767,"GB2-06":62.216936490328735,"GB2-07":35.52190151111717,"GB2-08":24.636395707468978},"per_game_all":{"GB2-02":24.163654706824683,"GB2-04":24.230298186825944,"GB2-06":49.546597088561064,"GB2-08":26.71740999483092},"per_game_match_totals_all":{"GB2-01":{"draws":31,"losses":48,"wins":29},"GB2-02":{"draws":153,"losses":12,"wins":1},"GB2-03":{"draws":57,"losses":25,"wins":12},"GB2-04":{"draws":96,"losses":32,"wins":16},"GB2-05":{"draws":0,"losses":62,"wins":54},"GB2-06":{"draws":5,"losses":111,"wins":90},"GB2-07":{"draws":0,"losses":71,"wins":39},"GB2-08":{"draws":150,"losses":32,"wins":12}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":55,"losses":7,"wins":0},"GB2-04":{"draws":37,"losses":14,"wins":11},"GB2-06":{"draws":3,"losses":34,"wins":43},"GB2-07":{"draws":0,"losses":43,"wins":23},"GB2-08":{"draws":59,"losses":15,"wins":6}},"medium":{"GB2-01":{"draws":20,"losses":24,"wins":16},"GB2-02":{"draws":55,"losses":4,"wins":1},"GB2-03":{"draws":28,"losses":13,"wins":7},"GB2-04":{"draws":42,"losses":6,"wins":4},"GB2-05":{"draws":0,"losses":35,"wins":33},"GB2-06":{"draws":1,"losses":44,"wins":21},"GB2-08":{"draws":54,"losses":11,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":24,"wins":13},"GB2-02":{"draws":43,"losses":1,"wins":0},"GB2-03":{"draws":29,"losses":12,"wins":5},"GB2-04":{"draws":17,"losses":12,"wins":1},"GB2-05":{"draws":0,"losses":27,"wins":21},"GB2-06":{"draws":1,"losses":33,"wins":26},"GB2-07":{"draws":0,"losses":28,"wins":16},"GB2-08":{"draws":37,"losses":6,"wins":3}}},"per_game_raw_elo_all":{"GB2-02":1474.8651175375278,"GB2-04":1455.959178705449,"GB2-06":1473.3671733420779,"GB2-08":1437.1798313744127},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1457.3592084361776,"GB2-04":1481.0409114048707,"GB2-06":1581.4894529905596,"GB2-07":1415.3015552707113,"GB2-08":1430.1174509379948},"medium":{"GB2-01":1397.6747028116988,"GB2-02":1478.4308374646337,"GB2-03":1426.7962430236144,"GB2-04":1470.896254983829,"GB2-05":1423.8445683656728,"GB2-06":1349.1726611844706,"GB2-08":1452.621919774562},"none":{"GB2-01":1363.6774166386915,"GB2-02":1488.805306711772,"GB2-03":1447.733296866472,"GB2-04":1415.9403697276475,"GB2-05":1361.7503235309423,"GB2-06":1489.4394058512037,"GB2-07":1347.04247733592,"GB2-08":1428.8001234106816}},"per_game_tracks":{"highest":{"GB2-02":17.599139901237052,"GB2-04":28.158592397937767,"GB2-06":62.216936490328735,"GB2-07":35.52190151111717,"GB2-08":24.636395707468978},"medium":{"GB2-01":34.84119805839559,"GB2-02":27.214870589482516,"GB2-03":33.69010844396414,"GB2-04":29.306168711049935,"GB2-05":38.26502642302819,"GB2-06":34.28148635006266,"GB2-08":30.253765749838735},"none":{"GB2-01":29.93983071183216,"GB2-02":27.67695362975448,"GB2-03":36.98944800191301,"GB2-04":15.226133451490124,"GB2-05":30.259854038877847,"GB2-06":52.1413684252918,"GB2-07":28.47639764067811,"GB2-08":25.262068527185047}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.898739160096007,"medium":31.48168783478601,"none":30.74650680337782},"reasoning_agg":{"highest":{"max":62.216936490328735,"mean":29.898739160096007,"min":17.599139901237052},"medium":{"max":38.26502642302819,"mean":31.48168783478601,"min":27.214870589482516},"none":{"max":52.1413684252918,"mean":30.74650680337782,"min":15.226133451490124}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":62.216936490328735,"expected_score":19.445794997940638,"reasoning_variance":1.5829486746900017,"reliability_score":69.22004213624933,"uncertainty_avg":30.77995786375066,"uncertainty_penalty":-11.263182934812644},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.216936490328735,"expected_score":21.05501743286755,"reliability_score":58.30628393848927,"uncertainty_avg":41.69371606151073,"uncertainty_penalty":-8.843721727228456},"medium":{"ceiling_score":38.26502642302819,"expected_score":20.104901317522668,"reliability_score":79.5190987714666,"uncertainty_avg":20.480901228533394,"uncertainty_penalty":-11.37678651726334},"none":{"ceiling_score":52.1413684252918,"expected_score":24.193314435974905,"reliability_score":69.79819702064265,"uncertainty_avg":30.20180297935736,"uncertainty_penalty":-6.553192367402914}}},{"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":0.46841705},"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":0.28542560000000006}},"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":0.75384265},"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":{"all":39.24449743574841,"highest":30.119423110989505,"medium":33.72285766535173,"none":36.89762704079522},"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":"2026-07-28T14:25:47Z","match_totals_all":{"draws":543,"losses":459,"wins":291},"match_totals_tracks":{"highest":{"draws":308,"losses":216,"wins":109},"medium":{"draws":128,"losses":124,"wins":86},"none":{"draws":107,"losses":119,"wins":96}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":62.55588820955038,"mean":29.791092763382665,"min":4.361503540371355},"per_game":{"GB2-01":31.310590016208856,"GB2-02":24.190638731861736,"GB2-04":23.674487280423463,"GB2-05":32.261988065707286,"GB2-06":44.805341339377094,"GB2-08":24.4734932323586},"per_game_all":{"GB2-01":43.97043503836676,"GB2-06":47.23439547582833,"GB2-08":26.528661793050134},"per_game_match_totals_all":{"GB2-01":{"draws":46,"losses":79,"wins":59},"GB2-02":{"draws":175,"losses":12,"wins":3},"GB2-03":{"draws":21,"losses":9,"wins":4},"GB2-04":{"draws":81,"losses":16,"wins":9},"GB2-05":{"draws":0,"losses":113,"wins":85},"GB2-06":{"draws":9,"losses":90,"wins":84},"GB2-07":{"draws":0,"losses":87,"wins":29},"GB2-08":{"draws":211,"losses":53,"wins":18}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":31,"wins":13},"GB2-02":{"draws":117,"losses":10,"wins":3},"GB2-04":{"draws":51,"losses":10,"wins":3},"GB2-05":{"draws":0,"losses":96,"wins":48},"GB2-06":{"draws":4,"losses":35,"wins":28},"GB2-08":{"draws":116,"losses":34,"wins":14}},"medium":{"GB2-01":{"draws":14,"losses":29,"wins":29},"GB2-02":{"draws":58,"losses":2,"wins":0},"GB2-06":{"draws":5,"losses":28,"wins":37},"GB2-07":{"draws":0,"losses":51,"wins":17},"GB2-08":{"draws":51,"losses":14,"wins":3}},"none":{"GB2-01":{"draws":12,"losses":19,"wins":17},"GB2-03":{"draws":21,"losses":9,"wins":4},"GB2-04":{"draws":30,"losses":6,"wins":6},"GB2-05":{"draws":0,"losses":17,"wins":37},"GB2-06":{"draws":0,"losses":27,"wins":19},"GB2-07":{"draws":0,"losses":36,"wins":12},"GB2-08":{"draws":44,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1478.8173058098876,"GB2-06":1458.3922951091815,"GB2-08":1434.7958732080251},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1387.7193090882554,"GB2-02":1484.5632352771195,"GB2-04":1456.9394455146103,"GB2-05":1388.8626371861264,"GB2-06":1449.938830974374,"GB2-08":1428.0487451221084},"medium":{"GB2-01":1500.6871955211363,"GB2-02":1477.573967254025,"GB2-06":1566.120201385086,"GB2-07":1139.144947953933,"GB2-08":1428.1113342083331},"none":{"GB2-01":1548.045412820271,"GB2-03":1422.2873610539257,"GB2-04":1500.908758448871,"GB2-05":1547.5175821569976,"GB2-06":1359.117852968085,"GB2-07":1325.8842408601347,"GB2-08":1448.227540293634}},"per_game_tracks":{"highest":{"GB2-01":31.310590016208856,"GB2-02":24.190638731861736,"GB2-04":23.674487280423463,"GB2-05":32.261988065707286,"GB2-06":44.805341339377094,"GB2-08":24.4734932323586},"medium":{"GB2-01":48.02728592138475,"GB2-02":27.012934165249288,"GB2-06":62.55588820955038,"GB2-07":4.361503540371355,"GB2-08":26.65667649020289},"none":{"GB2-01":52.573429177506654,"GB2-03":31.1858555184372,"GB2-04":34.00069750646294,"GB2-05":51.541673218867665,"GB2-06":34.3419568785575,"GB2-07":26.183961329145713,"GB2-08":28.45581565658891}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.36135859187534,"medium":29.114292657477428,"none":36.89762704079523},"reasoning_agg":{"highest":{"max":32.261988065707286,"mean":23.36135859187534,"min":24.190638731861736},"medium":{"max":62.55588820955038,"mean":29.114292657477428,"min":4.361503540371355},"none":{"max":52.573429177506654,"mean":36.89762704079523,"min":26.183961329145713}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":62.55588820955038,"expected_score":29.202988295695665,"reasoning_variance":13.536268448919888,"reliability_score":72.18134612730175,"uncertainty_avg":27.818653872698246,"uncertainty_penalty":-0.5881044676869998},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":32.261988065707286,"expected_score":14.970416802265019,"reliability_score":58.80495789086651,"uncertainty_avg":41.19504210913349,"uncertainty_penalty":-8.390941789610322},"medium":{"ceiling_score":62.55588820955038,"expected_score":25.587717477073898,"reliability_score":83.29721008800497,"uncertainty_avg":16.70278991199503,"uncertainty_penalty":-3.5265751804035297},"none":{"ceiling_score":52.573429177506654,"expected_score":38.02880600039889,"reliability_score":70.32309432957588,"uncertainty_avg":29.676905670424123,"uncertainty_penalty":1.131178959603659}}},{"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":{"medium":28.309342689144433,"none":28.958560220633643},"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":{"balanced":{"admitted_plugins":7,"evaluated_cells":15,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-08"],"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":1,"model_code_failure_rate":0.5333333333333333,"model_code_failures":8,"repaired_admitted":7,"repaired_rate":0.4666666666666667},"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":"2026-07-28T14:08:27Z","match_totals_all":{"draws":410,"losses":364,"wins":160},"match_totals_tracks":{"medium":{"draws":84,"losses":130,"wins":68},"none":{"draws":326,"losses":234,"wins":92}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":44.122391209452545,"mean":28.24400511430469,"min":18.45019817755536},"per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":77,"wins":42},"GB2-02":{"draws":97,"losses":7,"wins":2},"GB2-03":{"draws":38,"losses":46,"wins":18},"GB2-04":{"draws":95,"losses":10,"wins":3},"GB2-06":{"draws":4,"losses":156,"wins":56},"GB2-07":{"draws":0,"losses":45,"wins":35},"GB2-08":{"draws":123,"losses":23,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":14,"losses":22,"wins":4},"GB2-02":{"draws":33,"losses":5,"wins":2},"GB2-04":{"draws":36,"losses":5,"wins":1},"GB2-06":{"draws":1,"losses":53,"wins":26},"GB2-07":{"draws":0,"losses":45,"wins":35}},"none":{"GB2-01":{"draws":39,"losses":55,"wins":38},"GB2-02":{"draws":64,"losses":2,"wins":0},"GB2-03":{"draws":38,"losses":46,"wins":18},"GB2-04":{"draws":59,"losses":5,"wins":2},"GB2-06":{"draws":3,"losses":103,"wins":30},"GB2-08":{"draws":123,"losses":23,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1299.6094862262853,"GB2-02":1466.4538903440136,"GB2-04":1449.9950408721,"GB2-06":1336.3309167535742,"GB2-07":1472.2955250473424},"none":{"GB2-01":1470.946495713124,"GB2-02":1471.8518908493445,"GB2-03":1387.6113039946258,"GB2-04":1476.8265619678257,"GB2-06":1226.2200915200956,"GB2-08":1420.60997040424}},"per_game_tracks":{"medium":{"GB2-01":21.42073278137745,"GB2-02":21.73991493205433,"GB2-04":24.023951205664567,"GB2-06":30.857196415755688,"GB2-07":43.504918110870136},"none":{"GB2-01":44.122391209452545,"GB2-02":26.217532415940592,"GB2-03":27.417123475037705,"GB2-04":31.65894027136433,"GB2-06":18.45019817755536,"GB2-08":25.885175774451337}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.730769153254926,"none":25.75724107535446},"reasoning_agg":{"medium":{"max":43.504918110870136,"mean":30.730769153254926,"min":30.857196415755688},"none":{"max":44.122391209452545,"mean":25.75724107535446,"min":18.45019817755536}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":44.122391209452545,"reasoning_variance":4.973528077900465},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.504918110870136,"expected_score":15.226568355461183,"reliability_score":66.0306382112971,"uncertainty_avg":33.9693617887029,"uncertainty_penalty":-15.504200797793743},"none":{"ceiling_score":44.122391209452545,"expected_score":17.716769510836162,"reliability_score":82.046479795162,"uncertainty_avg":17.953520204838004,"uncertainty_penalty":-8.040471564518299}}},{"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":32.98876209267146,"none":28.543823196610145},"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":"2026-07-28T14:25:14Z","match_totals_all":{"draws":244,"losses":340,"wins":184},"match_totals_tracks":{"medium":{"draws":122,"losses":154,"wins":110},"none":{"draws":122,"losses":186,"wins":74}},"model_slug":"cohere-north-mini-code","overall":{"max":44.1778108469207,"mean":25.830446612943778,"min":20.961390926684352},"per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":73,"wins":20},"GB2-03":{"draws":23,"losses":20,"wins":9},"GB2-04":{"draws":41,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":31,"wins":41},"GB2-06":{"draws":1,"losses":45,"wins":18},"GB2-07":{"draws":0,"losses":142,"wins":88},"GB2-08":{"draws":112,"losses":22,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":23,"losses":20,"wins":9},"GB2-04":{"draws":41,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":31,"wins":41},"GB2-06":{"draws":1,"losses":45,"wins":18},"GB2-07":{"draws":0,"losses":38,"wins":38},"GB2-08":{"draws":57,"losses":13,"wins":0}},"none":{"GB2-01":{"draws":67,"losses":73,"wins":20},"GB2-07":{"draws":0,"losses":104,"wins":50},"GB2-08":{"draws":55,"losses":9,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1433.178888842719,"GB2-04":1485.2434845651546,"GB2-05":1477.1269576314262,"GB2-06":1345.4128443341024,"GB2-07":1481.0174393089364,"GB2-08":1410.9061980157899},"none":{"GB2-01":1329.371017113623,"GB2-07":1335.3254588676755,"GB2-08":1447.898423960942}},"per_game_tracks":{"medium":{"GB2-03":31.332971348560825,"GB2-04":27.76839770448181,"GB2-05":42.20844056832008,"GB2-06":31.05565578153827,"GB2-07":44.1778108469207,"GB2-08":21.38929630620705},"none":{"GB2-01":27.275894143562212,"GB2-07":28.795013700601388,"GB2-08":29.56056174566684}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.699502299203203,"none":20.961390926684352},"reasoning_agg":{"medium":{"max":44.1778108469207,"mean":30.699502299203203,"min":21.38929630620705},"none":{"max":28.795013700601388,"mean":20.961390926684352,"min":27.275894143562212}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":44.1778108469207,"reasoning_variance":9.738111372518851},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":44.1778108469207,"expected_score":27.889916919434242,"reliability_score":55.46785237926375,"uncertainty_avg":44.53214762073625,"uncertainty_penalty":-2.8095853797689614},"none":{"ceiling_score":28.795013700601388,"expected_score":16.355646631282,"reliability_score":86.24715179647673,"uncertainty_avg":13.752848203523271,"uncertainty_penalty":-4.605744295402353}}},{"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":0.21124249999999997},"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":0.07321124999999999}},"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":{"all":23.910639959350856,"highest":27.166812791071994,"medium":29.071582104314245,"none":23.265972003097453},"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":"2026-07-28T14:20:19Z","match_totals_all":{"draws":278,"losses":483,"wins":220},"match_totals_tracks":{"highest":{"draws":112,"losses":180,"wins":65},"medium":{"draws":104,"losses":182,"wins":102},"none":{"draws":62,"losses":121,"wins":53}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":41.55535155576687,"mean":24.825073160843534,"min":0.0},"per_game":{"GB2-04":26.56620142152815,"GB2-05":16.920258098098685,"GB2-06":30.965174199812797,"GB2-07":37.24190458473867,"GB2-08":24.140525651181648},"per_game_all":{"GB2-05":20.276027963902575,"GB2-06":37.36560711100213,"GB2-07":14.090284803147858},"per_game_match_totals_all":{"GB2-01":{"draws":58,"losses":33,"wins":21},"GB2-02":{"draws":38,"losses":3,"wins":1},"GB2-04":{"draws":84,"losses":8,"wins":8},"GB2-05":{"draws":0,"losses":135,"wins":53},"GB2-06":{"draws":1,"losses":114,"wins":70},"GB2-07":{"draws":0,"losses":151,"wins":39},"GB2-08":{"draws":97,"losses":39,"wins":28}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":41,"losses":6,"wins":3},"GB2-05":{"draws":0,"losses":56,"wins":10},"GB2-06":{"draws":0,"losses":52,"wins":23},"GB2-07":{"draws":0,"losses":55,"wins":25},"GB2-08":{"draws":71,"losses":11,"wins":4}},"medium":{"GB2-01":{"draws":35,"losses":16,"wins":13},"GB2-04":{"draws":43,"losses":2,"wins":5},"GB2-05":{"draws":0,"losses":43,"wins":27},"GB2-06":{"draws":0,"losses":41,"wins":23},"GB2-07":{"draws":0,"losses":52,"wins":10},"GB2-08":{"draws":26,"losses":28,"wins":24}},"none":{"GB2-01":{"draws":23,"losses":17,"wins":8},"GB2-02":{"draws":38,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":36,"wins":16},"GB2-06":{"draws":1,"losses":21,"wins":24},"GB2-07":{"draws":0,"losses":44,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1273.3351318224352,"GB2-06":1381.5980606081976,"GB2-07":1226.922409321695},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1481.5339608157208,"GB2-05":1255.881907203846,"GB2-06":1339.1651662641182,"GB2-07":1421.3371516246898,"GB2-08":1423.1258813874501},"medium":{"GB2-01":1450.7657677567693,"GB2-04":1495.4259070579112,"GB2-05":1292.0994540643576,"GB2-06":1393.3523465645424,"GB2-07":1146.8224295367877,"GB2-08":1451.3559728598718},"none":{"GB2-01":1331.1073977123126,"GB2-02":1494.771862796145,"GB2-05":1272.024034199102,"GB2-06":1412.2766689959317,"GB2-07":1112.6076468036076}},"per_game_tracks":{"highest":{"GB2-04":26.56620142152815,"GB2-05":16.920258098098685,"GB2-06":30.965174199812797,"GB2-07":37.24190458473867,"GB2-08":24.140525651181648},"medium":{"GB2-01":41.55535155576687,"GB2-04":33.9037734449991,"GB2-05":23.50512954504209,"GB2-06":39.905904249814974,"GB2-07":5.028949824704899,"GB2-08":30.530384005557536},"none":{"GB2-01":25.94143215206774,"GB2-02":28.759988731473964,"GB2-05":20.402696248566944,"GB2-06":41.225742883378615,"GB2-07":0.0}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.155091911372683,"medium":27.054155568060477,"none":23.265972003097453},"reasoning_agg":{"highest":{"max":37.24190458473867,"mean":24.155091911372683,"min":16.920258098098685},"medium":{"max":41.55535155576687,"mean":27.054155568060477,"min":5.028949824704899},"none":{"max":41.225742883378615,"mean":23.265972003097453,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":41.55535155576687,"expected_score":13.85359744938637,"reasoning_variance":3.788183564963024,"reliability_score":72.27312045955145,"uncertainty_avg":27.726879540448554,"uncertainty_penalty":-10.971475711457163},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.24190458473867,"expected_score":10.893346368705544,"reliability_score":59.60034441063097,"uncertainty_avg":40.39965558936903,"uncertainty_penalty":-13.26174554266714},"medium":{"ceiling_score":41.55535155576687,"expected_score":22.674213372053583,"reliability_score":81.643950736421,"uncertainty_avg":18.356049263579003,"uncertainty_penalty":-4.379942196006894},"none":{"ceiling_score":41.225742883378615,"expected_score":16.993827579985613,"reliability_score":71.6061588506526,"uncertainty_avg":28.393841149347395,"uncertainty_penalty":-6.27214442311184}}},{"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":1.7932035},"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":2.137161},"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":21.966074117634754,"none":32.20482114814492},"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":"2026-07-28T14:25:46Z","match_totals_all":{"draws":93,"losses":363,"wins":153},"match_totals_tracks":{"highest":{"draws":21,"losses":209,"wins":64},"none":{"draws":72,"losses":154,"wins":89}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":38.05680239306483,"mean":22.508071535407936,"min":15.60659671700303},"per_game":{"GB2-01":25.175567645434295,"GB2-05":18.865594222722617,"GB2-06":28.216537885379076,"GB2-07":15.60659671700303},"per_game_match_totals_all":{"GB2-01":{"draws":27,"losses":85,"wins":35},"GB2-05":{"draws":0,"losses":111,"wins":57},"GB2-06":{"draws":5,"losses":86,"wins":49},"GB2-07":{"draws":0,"losses":63,"wins":11},"GB2-08":{"draws":61,"losses":18,"wins":1}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":39,"wins":14},"GB2-05":{"draws":0,"losses":58,"wins":16},"GB2-06":{"draws":0,"losses":49,"wins":23},"GB2-07":{"draws":0,"losses":63,"wins":11}},"none":{"GB2-01":{"draws":6,"losses":46,"wins":21},"GB2-05":{"draws":0,"losses":53,"wins":41},"GB2-06":{"draws":5,"losses":37,"wins":26},"GB2-08":{"draws":61,"losses":18,"wins":1}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1332.6314157550598,"GB2-05":1268.746196576296,"GB2-06":1319.3011959811236,"GB2-07":1247.9006699810348},"none":{"GB2-01":1392.3613831959185,"GB2-05":1414.8804142848849,"GB2-06":1319.423486454839,"GB2-08":1416.3368045051216}},"per_game_tracks":{"highest":{"GB2-01":25.175567645434295,"GB2-05":18.865594222722617,"GB2-06":28.216537885379076,"GB2-07":15.60659671700303},"none":{"GB2-01":34.7678319511097,"GB2-05":38.05680239306483,"GB2-06":30.52151155484641,"GB2-08":25.473138693558756}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.935224413453792,"none":27.08091865736208},"reasoning_agg":{"highest":{"max":28.216537885379076,"mean":17.935224413453792,"min":15.60659671700303},"none":{"max":38.05680239306483,"mean":27.08091865736208,"min":25.473138693558756}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":38.05680239306483,"reasoning_variance":9.145694243908288},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":28.216537885379076,"expected_score":2.5130855339159184,"reliability_score":62.07258759763501,"uncertainty_avg":37.92741240236499,"uncertainty_penalty":-15.422138879537874},"none":{"ceiling_score":38.05680239306483,"expected_score":21.79860542290878,"reliability_score":87.45719523134812,"uncertainty_avg":12.542804768651877,"uncertainty_penalty":-5.2823132344533015}}}],"public_release_id":"gb2-20260728-67bc5cf10e2e","results_cut_id":"gb2-20260728-67bc5cf10e2e","snapshot_id":"20260728_143429","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-07-28 14:34 UTC","versus_totals_all":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":5,"wins":5},"claude-opus-4-5":{"draws":3,"losses":2,"wins":27},"claude-opus-4-8":{"draws":2,"losses":13,"wins":15},"claude-opus-5":{"draws":20,"losses":32,"wins":34},"claude-sonnet-5":{"draws":6,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":13},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":18},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":1,"wins":21},"gpt-5.4":{"draws":6,"losses":14,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":29},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":47},"gpt-5.5":{"draws":7,"losses":13,"wins":12},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":25},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":12,"losses":7,"wins":49},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":1,"wins":15},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":23,"wins":50},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"z-ai/glm-5.2":{"draws":1,"losses":9,"wins":34}},"claude-opus-4-5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":2,"wins":6},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":3,"losses":15,"wins":2},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":5},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":5,"losses":5,"wins":8},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":22},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":20},"gpt-5.5":{"draws":7,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":4},"o3":{"draws":4,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":8,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":15,"wins":13},"claude-opus-4-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-8":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":10,"losses":22,"wins":12},"claude-sonnet-5":{"draws":13,"losses":13,"wins":22},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":18,"losses":9,"wins":33},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":17},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.5-flash":{"draws":7,"losses":9,"wins":6},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":10},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":8},"gpt-4.1":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":7,"losses":5,"wins":18},"gpt-5.4":{"draws":6,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":21,"wins":39},"gpt-5.4-nano":{"draws":20,"losses":20,"wins":50},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":23,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":10,"wins":16},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":25,"losses":32,"wins":27},"nex-agi/nex-n2-pro":{"draws":10,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":8,"wins":17},"o3":{"draws":5,"losses":10,"wins":21},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":7},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":15},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":11},"thinkingmachines/inkling":{"draws":0,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":20,"losses":42,"wins":32},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":9,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":16},"z-ai/glm-5.2":{"draws":23,"losses":26,"wins":37}},"claude-opus-5":{"claude-fable-5":{"draws":20,"losses":34,"wins":32},"claude-opus-4-5":{"draws":18,"losses":15,"wins":103},"claude-opus-4-8":{"draws":10,"losses":12,"wins":22},"claude-opus-5":{"draws":44,"losses":160,"wins":160},"claude-sonnet-5":{"draws":15,"losses":8,"wins":47},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":16},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":2,"losses":9,"wins":25},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":24},"google/gemini-3.6-flash":{"draws":8,"losses":23,"wins":49},"gpt-4.1":{"draws":6,"losses":0,"wins":18},"gpt-5":{"draws":4,"losses":2,"wins":12},"gpt-5.4":{"draws":12,"losses":26,"wins":34},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":38},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":49},"gpt-5.5":{"draws":8,"losses":20,"wins":34},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":17},"gpt-5.6-sol":{"draws":16,"losses":19,"wins":53},"gpt-5.6-terra":{"draws":16,"losses":8,"wins":26},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":14},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":22,"losses":14,"wins":70},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":22},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":30},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":8},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":30},"x-ai/grok-4.5":{"draws":27,"losses":41,"wins":136},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":1,"wins":13},"z-ai/glm-5.2":{"draws":17,"losses":12,"wins":71}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":16,"wins":0},"claude-opus-4-5":{"draws":24,"losses":14,"wins":22},"claude-opus-4-8":{"draws":13,"losses":22,"wins":13},"claude-opus-5":{"draws":15,"losses":47,"wins":8},"claude-sonnet-5":{"draws":8,"losses":10,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":27,"losses":12,"wins":23},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":7},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":16},"google/gemini-3.5-flash":{"draws":10,"losses":12,"wins":8},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":11},"google/gemini-3.6-flash":{"draws":5,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":6},"gpt-4.1":{"draws":5,"losses":1,"wins":8},"gpt-5":{"draws":20,"losses":17,"wins":13},"gpt-5.4":{"draws":14,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":30,"losses":29,"wins":35},"gpt-5.4-nano":{"draws":34,"losses":23,"wins":37},"gpt-5.5":{"draws":14,"losses":12,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":14,"wins":19},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":25,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":9,"wins":18},"o3":{"draws":3,"losses":13,"wins":12},"openai/gpt-oss-120b":{"draws":5,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":12},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":23,"losses":37,"wins":16},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":37,"losses":13,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":40,"losses":37,"wins":37}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":7,"losses":11,"wins":2},"claude-opus-4-8":{"draws":5,"losses":5,"wins":2},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":3,"losses":13,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":10,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":8,"wins":5},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":5,"losses":12,"wins":1},"gpt-5.4":{"draws":7,"losses":10,"wins":7},"gpt-5.4-mini":{"draws":21,"losses":27,"wins":10},"gpt-5.4-nano":{"draws":22,"losses":35,"wins":27},"gpt-5.5":{"draws":11,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":18,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":8,"wins":9},"o3":{"draws":3,"losses":9,"wins":4},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":14,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":14,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":2,"losses":14,"wins":2},"claude-opus-4-5":{"draws":45,"losses":23,"wins":10},"claude-opus-4-8":{"draws":18,"losses":33,"wins":9},"claude-opus-5":{"draws":3,"losses":6,"wins":1},"claude-sonnet-5":{"draws":27,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":11},"deepseek/deepseek-v4-flash":{"draws":48,"losses":58,"wins":58},"deepseek/deepseek-v4-pro":{"draws":17,"losses":23,"wins":14},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":14,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":16,"wins":4},"google/gemini-3.6-flash":{"draws":13,"losses":6,"wins":5},"google/gemma-4-31b-it":{"draws":15,"losses":19,"wins":16},"gpt-4.1":{"draws":6,"losses":11,"wins":7},"gpt-5":{"draws":9,"losses":21,"wins":2},"gpt-5.4":{"draws":28,"losses":25,"wins":13},"gpt-5.4-mini":{"draws":87,"losses":76,"wins":53},"gpt-5.4-nano":{"draws":89,"losses":47,"wins":70},"gpt-5.5":{"draws":28,"losses":26,"wins":2},"gpt-5.6-luna":{"draws":39,"losses":18,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":45,"wins":13},"gpt-5.6-terra":{"draws":22,"losses":48,"wins":14},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":5,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":28,"wins":12},"mistralai/mistral-medium-3-5":{"draws":13,"losses":22,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":34,"losses":59,"wins":11},"nex-agi/nex-n2-pro":{"draws":19,"losses":24,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":14,"wins":20},"o3":{"draws":11,"losses":31,"wins":12},"openai/gpt-oss-120b":{"draws":32,"losses":21,"wins":15},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":4},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":8},"qwen/qwen3.7-plus":{"draws":19,"losses":16,"wins":15},"stepfun/step-3.7-flash":{"draws":22,"losses":24,"wins":20},"tencent/hy3-preview":{"draws":26,"losses":19,"wins":17},"thinkingmachines/inkling":{"draws":21,"losses":25,"wins":12},"x-ai/grok-4.5":{"draws":27,"losses":63,"wins":14},"x-ai/grok-build-0.1":{"draws":8,"losses":10,"wins":4},"xiaomi/mimo-v2.5":{"draws":38,"losses":42,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":21,"wins":19},"z-ai/glm-5.2":{"draws":59,"losses":60,"wins":49}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":13,"wins":0},"claude-opus-4-5":{"draws":7,"losses":11,"wins":8},"claude-opus-4-8":{"draws":9,"losses":17,"wins":10},"claude-opus-5":{"draws":1,"losses":16,"wins":1},"claude-sonnet-5":{"draws":9,"losses":7,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":23},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":8},"gpt-5":{"draws":0,"losses":5,"wins":11},"gpt-5.4":{"draws":4,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":24,"losses":14,"wins":30},"gpt-5.4-nano":{"draws":24,"losses":19,"wins":29},"gpt-5.5":{"draws":9,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":4,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":9,"wins":7},"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":7,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":16},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":5,"losses":6,"wins":9},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":8},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":42,"wins":15},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":14,"losses":14,"wins":26}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":9,"losses":23,"wins":0},"claude-opus-4-8":{"draws":7,"losses":14,"wins":3},"claude-opus-5":{"draws":0,"losses":11,"wins":1},"claude-sonnet-5":{"draws":12,"losses":16,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":10},"deepseek/deepseek-v4-flash":{"draws":16,"losses":19,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":5,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":5},"gpt-4.1":{"draws":4,"losses":3,"wins":3},"gpt-5":{"draws":8,"losses":10,"wins":2},"gpt-5.4":{"draws":1,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":23,"losses":39,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":40,"wins":27},"gpt-5.5":{"draws":9,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":24,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":10,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":15,"wins":11},"o3":{"draws":6,"losses":10,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":11,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":13,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":10,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":10,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":18,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":24,"wins":6}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":6,"losses":18,"wins":10},"claude-opus-4-5":{"draws":13,"losses":11,"wins":14},"claude-opus-4-8":{"draws":7,"losses":6,"wins":9},"claude-opus-5":{"draws":2,"losses":25,"wins":9},"claude-sonnet-5":{"draws":10,"losses":8,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":19,"losses":5,"wins":14},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":1,"wins":5},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":7,"losses":5,"wins":12},"gpt-5.4":{"draws":7,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":20,"losses":23,"wins":25},"gpt-5.4-nano":{"draws":22,"losses":16,"wins":20},"gpt-5.5":{"draws":10,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":13,"losses":9,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"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":22,"losses":24,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":14},"o3":{"draws":0,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":1},"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":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":8},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":13,"wins":22},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":7,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":16,"wins":23}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":3},"claude-opus-4-8":{"draws":1,"losses":10,"wins":1},"claude-opus-5":{"draws":11,"losses":24,"wins":5},"claude-sonnet-5":{"draws":4,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":120,"losses":112,"wins":112},"google/gemini-3.6-flash":{"draws":145,"losses":120,"wins":69},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":17,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":19,"losses":9,"wins":26},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":55,"losses":18,"wins":59},"meituan/longcat-2.0":{"draws":65,"losses":63,"wins":81},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":66,"losses":80,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":11},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":86,"losses":77,"wins":49},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":71,"losses":82,"wins":81},"x-ai/grok-4.5":{"draws":61,"losses":110,"wins":35},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":13,"losses":14,"wins":7}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":3,"wins":3},"claude-opus-4-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-8":{"draws":4,"losses":0,"wins":2},"claude-opus-5":{"draws":8,"losses":49,"wins":23},"claude-sonnet-5":{"draws":5,"losses":1,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":1},"google/gemini-3.5-flash-lite":{"draws":145,"losses":69,"wins":120},"google/gemini-3.6-flash":{"draws":96,"losses":80,"wins":80},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":1,"losses":4,"wins":1},"gpt-5.4":{"draws":6,"losses":11,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":24,"losses":10,"wins":22},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":75,"losses":14,"wins":41},"meituan/longcat-2.0":{"draws":64,"losses":47,"wins":83},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":57,"losses":53,"wins":42},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":1},"o3":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":66,"losses":26,"wins":66},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":80,"losses":44,"wins":96},"x-ai/grok-4.5":{"draws":39,"losses":67,"wins":80},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":9,"wins":11}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":6,"losses":7,"wins":9},"claude-opus-4-8":{"draws":6,"losses":8,"wins":0},"claude-sonnet-5":{"draws":6,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":15,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":7},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":1,"losses":4,"wins":1},"gpt-5.4":{"draws":5,"losses":8,"wins":1},"gpt-5.4-mini":{"draws":21,"losses":22,"wins":21},"gpt-5.4-nano":{"draws":14,"losses":25,"wins":25},"gpt-5.5":{"draws":4,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":8},"gpt-5.6-sol":{"draws":8,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":15,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":6},"o3":{"draws":4,"losses":9,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":24,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":6,"losses":16,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":9,"losses":7,"wins":6}},"gpt-4.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":6,"losses":2,"wins":2},"claude-opus-4-8":{"draws":1,"losses":7,"wins":2},"claude-opus-5":{"draws":6,"losses":18,"wins":0},"claude-sonnet-5":{"draws":5,"losses":8,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":7},"gpt-5.5":{"draws":3,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":5},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":6},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":17,"wins":11}},"gpt-5":{"claude-fable-5":{"draws":2,"losses":21,"wins":1},"claude-opus-4-5":{"draws":13,"losses":7,"wins":14},"claude-opus-4-8":{"draws":7,"losses":18,"wins":5},"claude-opus-5":{"draws":4,"losses":12,"wins":2},"claude-sonnet-5":{"draws":20,"losses":13,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":21},"deepseek/deepseek-v4-pro":{"draws":0,"losses":11,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":4},"gpt-4.1":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":6,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":28,"losses":21,"wins":13},"gpt-5.4-nano":{"draws":28,"losses":20,"wins":32},"gpt-5.5":{"draws":6,"losses":16,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":7,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":13,"wins":5},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":21,"losses":10,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":6},"o3":{"draws":2,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":1,"losses":6,"wins":9},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":13,"losses":31,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":22,"losses":14,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":6},"z-ai/glm-5.2":{"draws":27,"losses":34,"wins":29}},"gpt-5.4":{"claude-fable-5":{"draws":6,"losses":16,"wins":14},"claude-opus-4-5":{"draws":17,"losses":15,"wins":26},"claude-opus-4-8":{"draws":6,"losses":16,"wins":20},"claude-opus-5":{"draws":12,"losses":34,"wins":26},"claude-sonnet-5":{"draws":14,"losses":6,"wins":20},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":10},"deepseek/deepseek-v4-flash":{"draws":28,"losses":13,"wins":25},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":17},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":12},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":6,"losses":9,"wins":11},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":8},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":17},"gpt-5.4":{"draws":12,"losses":10,"wins":10},"gpt-5.4-mini":{"draws":41,"losses":21,"wins":60},"gpt-5.4-nano":{"draws":40,"losses":18,"wins":57},"gpt-5.5":{"draws":20,"losses":15,"wins":19},"gpt-5.6-luna":{"draws":24,"losses":4,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":29},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":23},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":21,"losses":21,"wins":54},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":9},"o3":{"draws":5,"losses":6,"wins":9},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":13},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":15},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":36,"losses":35,"wins":59},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":5,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":21},"z-ai/glm-5.2":{"draws":46,"losses":17,"wins":33}},"gpt-5.4-mini":{"claude-fable-5":{"draws":9,"losses":29,"wins":6},"claude-opus-4-5":{"draws":47,"losses":48,"wins":21},"claude-opus-4-8":{"draws":28,"losses":39,"wins":21},"claude-opus-5":{"draws":10,"losses":38,"wins":8},"claude-sonnet-5":{"draws":30,"losses":35,"wins":29},"cohere/north-mini-code":{"draws":21,"losses":10,"wins":27},"deepseek/deepseek-v4-flash":{"draws":87,"losses":53,"wins":76},"deepseek/deepseek-v4-pro":{"draws":24,"losses":30,"wins":14},"google/gemini-3.1-flash-lite":{"draws":23,"losses":12,"wins":39},"google/gemini-3.5-flash":{"draws":20,"losses":25,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":12,"wins":11},"google/gemini-3.6-flash":{"draws":14,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":21,"losses":21,"wins":22},"gpt-4.1":{"draws":14,"losses":6,"wins":14},"gpt-5":{"draws":28,"losses":13,"wins":21},"gpt-5.4":{"draws":41,"losses":60,"wins":21},"gpt-5.4-mini":{"draws":108,"losses":76,"wins":76},"gpt-5.4-nano":{"draws":112,"losses":97,"wins":120},"gpt-5.5":{"draws":41,"losses":24,"wins":11},"gpt-5.6-luna":{"draws":54,"losses":33,"wins":33},"gpt-5.6-sol":{"draws":19,"losses":39,"wins":20},"gpt-5.6-terra":{"draws":58,"losses":51,"wins":31},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":14,"wins":17},"minimax/minimax-m3":{"draws":32,"losses":29,"wins":27},"mistralai/mistral-medium-3-5":{"draws":10,"losses":11,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":20,"wins":5},"moonshotai/kimi-k3":{"draws":63,"losses":58,"wins":33},"nex-agi/nex-n2-pro":{"draws":23,"losses":14,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":18,"wins":26},"o3":{"draws":19,"losses":48,"wins":23},"openai/gpt-oss-120b":{"draws":36,"losses":27,"wins":35},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-max":{"draws":28,"losses":27,"wins":21},"qwen/qwen3.7-plus":{"draws":28,"losses":30,"wins":16},"stepfun/step-3.7-flash":{"draws":25,"losses":23,"wins":38},"tencent/hy3-preview":{"draws":23,"losses":15,"wins":24},"thinkingmachines/inkling":{"draws":21,"losses":18,"wins":19},"x-ai/grok-4.5":{"draws":63,"losses":120,"wins":31},"x-ai/grok-build-0.1":{"draws":5,"losses":12,"wins":11},"xiaomi/mimo-v2.5":{"draws":80,"losses":71,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":17,"wins":24},"z-ai/glm-5.2":{"draws":88,"losses":83,"wins":65}},"gpt-5.4-nano":{"claude-fable-5":{"draws":7,"losses":47,"wins":10},"claude-opus-4-5":{"draws":40,"losses":66,"wins":32},"claude-opus-4-8":{"draws":20,"losses":50,"wins":20},"claude-opus-5":{"draws":9,"losses":49,"wins":12},"claude-sonnet-5":{"draws":34,"losses":37,"wins":23},"cohere/north-mini-code":{"draws":22,"losses":27,"wins":35},"deepseek/deepseek-v4-flash":{"draws":89,"losses":70,"wins":47},"deepseek/deepseek-v4-pro":{"draws":24,"losses":29,"wins":19},"google/gemini-3.1-flash-lite":{"draws":17,"losses":27,"wins":40},"google/gemini-3.5-flash":{"draws":22,"losses":20,"wins":16},"google/gemini-3.5-flash-lite":{"draws":19,"losses":26,"wins":9},"google/gemini-3.6-flash":{"draws":24,"losses":22,"wins":10},"google/gemma-4-31b-it":{"draws":14,"losses":25,"wins":25},"gpt-4.1":{"draws":4,"losses":7,"wins":9},"gpt-5":{"draws":28,"losses":32,"wins":20},"gpt-5.4":{"draws":40,"losses":57,"wins":18},"gpt-5.4-mini":{"draws":112,"losses":120,"wins":97},"gpt-5.4-nano":{"draws":100,"losses":104,"wins":104},"gpt-5.5":{"draws":29,"losses":36,"wins":21},"gpt-5.6-luna":{"draws":42,"losses":37,"wins":41},"gpt-5.6-sol":{"draws":13,"losses":53,"wins":24},"gpt-5.6-terra":{"draws":40,"losses":34,"wins":40},"inclusionai/ling-3.0-flash":{"draws":21,"losses":8,"wins":3},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":19},"minimax/minimax-m3":{"draws":39,"losses":37,"wins":32},"mistralai/mistral-medium-3-5":{"draws":9,"losses":18,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":9,"wins":7},"moonshotai/kimi-k3":{"draws":55,"losses":84,"wins":47},"nex-agi/nex-n2-pro":{"draws":24,"losses":27,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":23,"wins":23},"o3":{"draws":24,"losses":29,"wins":34},"openai/gpt-oss-120b":{"draws":52,"losses":32,"wins":30},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":36,"losses":29,"wins":15},"qwen/qwen3.7-plus":{"draws":28,"losses":45,"wins":19},"stepfun/step-3.7-flash":{"draws":28,"losses":23,"wins":25},"tencent/hy3-preview":{"draws":36,"losses":28,"wins":14},"thinkingmachines/inkling":{"draws":15,"losses":36,"wins":17},"x-ai/grok-4.5":{"draws":52,"losses":104,"wins":60},"x-ai/grok-build-0.1":{"draws":13,"losses":15,"wins":6},"xiaomi/mimo-v2.5":{"draws":93,"losses":72,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":35,"wins":23},"z-ai/glm-5.2":{"draws":94,"losses":90,"wins":73}},"gpt-5.5":{"claude-fable-5":{"draws":7,"losses":12,"wins":13},"claude-opus-4-5":{"draws":20,"losses":15,"wins":21},"claude-opus-4-8":{"draws":10,"losses":9,"wins":25},"claude-opus-5":{"draws":8,"losses":34,"wins":20},"claude-sonnet-5":{"draws":14,"losses":8,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":28,"losses":2,"wins":26},"deepseek/deepseek-v4-pro":{"draws":9,"losses":2,"wins":11},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":10,"losses":12,"wins":14},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":3,"losses":3,"wins":8},"gpt-5":{"draws":6,"losses":7,"wins":16},"gpt-5.4":{"draws":20,"losses":19,"wins":15},"gpt-5.4-mini":{"draws":41,"losses":11,"wins":24},"gpt-5.4-nano":{"draws":29,"losses":21,"wins":36},"gpt-5.5":{"draws":14,"losses":9,"wins":9},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":14},"gpt-5.6-sol":{"draws":14,"losses":17,"wins":21},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":20},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":30,"losses":19,"wins":35},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":3,"wins":9},"o3":{"draws":11,"losses":3,"wins":12},"openai/gpt-oss-120b":{"draws":15,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":16,"losses":5,"wins":13},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":27,"losses":47,"wins":34},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":7,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":28,"losses":22,"wins":28}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":17,"wins":3},"claude-opus-4-5":{"draws":20,"losses":18,"wins":16},"claude-opus-4-8":{"draws":12,"losses":16,"wins":14},"claude-opus-5":{"draws":2,"losses":17,"wins":5},"claude-sonnet-5":{"draws":15,"losses":7,"wins":14},"cohere/north-mini-code":{"draws":5,"losses":14,"wins":5},"deepseek/deepseek-v4-flash":{"draws":39,"losses":21,"wins":18},"deepseek/deepseek-v4-pro":{"draws":15,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":8},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":9},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":6},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":10,"wins":7},"gpt-5.4":{"draws":24,"losses":22,"wins":4},"gpt-5.4-mini":{"draws":54,"losses":33,"wins":33},"gpt-5.4-nano":{"draws":42,"losses":41,"wins":37},"gpt-5.5":{"draws":13,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":19,"wins":10},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":20},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":12},"o3":{"draws":2,"losses":8,"wins":10},"openai/gpt-oss-120b":{"draws":20,"losses":11,"wins":15},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":18,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":11,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":13,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":34,"wins":26},"x-ai/grok-build-0.1":{"draws":14,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":26,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":40,"wins":27}},"gpt-5.6-sol":{"claude-fable-5":{"draws":8,"losses":28,"wins":14},"claude-opus-4-5":{"draws":14,"losses":11,"wins":37},"claude-opus-4-8":{"draws":8,"losses":11,"wins":23},"claude-opus-5":{"draws":16,"losses":53,"wins":19},"claude-sonnet-5":{"draws":6,"losses":9,"wins":29},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":12,"losses":13,"wins":45},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":15},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":8},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":13},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":9},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":8},"gpt-4.1":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":4,"losses":5,"wins":13},"gpt-5.4":{"draws":6,"losses":29,"wins":13},"gpt-5.4-mini":{"draws":19,"losses":20,"wins":39},"gpt-5.4-nano":{"draws":13,"losses":24,"wins":53},"gpt-5.5":{"draws":14,"losses":21,"wins":17},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":14},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":24},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":23,"losses":35,"wins":62},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":22},"o3":{"draws":6,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":5,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":12},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":19},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":26,"losses":48,"wins":64},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":6},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":23,"losses":24,"wins":45}},"gpt-5.6-terra":{"claude-fable-5":{"draws":5,"losses":25,"wins":4},"claude-opus-4-5":{"draws":19,"losses":20,"wins":25},"claude-opus-4-8":{"draws":14,"losses":16,"wins":10},"claude-opus-5":{"draws":16,"losses":26,"wins":8},"claude-sonnet-5":{"draws":13,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":14,"wins":48},"deepseek/deepseek-v4-pro":{"draws":12,"losses":7,"wins":9},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":12},"google/gemini-3.5-flash":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash-lite":{"draws":12,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":15},"gpt-4.1":{"draws":5,"losses":1,"wins":0},"gpt-5":{"draws":9,"losses":6,"wins":17},"gpt-5.4":{"draws":14,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":58,"losses":31,"wins":51},"gpt-5.4-nano":{"draws":40,"losses":40,"wins":34},"gpt-5.5":{"draws":17,"losses":20,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":24,"wins":16},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":38,"losses":34,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":14},"o3":{"draws":11,"losses":6,"wins":9},"openai/gpt-oss-120b":{"draws":9,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":30,"losses":58,"wins":26},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":9,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":34,"wins":31}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":3,"losses":1,"wins":0},"claude-opus-5":{"draws":5,"losses":5,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":55,"losses":59,"wins":18},"google/gemini-3.6-flash":{"draws":75,"losses":41,"wins":14},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":21,"losses":3,"wins":8},"gpt-5.5":{"draws":4,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":14,"losses":21,"wins":21},"meituan/longcat-2.0":{"draws":30,"losses":42,"wins":20},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":1},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":33,"losses":20,"wins":11},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":29,"losses":38,"wins":27},"x-ai/grok-4.5":{"draws":17,"losses":43,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":2,"wins":1},"claude-opus-4-5":{"draws":6,"losses":5,"wins":5},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":6},"claude-sonnet-5":{"draws":5,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":7,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":65,"losses":81,"wins":63},"google/gemini-3.6-flash":{"draws":64,"losses":83,"wins":47},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":0,"losses":5,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":17,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":17},"gpt-5.5":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":30,"losses":20,"wins":42},"meituan/longcat-2.0":{"draws":28,"losses":40,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":35,"losses":40,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":45,"losses":38,"wins":33},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":36,"losses":44,"wins":60},"x-ai/grok-4.5":{"draws":27,"losses":66,"wins":19},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":18,"losses":10,"wins":4}},"minimax/minimax-m3":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":9,"losses":17,"wins":6},"claude-opus-4-8":{"draws":8,"losses":10,"wins":0},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-sonnet-5":{"draws":9,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":12},"deepseek/deepseek-v4-flash":{"draws":8,"losses":12,"wins":28},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":10,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":9},"gpt-4.1":{"draws":2,"losses":7,"wins":1},"gpt-5":{"draws":6,"losses":9,"wins":5},"gpt-5.4":{"draws":5,"losses":14,"wins":5},"gpt-5.4-mini":{"draws":32,"losses":27,"wins":29},"gpt-5.4-nano":{"draws":39,"losses":32,"wins":37},"gpt-5.5":{"draws":6,"losses":12,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":23,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":7},"o3":{"draws":6,"losses":8,"wins":6},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":17,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":7,"wins":11}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-8":{"draws":0,"losses":12,"wins":2},"claude-sonnet-5":{"draws":2,"losses":10,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":13,"losses":21,"wins":22},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":5},"gpt-5":{"draws":0,"losses":8,"wins":2},"gpt-5.4":{"draws":1,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":23,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":25,"wins":18},"gpt-5.5":{"draws":2,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":13,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":25,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":11,"wins":7},"o3":{"draws":0,"losses":12,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":11,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":0,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":18,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":20,"wins":14}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":8,"wins":2},"claude-opus-4-5":{"draws":4,"losses":8,"wins":8},"claude-opus-4-8":{"draws":2,"losses":3,"wins":3},"claude-opus-5":{"draws":5,"losses":8,"wins":1},"claude-sonnet-5":{"draws":5,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":5,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":20},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":9},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"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":1,"wins":1},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":8,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":8}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":12,"losses":49,"wins":7},"claude-opus-4-5":{"draws":33,"losses":19,"wins":44},"claude-opus-4-8":{"draws":25,"losses":27,"wins":32},"claude-opus-5":{"draws":22,"losses":70,"wins":14},"claude-sonnet-5":{"draws":19,"losses":12,"wins":25},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":18},"deepseek/deepseek-v4-flash":{"draws":34,"losses":11,"wins":59},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":21},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":22,"losses":18,"wins":24},"google/gemini-3.5-flash-lite":{"draws":66,"losses":28,"wins":80},"google/gemini-3.6-flash":{"draws":57,"losses":42,"wins":53},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":12},"gpt-4.1":{"draws":4,"losses":5,"wins":3},"gpt-5":{"draws":21,"losses":19,"wins":10},"gpt-5.4":{"draws":21,"losses":54,"wins":21},"gpt-5.4-mini":{"draws":63,"losses":33,"wins":58},"gpt-5.4-nano":{"draws":55,"losses":47,"wins":84},"gpt-5.5":{"draws":30,"losses":35,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":20,"wins":19},"gpt-5.6-sol":{"draws":23,"losses":62,"wins":35},"gpt-5.6-terra":{"draws":38,"losses":16,"wins":34},"inclusionai/ling-3.0-flash":{"draws":27,"losses":3,"wins":20},"meituan/longcat-2.0":{"draws":35,"losses":12,"wins":40},"minimax/minimax-m3":{"draws":12,"losses":5,"wins":23},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":62,"losses":49,"wins":49},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":8,"wins":29},"o3":{"draws":15,"losses":12,"wins":27},"openai/gpt-oss-120b":{"draws":29,"losses":4,"wins":31},"poolside/laguna-s-2.1":{"draws":45,"losses":17,"wins":28},"qwen/qwen3.7-max":{"draws":15,"losses":12,"wins":17},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":14,"losses":6,"wins":30},"tencent/hy3-preview":{"draws":13,"losses":14,"wins":27},"thinkingmachines/inkling":{"draws":36,"losses":13,"wins":47},"x-ai/grok-4.5":{"draws":72,"losses":121,"wins":101},"x-ai/grok-build-0.1":{"draws":14,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":14},"z-ai/glm-5.2":{"draws":42,"losses":28,"wins":40}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":6,"losses":11,"wins":3},"claude-opus-4-8":{"draws":10,"losses":8,"wins":2},"claude-opus-5":{"draws":0,"losses":5,"wins":1},"claude-sonnet-5":{"draws":4,"losses":16,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":11,"wins":24},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":4},"gpt-4.1":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":2},"gpt-5.4":{"draws":6,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":23,"losses":31,"wins":14},"gpt-5.4-nano":{"draws":24,"losses":19,"wins":27},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":4},"o3":{"draws":4,"losses":8,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":10,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":21,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":14,"wins":8}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":18,"losses":16,"wins":8},"claude-opus-4-8":{"draws":7,"losses":17,"wins":8},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":27,"losses":18,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":8},"deepseek/deepseek-v4-flash":{"draws":32,"losses":20,"wins":14},"deepseek/deepseek-v4-pro":{"draws":10,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":2},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":4},"google/gemini-3.6-flash":{"draws":7,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":6},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-5":{"draws":12,"losses":6,"wins":4},"gpt-5.4":{"draws":11,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":48,"losses":26,"wins":18},"gpt-5.4-nano":{"draws":58,"losses":23,"wins":23},"gpt-5.5":{"draws":16,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":12,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":22,"losses":14,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":29,"losses":29,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":7},"o3":{"draws":6,"losses":16,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":5},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":5},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":14,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":9,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":37,"losses":33,"wins":28}},"o3":{"claude-fable-5":{"draws":0,"losses":15,"wins":1},"claude-opus-4-5":{"draws":11,"losses":18,"wins":17},"claude-opus-4-8":{"draws":5,"losses":21,"wins":10},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":12,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":12,"wins":31},"deepseek/deepseek-v4-pro":{"draws":5,"losses":9,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":7},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":9},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":2,"losses":13,"wins":5},"gpt-5.4":{"draws":5,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":19,"losses":23,"wins":48},"gpt-5.4-nano":{"draws":24,"losses":34,"wins":29},"gpt-5.5":{"draws":11,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":10,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":12,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":27,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":16},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":15},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":14},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":8},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":49,"wins":23},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":7,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":7,"losses":22,"wins":17}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":16,"losses":13,"wins":7},"claude-opus-4-8":{"draws":8,"losses":10,"wins":6},"claude-sonnet-5":{"draws":5,"losses":13,"wins":6},"cohere/north-mini-code":{"draws":14,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":32,"losses":15,"wins":21},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":9,"wins":3},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":7,"losses":4,"wins":1},"gpt-5.4":{"draws":10,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":36,"losses":35,"wins":27},"gpt-5.4-nano":{"draws":52,"losses":30,"wins":32},"gpt-5.5":{"draws":15,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":14,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":31,"wins":4},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":2,"wins":5},"o3":{"draws":9,"losses":15,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":14,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":26,"losses":18,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":25,"losses":17,"wins":16}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-8":{"draws":0,"losses":7,"wins":1},"claude-opus-5":{"draws":2,"losses":30,"wins":2},"claude-sonnet-5":{"draws":5,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":9,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":86,"losses":49,"wins":77},"google/gemini-3.6-flash":{"draws":66,"losses":66,"wins":26},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":2,"wins":4},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":4,"wins":10},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":33,"losses":11,"wins":20},"meituan/longcat-2.0":{"draws":45,"losses":33,"wins":38},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":45,"losses":28,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":44,"losses":22,"wins":22},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":6},"thinkingmachines/inkling":{"draws":34,"losses":29,"wins":45},"x-ai/grok-4.5":{"draws":29,"losses":60,"wins":21},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":14}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":1,"losses":9,"wins":2},"claude-opus-4-5":{"draws":11,"losses":18,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":9},"claude-opus-5":{"draws":3,"losses":23,"wins":6},"claude-sonnet-5":{"draws":8,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":22},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":4},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":8,"wins":4},"gpt-5.4":{"draws":4,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":28,"losses":21,"wins":27},"gpt-5.4-nano":{"draws":36,"losses":15,"wins":29},"gpt-5.5":{"draws":9,"losses":11,"wins":8},"gpt-5.6-luna":{"draws":18,"losses":7,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":17,"wins":9},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":6},"o3":{"draws":11,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":18,"losses":31,"wins":23},"x-ai/grok-build-0.1":{"draws":0,"losses":8,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":12,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":4,"wins":14},"z-ai/glm-5.2":{"draws":15,"losses":15,"wins":12}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":11,"wins":0},"claude-opus-4-5":{"draws":18,"losses":11,"wins":5},"claude-opus-4-8":{"draws":6,"losses":15,"wins":5},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":10,"losses":5,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":19,"losses":15,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":11,"wins":3},"gpt-5":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":8,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":28,"losses":16,"wins":30},"gpt-5.4-nano":{"draws":28,"losses":19,"wins":45},"gpt-5.5":{"draws":7,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":10,"wins":11},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":6},"o3":{"draws":2,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":10,"wins":2},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":31,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":9,"losses":16,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":19,"losses":19,"wins":10}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":15,"losses":17,"wins":4},"claude-opus-4-8":{"draws":0,"losses":8,"wins":4},"claude-opus-5":{"draws":1,"losses":3,"wins":0},"claude-sonnet-5":{"draws":4,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":22,"losses":20,"wins":24},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":13},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":9},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4":{"draws":4,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":25,"losses":38,"wins":23},"gpt-5.4-nano":{"draws":28,"losses":25,"wins":23},"gpt-5.5":{"draws":5,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":12,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":30,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":8},"o3":{"draws":4,"losses":14,"wins":6},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":11,"losses":43,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":18,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":8,"wins":1},"z-ai/glm-5.2":{"draws":2,"losses":18,"wins":6}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":6,"wins":5},"claude-opus-4-5":{"draws":14,"losses":15,"wins":5},"claude-opus-4-8":{"draws":3,"losses":11,"wins":4},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":7,"losses":12,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":19},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":2},"google/gemini-3.6-flash":{"draws":4,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":1,"losses":9,"wins":6},"gpt-5.4":{"draws":13,"losses":15,"wins":4},"gpt-5.4-mini":{"draws":23,"losses":24,"wins":15},"gpt-5.4-nano":{"draws":36,"losses":14,"wins":28},"gpt-5.5":{"draws":16,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":6},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":14},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":10},"o3":{"draws":11,"losses":8,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":16,"losses":33,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":14,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":19,"wins":15}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":5,"wins":7},"claude-opus-4-8":{"draws":0,"losses":7,"wins":3},"claude-opus-5":{"draws":1,"losses":30,"wins":3},"claude-sonnet-5":{"draws":4,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":21,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":10},"google/gemini-3.5-flash":{"draws":0,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":71,"losses":81,"wins":82},"google/gemini-3.6-flash":{"draws":80,"losses":96,"wins":44},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4":{"draws":6,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":21,"losses":19,"wins":18},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":36},"gpt-5.5":{"draws":5,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":9,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":29,"losses":27,"wins":38},"meituan/longcat-2.0":{"draws":36,"losses":60,"wins":44},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":36,"losses":47,"wins":13},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":0,"losses":9,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":6,"wins":1},"poolside/laguna-s-2.1":{"draws":34,"losses":45,"wins":29},"qwen/qwen3.7-max":{"draws":10,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":38,"losses":43,"wins":43},"x-ai/grok-4.5":{"draws":34,"losses":64,"wins":16},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":19,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":10,"losses":20,"wins":12}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":15,"losses":50,"wins":23},"claude-opus-4-5":{"draws":34,"losses":33,"wins":73},"claude-opus-4-8":{"draws":20,"losses":32,"wins":42},"claude-opus-5":{"draws":27,"losses":136,"wins":41},"claude-sonnet-5":{"draws":23,"losses":16,"wins":37},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":27,"losses":14,"wins":63},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":42},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":15,"losses":22,"wins":13},"google/gemini-3.5-flash-lite":{"draws":61,"losses":35,"wins":110},"google/gemini-3.6-flash":{"draws":39,"losses":80,"wins":67},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":24},"gpt-4.1":{"draws":1,"losses":4,"wins":5},"gpt-5":{"draws":13,"losses":12,"wins":31},"gpt-5.4":{"draws":36,"losses":59,"wins":35},"gpt-5.4-mini":{"draws":63,"losses":31,"wins":120},"gpt-5.4-nano":{"draws":52,"losses":60,"wins":104},"gpt-5.5":{"draws":27,"losses":34,"wins":47},"gpt-5.6-luna":{"draws":18,"losses":26,"wins":34},"gpt-5.6-sol":{"draws":26,"losses":64,"wins":48},"gpt-5.6-terra":{"draws":30,"losses":26,"wins":58},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":43},"meituan/longcat-2.0":{"draws":27,"losses":19,"wins":66},"minimax/minimax-m3":{"draws":17,"losses":3,"wins":32},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":33},"moonshotai/kimi-k3":{"draws":72,"losses":101,"wins":121},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":22},"o3":{"draws":12,"losses":23,"wins":49},"openai/gpt-oss-120b":{"draws":15,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":29,"losses":21,"wins":60},"qwen/qwen3.7-max":{"draws":18,"losses":23,"wins":31},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":31},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":43},"tencent/hy3-preview":{"draws":16,"losses":11,"wins":33},"thinkingmachines/inkling":{"draws":34,"losses":16,"wins":64},"x-ai/grok-4.5":{"draws":74,"losses":109,"wins":109},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":33,"losses":13,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":24},"z-ai/glm-5.2":{"draws":21,"losses":55,"wins":80}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":1,"losses":1,"wins":2},"claude-opus-4-5":{"draws":9,"losses":9,"wins":2},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":4,"losses":2,"wins":2},"claude-sonnet-5":{"draws":3,"losses":10,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":5},"gpt-5":{"draws":6,"losses":7,"wins":3},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":15},"gpt-5.5":{"draws":9,"losses":2,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":0},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":4},"o3":{"draws":3,"losses":7,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":40,"losses":29,"wins":21},"claude-opus-4-8":{"draws":20,"losses":29,"wins":9},"claude-opus-5":{"draws":3,"losses":6,"wins":1},"claude-sonnet-5":{"draws":37,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":23,"losses":13,"wins":14},"deepseek/deepseek-v4-flash":{"draws":38,"losses":36,"wins":42},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":9},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":18},"google/gemini-3.5-flash":{"draws":13,"losses":10,"wins":7},"google/gemini-3.5-flash-lite":{"draws":10,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":15,"wins":16},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-5":{"draws":22,"losses":10,"wins":14},"gpt-5.4":{"draws":23,"losses":26,"wins":5},"gpt-5.4-mini":{"draws":80,"losses":59,"wins":71},"gpt-5.4-nano":{"draws":93,"losses":65,"wins":72},"gpt-5.5":{"draws":28,"losses":13,"wins":7},"gpt-5.6-luna":{"draws":23,"losses":11,"wins":26},"gpt-5.6-sol":{"draws":13,"losses":19,"wins":10},"gpt-5.6-terra":{"draws":23,"losses":24,"wins":9},"inclusionai/ling-3.0-flash":{"draws":7,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":12,"wins":6},"minimax/minimax-m3":{"draws":22,"losses":20,"wins":16},"mistralai/mistral-medium-3-5":{"draws":5,"losses":9,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":6},"moonshotai/kimi-k3":{"draws":31,"losses":38,"wins":17},"nex-agi/nex-n2-pro":{"draws":12,"losses":15,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":12,"wins":9},"o3":{"draws":17,"losses":34,"wins":7},"openai/gpt-oss-120b":{"draws":26,"losses":16,"wins":18},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":14,"losses":14,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":13,"wins":16},"stepfun/step-3.7-flash":{"draws":24,"losses":20,"wins":18},"tencent/hy3-preview":{"draws":14,"losses":12,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":9,"wins":19},"x-ai/grok-4.5":{"draws":33,"losses":64,"wins":13},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":5},"xiaomi/mimo-v2.5":{"draws":58,"losses":31,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":17,"wins":12},"z-ai/glm-5.2":{"draws":56,"losses":54,"wins":26}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":3,"losses":10,"wins":13},"claude-opus-4-8":{"draws":8,"losses":16,"wins":8},"claude-opus-5":{"draws":8,"losses":13,"wins":1},"claude-sonnet-5":{"draws":4,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":14,"losses":19,"wins":21},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":6,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":8},"gpt-4.1":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":5},"gpt-5.4":{"draws":8,"losses":21,"wins":9},"gpt-5.4-mini":{"draws":21,"losses":24,"wins":17},"gpt-5.4-nano":{"draws":24,"losses":23,"wins":35},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":13},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":5,"wins":5},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":12},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":14,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":11},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":24,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":12,"wins":17},"z-ai/glm-5.2":{"draws":9,"losses":16,"wins":5}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":34,"wins":9},"claude-opus-4-5":{"draws":43,"losses":52,"wins":39},"claude-opus-4-8":{"draws":23,"losses":37,"wins":26},"claude-opus-5":{"draws":17,"losses":71,"wins":12},"claude-sonnet-5":{"draws":40,"losses":37,"wins":37},"cohere/north-mini-code":{"draws":14,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":59,"losses":49,"wins":60},"deepseek/deepseek-v4-pro":{"draws":14,"losses":26,"wins":14},"google/gemini-3.1-flash-lite":{"draws":16,"losses":6,"wins":24},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":14},"google/gemini-3.6-flash":{"draws":22,"losses":11,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":7},"gpt-4.1":{"draws":8,"losses":11,"wins":17},"gpt-5":{"draws":27,"losses":29,"wins":34},"gpt-5.4":{"draws":46,"losses":33,"wins":17},"gpt-5.4-mini":{"draws":88,"losses":65,"wins":83},"gpt-5.4-nano":{"draws":94,"losses":73,"wins":90},"gpt-5.5":{"draws":28,"losses":28,"wins":22},"gpt-5.6-luna":{"draws":37,"losses":27,"wins":40},"gpt-5.6-sol":{"draws":23,"losses":45,"wins":24},"gpt-5.6-terra":{"draws":27,"losses":31,"wins":34},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":18,"losses":4,"wins":10},"minimax/minimax-m3":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":4,"losses":14,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":7},"moonshotai/kimi-k3":{"draws":42,"losses":40,"wins":28},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":28,"wins":33},"o3":{"draws":7,"losses":17,"wins":22},"openai/gpt-oss-120b":{"draws":25,"losses":16,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":14,"wins":10},"qwen/qwen3.7-max":{"draws":15,"losses":12,"wins":15},"qwen/qwen3.7-plus":{"draws":19,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":18},"tencent/hy3-preview":{"draws":32,"losses":15,"wins":19},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":20},"x-ai/grok-4.5":{"draws":21,"losses":80,"wins":55},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":56,"losses":26,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":16},"z-ai/glm-5.2":{"draws":98,"losses":75,"wins":75}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-fable-5":{"draws":1,"losses":0,"wins":5},"claude-opus-4-5":{"draws":1,"losses":1,"wins":14},"claude-opus-4-8":{"draws":1,"losses":5,"wins":10},"claude-opus-5":{"draws":12,"losses":12,"wins":22},"claude-sonnet-5":{"draws":6,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":13},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":13},"gpt-5.4":{"draws":2,"losses":8,"wins":8},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":27},"gpt-5.5":{"draws":5,"losses":6,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":14},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":31},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":8},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":30},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":1,"losses":5,"wins":24}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":8,"wins":8},"claude-opus-4-5":{"draws":1,"losses":5,"wins":12},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":8,"losses":14,"wins":8},"claude-sonnet-5":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":3,"wins":11},"gpt-5.4":{"draws":3,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":17},"gpt-5.5":{"draws":1,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":11},"o3":{"draws":0,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":11,"wins":21}},"claude-opus-5":{"claude-fable-5":{"draws":5,"losses":8,"wins":15},"claude-opus-4-5":{"draws":3,"losses":4,"wins":39},"claude-opus-4-8":{"draws":2,"losses":5,"wins":5},"claude-opus-5":{"draws":10,"losses":41,"wins":71},"claude-sonnet-5":{"draws":0,"losses":0,"wins":12},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":22},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5.4":{"draws":0,"losses":4,"wins":14},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":6},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":6},"gpt-5.5":{"draws":0,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":10},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":37},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":12}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-opus-4-5":{"draws":11,"losses":6,"wins":13},"claude-opus-4-8":{"draws":3,"losses":14,"wins":5},"claude-opus-5":{"draws":10,"losses":23,"wins":3},"claude-sonnet-5":{"draws":3,"losses":5,"wins":6},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":21},"deepseek/deepseek-v4-pro":{"draws":5,"losses":5,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":10,"losses":8,"wins":6},"gpt-5.4":{"draws":6,"losses":14,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":13,"wins":8},"gpt-5.5":{"draws":8,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":9},"nex-agi/nex-n2-pro":{"draws":1,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":10},"o3":{"draws":0,"losses":8,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":18,"losses":18,"wins":10},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":27,"losses":22,"wins":17}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":16,"losses":9,"wins":7},"claude-opus-4-8":{"draws":0,"losses":13,"wins":7},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":5,"losses":14,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":13,"wins":17},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":7,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":18,"wins":1},"gpt-5.4":{"draws":8,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":12,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":22,"losses":13,"wins":19},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":19,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":12},"o3":{"draws":1,"losses":13,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":29,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":23,"losses":28,"wins":29}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":5,"losses":6,"wins":3},"claude-opus-4-8":{"draws":3,"losses":9,"wins":4},"claude-opus-5":{"draws":1,"losses":11,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":15},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":3,"wins":9},"gpt-5.4":{"draws":1,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":12},"gpt-5.5":{"draws":5,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":5},"o3":{"draws":1,"losses":2,"wins":5},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":8},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":24,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":20}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":13,"wins":0},"claude-opus-4-8":{"draws":3,"losses":7,"wins":2},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":6,"losses":5,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":6,"wins":0},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":13,"wins":4},"gpt-5.5":{"draws":4,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":3},"o3":{"draws":0,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":12,"wins":4}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":2,"losses":12,"wins":4},"claude-opus-4-5":{"draws":5,"losses":5,"wins":6},"claude-opus-4-8":{"draws":1,"losses":3,"wins":4},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":6},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":15,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":5},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":10},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":9},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":10,"wins":15}},"google/gemini-3.5-flash-lite":{"claude-opus-5":{"draws":1,"losses":8,"wins":1},"google/gemini-3.5-flash-lite":{"draws":37,"losses":32,"wins":39},"google/gemini-3.6-flash":{"draws":48,"losses":43,"wins":25},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":24},"meituan/longcat-2.0":{"draws":26,"losses":21,"wins":27},"moonshotai/kimi-k3":{"draws":21,"losses":32,"wins":9},"poolside/laguna-s-2.1":{"draws":30,"losses":26,"wins":18},"thinkingmachines/inkling":{"draws":28,"losses":26,"wins":34},"x-ai/grok-4.5":{"draws":22,"losses":36,"wins":10},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":1,"losses":1,"wins":0},"claude-opus-5":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":29},"google/gemini-3.6-flash":{"draws":14,"losses":13,"wins":27},"inclusionai/ling-3.0-flash":{"draws":14,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":5,"wins":20},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":2,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":2,"losses":15,"wins":23}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":10,"losses":5,"wins":7},"claude-opus-4-8":{"draws":2,"losses":11,"wins":1},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":13,"losses":6,"wins":9},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":9,"losses":1,"wins":18},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":14,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":4,"wins":24},"gpt-5.5":{"draws":6,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":0,"wins":3},"o3":{"draws":0,"losses":2,"wins":8},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":7},"x-ai/grok-4.5":{"draws":7,"losses":14,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":25,"wins":19}},"gpt-5.4":{"claude-fable-5":{"draws":4,"losses":7,"wins":9},"claude-opus-4-5":{"draws":7,"losses":2,"wins":11},"claude-opus-4-8":{"draws":3,"losses":5,"wins":8},"claude-opus-5":{"draws":6,"losses":20,"wins":20},"claude-sonnet-5":{"draws":3,"losses":2,"wins":9},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":8},"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":3,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":5},"gpt-5":{"draws":2,"losses":3,"wins":9},"gpt-5.4":{"draws":3,"losses":1,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":3,"wins":19},"gpt-5.5":{"draws":10,"losses":3,"wins":9},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":12},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":11},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":33},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":3},"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},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":8,"wins":33},"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":8,"losses":9,"wins":21}},"gpt-5.4-mini":{"claude-fable-5":{"draws":2,"losses":14,"wins":4},"claude-opus-4-5":{"draws":11,"losses":5,"wins":8},"claude-opus-4-8":{"draws":1,"losses":10,"wins":7},"claude-opus-5":{"draws":2,"losses":28,"wins":2},"claude-sonnet-5":{"draws":5,"losses":8,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":14,"losses":6,"wins":24},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":9},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":12},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":11},"gpt-5.4":{"draws":1,"losses":15,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":22},"gpt-5.4-nano":{"draws":16,"losses":15,"wins":15},"gpt-5.5":{"draws":4,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":13},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":14},"o3":{"draws":0,"losses":15,"wins":7},"openai/gpt-oss-120b":{"draws":11,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":13},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":41,"wins":12},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":29,"losses":35,"wins":36}},"gpt-5.4-nano":{"claude-fable-5":{"draws":3,"losses":18,"wins":5},"claude-opus-4-5":{"draws":11,"losses":13,"wins":12},"claude-opus-4-8":{"draws":2,"losses":13,"wins":7},"claude-opus-5":{"draws":4,"losses":19,"wins":3},"claude-sonnet-5":{"draws":15,"losses":8,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":25,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":9},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":10,"losses":6,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":20,"wins":6},"gpt-5.4":{"draws":13,"losses":17,"wins":8},"gpt-5.4-mini":{"draws":24,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":23},"gpt-5.5":{"draws":5,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":1},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":18,"losses":27,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":2,"wins":8},"o3":{"draws":0,"losses":3,"wins":13},"openai/gpt-oss-120b":{"draws":7,"losses":9,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":10,"losses":30,"wins":26},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":42,"losses":31,"wins":29}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":6,"wins":9},"claude-opus-4-5":{"draws":3,"losses":3,"wins":10},"claude-opus-4-8":{"draws":2,"losses":1,"wins":15},"claude-opus-5":{"draws":0,"losses":16,"wins":18},"claude-sonnet-5":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":3,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":3,"wins":12},"gpt-5.4":{"draws":7,"losses":7,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":8},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":18},"gpt-5.5":{"draws":5,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":10},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":8},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":15},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":6},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":0,"wins":7},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":19},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":9,"losses":7,"wins":18}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":5,"losses":6,"wins":13},"claude-opus-4-8":{"draws":2,"losses":8,"wins":10},"claude-opus-5":{"draws":1,"losses":13,"wins":4},"claude-sonnet-5":{"draws":4,"losses":3,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":7,"wins":3},"gpt-5.4":{"draws":7,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":11},"gpt-5.5":{"draws":2,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":14},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":7},"o3":{"draws":0,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":17,"wins":15},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":17,"wins":19}},"gpt-5.6-sol":{"claude-fable-5":{"draws":5,"losses":8,"wins":9},"claude-opus-4-5":{"draws":2,"losses":4,"wins":16},"claude-opus-4-8":{"draws":1,"losses":3,"wins":10},"claude-opus-5":{"draws":6,"losses":24,"wins":14},"claude-sonnet-5":{"draws":1,"losses":5,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":1,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":3,"wins":11},"gpt-5.4":{"draws":2,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":20},"gpt-5.5":{"draws":3,"losses":8,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":5},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":4,"wins":8},"o3":{"draws":1,"losses":1,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":8},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":10,"wins":30},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":21}},"gpt-5.6-terra":{"claude-fable-5":{"draws":3,"losses":18,"wins":3},"claude-opus-4-5":{"draws":3,"losses":4,"wins":11},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":10,"losses":18,"wins":6},"claude-sonnet-5":{"draws":5,"losses":6,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":8},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":5,"wins":13},"gpt-5.4":{"draws":3,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":10,"wins":23},"gpt-5.4-nano":{"draws":2,"losses":13,"wins":9},"gpt-5.5":{"draws":4,"losses":9,"wins":9},"gpt-5.6-luna":{"draws":2,"losses":6,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":9},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":12,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"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},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":20,"wins":18},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":21}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":10,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":5,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":0,"losses":8,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":14,"wins":13},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":17,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":8,"wins":4},"o3":{"draws":0,"losses":8,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":8,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":7,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":16,"wins":2}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-opus-4-5":{"draws":13,"losses":11,"wins":22},"claude-opus-4-8":{"draws":11,"losses":16,"wins":11},"claude-opus-5":{"draws":11,"losses":23,"wins":6},"claude-sonnet-5":{"draws":11,"losses":12,"wins":19},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":15,"losses":8,"wins":27},"deepseek/deepseek-v4-pro":{"draws":5,"losses":9,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":13,"losses":10,"wins":21},"google/gemini-3.5-flash-lite":{"draws":13,"losses":2,"wins":23},"google/gemini-3.6-flash":{"draws":11,"losses":8,"wins":15},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":4,"losses":5,"wins":3},"gpt-5":{"draws":16,"losses":12,"wins":6},"gpt-5.4":{"draws":9,"losses":37,"wins":4},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":19},"gpt-5.4-nano":{"draws":27,"losses":24,"wins":36},"gpt-5.5":{"draws":11,"losses":22,"wins":7},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":7},"gpt-5.6-sol":{"draws":13,"losses":34,"wins":17},"gpt-5.6-terra":{"draws":18,"losses":8,"wins":16},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":1,"wins":12},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":17},"moonshotai/kimi-k3":{"draws":21,"losses":20,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":4,"wins":24},"o3":{"draws":2,"losses":4,"wins":12},"openai/gpt-oss-120b":{"draws":19,"losses":0,"wins":13},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":14},"tencent/hy3-preview":{"draws":9,"losses":11,"wins":14},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":17},"x-ai/grok-4.5":{"draws":19,"losses":51,"wins":38},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":42,"losses":28,"wins":40}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":14,"losses":9,"wins":1},"claude-opus-4-8":{"draws":3,"losses":10,"wins":3},"claude-sonnet-5":{"draws":18,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":22,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":8,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":27,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":29,"losses":12,"wins":7},"gpt-5.5":{"draws":5,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":21,"losses":14,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":3},"o3":{"draws":2,"losses":11,"wins":1},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":10,"losses":15,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":2,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":27,"losses":22,"wins":19}},"o3":{"claude-fable-5":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":4,"losses":6,"wins":8},"claude-opus-4-8":{"draws":0,"losses":8,"wins":4},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":14},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":1,"losses":13,"wins":4},"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},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":13},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":19,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":0,"losses":13,"wins":11}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":7,"losses":2,"wins":5},"claude-opus-4-8":{"draws":3,"losses":5,"wins":0},"claude-sonnet-5":{"draws":4,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":11,"losses":0,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":10,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":10},"gpt-5.5":{"draws":5,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":0,"wins":2},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":9}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":2,"losses":9,"wins":3},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":2,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":11,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":17,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":0,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":0,"losses":21,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":3,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":2,"losses":14,"wins":6}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":9,"losses":9,"wins":2},"claude-opus-4-8":{"draws":2,"losses":5,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":10,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":9,"wins":6},"gpt-5.4":{"draws":3,"losses":7,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":9},"gpt-5.5":{"draws":8,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":10},"o3":{"draws":2,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":23,"wins":3},"xiaomi/mimo-v2.5":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":13,"wins":14}},"thinkingmachines/inkling":{"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":12},"google/gemini-3.6-flash":{"draws":17,"losses":23,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":9,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":3}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":4,"losses":33,"wins":9},"claude-opus-4-5":{"draws":16,"losses":11,"wins":29},"claude-opus-4-8":{"draws":10,"losses":19,"wins":13},"claude-opus-5":{"draws":11,"losses":31,"wins":18},"claude-sonnet-5":{"draws":16,"losses":13,"wins":19},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":27},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":13},"google/gemini-3.5-flash":{"draws":2,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":15,"wins":35},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":20},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":14},"gpt-5.4":{"draws":15,"losses":27,"wins":10},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":46},"gpt-5.4-nano":{"draws":17,"losses":24,"wins":27},"gpt-5.5":{"draws":8,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":5,"losses":16,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":33,"wins":15},"gpt-5.6-terra":{"draws":3,"losses":17,"wins":16},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":3,"wins":25},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":38,"wins":53},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":20},"o3":{"draws":1,"losses":8,"wins":19},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":4,"wins":27},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":20},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":17},"x-ai/grok-4.5":{"draws":22,"losses":47,"wins":55},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":8,"losses":34,"wins":50}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-8":{"draws":3,"losses":2,"wins":1},"claude-sonnet-5":{"draws":5,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":20,"losses":2,"wins":2},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":0},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":3,"wins":3}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":20,"wins":3},"claude-opus-4-5":{"draws":17,"losses":19,"wins":20},"claude-opus-4-8":{"draws":5,"losses":18,"wins":7},"claude-opus-5":{"draws":10,"losses":26,"wins":6},"claude-sonnet-5":{"draws":18,"losses":13,"wins":21},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":21},"deepseek/deepseek-v4-pro":{"draws":8,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":8},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":8,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":1},"gpt-4.1":{"draws":1,"losses":4,"wins":3},"gpt-5":{"draws":18,"losses":14,"wins":12},"gpt-5.4":{"draws":14,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":34,"losses":24,"wins":24},"gpt-5.4-nano":{"draws":43,"losses":17,"wins":23},"gpt-5.5":{"draws":10,"losses":14,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":9},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":32,"losses":21,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":9,"wins":18},"o3":{"draws":2,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":11},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":47,"wins":30},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":3,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":31,"losses":30,"wins":29}}},"medium":{"claude-fable-5":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":2,"losses":1,"wins":13},"claude-opus-4-8":{"draws":1,"losses":8,"wins":5},"claude-opus-5":{"draws":8,"losses":20,"wins":12},"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":8,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":1,"losses":1,"wins":8},"gpt-5.4":{"draws":4,"losses":6,"wins":8},"gpt-5.4-mini":{"draws":7,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":20},"gpt-5.5":{"draws":2,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":14},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":13},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":15,"wins":20},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":10}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":3,"wins":5},"claude-opus-4-5":{"draws":4,"losses":3,"wins":7},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":8,"losses":2,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":2},"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":4,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":6},"gpt-5.4":{"draws":3,"losses":3,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":12},"gpt-5.5":{"draws":6,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":5},"o3":{"draws":4,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":16,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":2,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":4,"wins":13}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":16,"wins":10},"claude-opus-4-5":{"draws":6,"losses":4,"wins":42},"claude-opus-4-8":{"draws":3,"losses":2,"wins":9},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"claude-sonnet-5":{"draws":7,"losses":5,"wins":28},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":8},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":11},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":18},"gpt-4.1":{"draws":2,"losses":0,"wins":8},"gpt-5":{"draws":1,"losses":1,"wins":4},"gpt-5.4":{"draws":3,"losses":7,"wins":12},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":17},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":22},"gpt-5.5":{"draws":2,"losses":10,"wins":12},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":21},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":2,"wins":22},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":13},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":11,"losses":28,"wins":49},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":30}},"claude-sonnet-5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":8,"losses":7,"wins":7},"claude-opus-4-8":{"draws":6,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":5,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":6,"wins":3},"gpt-5.4":{"draws":4,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":12,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":21},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":2},"o3":{"draws":3,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":15,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":3,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":9}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":3,"losses":5,"wins":2},"claude-opus-4-8":{"draws":5,"losses":1,"wins":2},"claude-sonnet-5":{"draws":3,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":10,"wins":1},"gpt-5.4":{"draws":3,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":12,"losses":14,"wins":14},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":6,"wins":7},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"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":4,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":5,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":1}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":6,"losses":0,"wins":2},"claude-opus-4-8":{"draws":8,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":9,"losses":5,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":13,"losses":13,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":4},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":6,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":21,"losses":23,"wins":10},"gpt-5.4-nano":{"draws":24,"losses":11,"wins":15},"gpt-5.5":{"draws":9,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":3},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":3},"o3":{"draws":3,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":9,"losses":10,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":12,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":18,"wins":7}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":4,"losses":10,"wins":0},"claude-opus-4-8":{"draws":4,"losses":5,"wins":1},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":6,"losses":9,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":2,"wins":2},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":17,"wins":13},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":7},"o3":{"draws":6,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":0},"xiaomi/mimo-v2.5":{"draws":3,"losses":14,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":1}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":4,"losses":6,"wins":6},"claude-opus-4-5":{"draws":8,"losses":6,"wins":8},"claude-opus-4-8":{"draws":6,"losses":3,"wins":5},"claude-opus-5":{"draws":2,"losses":21,"wins":9},"claude-sonnet-5":{"draws":6,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"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":3,"losses":3,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":6},"gpt-5.4":{"draws":5,"losses":8,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":5,"wins":15},"gpt-5.5":{"draws":2,"losses":6,"wins":10},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":9,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":0,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"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":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":2,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":8}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":3},"claude-opus-4-8":{"draws":1,"losses":10,"wins":1},"claude-opus-5":{"draws":5,"losses":4,"wins":1},"claude-sonnet-5":{"draws":4,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":35,"losses":45,"wins":32},"google/gemini-3.6-flash":{"draws":50,"losses":35,"wins":23},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":17,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":19,"losses":9,"wins":26},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":12,"wins":18},"meituan/longcat-2.0":{"draws":21,"losses":25,"wins":18},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":27,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":11},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":28,"losses":34,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":34,"wins":24},"x-ai/grok-4.5":{"draws":25,"losses":39,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":13,"losses":13,"wins":6}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":1,"losses":2,"wins":3},"claude-opus-4-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-8":{"draws":4,"losses":0,"wins":2},"claude-opus-5":{"draws":4,"losses":23,"wins":15},"claude-sonnet-5":{"draws":5,"losses":1,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":1},"google/gemini-3.5-flash-lite":{"draws":57,"losses":30,"wins":55},"google/gemini-3.6-flash":{"draws":39,"losses":36,"wins":27},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":1,"losses":4,"wins":1},"gpt-5.4":{"draws":6,"losses":11,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":24,"losses":10,"wins":22},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":31,"losses":3,"wins":18},"meituan/longcat-2.0":{"draws":22,"losses":21,"wins":39},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":25,"wins":21},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":1},"o3":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":28},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":36,"losses":15,"wins":37},"x-ai/grok-4.5":{"draws":22,"losses":24,"wins":38},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":9,"wins":11}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":2,"wins":1},"claude-opus-4-5":{"draws":2,"losses":4,"wins":8},"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":4,"wins":1},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":12},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":4},"o3":{"draws":2,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":4}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":3,"losses":2,"wins":7},"claude-opus-4-8":{"draws":5,"losses":7,"wins":4},"claude-opus-5":{"draws":4,"losses":4,"wins":2},"claude-sonnet-5":{"draws":7,"losses":7,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":6},"gpt-5.4-nano":{"draws":16,"losses":16,"wins":8},"gpt-5.5":{"draws":0,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":4,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":3},"o3":{"draws":2,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":17,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":12,"losses":13,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":5,"losses":9,"wins":10}},"gpt-5.4":{"claude-fable-5":{"draws":2,"losses":5,"wins":3},"claude-opus-4-5":{"draws":2,"losses":5,"wins":11},"claude-opus-4-8":{"draws":3,"losses":7,"wins":6},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-sonnet-5":{"draws":10,"losses":4,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":7,"losses":4,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"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":2,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":1},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":4,"losses":2,"wins":2},"gpt-5.4":{"draws":5,"losses":6,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":18},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":21},"gpt-5.5":{"draws":6,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":3},"o3":{"draws":1,"losses":3,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":15,"losses":18,"wins":7},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":5,"wins":9}},"gpt-5.4-mini":{"claude-fable-5":{"draws":7,"losses":13,"wins":2},"claude-opus-4-5":{"draws":14,"losses":20,"wins":6},"claude-opus-4-8":{"draws":10,"losses":10,"wins":8},"claude-opus-5":{"draws":4,"losses":6,"wins":6},"claude-sonnet-5":{"draws":10,"losses":16,"wins":18},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":11,"losses":18,"wins":9},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":9},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-5":{"draws":13,"losses":5,"wins":10},"gpt-5.4":{"draws":14,"losses":22,"wins":10},"gpt-5.4-mini":{"draws":48,"losses":24,"wins":24},"gpt-5.4-nano":{"draws":37,"losses":32,"wins":60},"gpt-5.5":{"draws":11,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":8},"gpt-5.6-sol":{"draws":11,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":29,"losses":15,"wins":14},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":10},"minimax/minimax-m3":{"draws":18,"losses":10,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":20,"wins":5},"moonshotai/kimi-k3":{"draws":22,"losses":16,"wins":12},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":7},"o3":{"draws":5,"losses":12,"wins":13},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":12,"losses":16,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":13,"wins":7},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":21,"losses":47,"wins":18},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":10},"xiaomi/mimo-v2.5":{"draws":29,"losses":27,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":7,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":29,"wins":17}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":25,"wins":5},"claude-opus-4-5":{"draws":12,"losses":31,"wins":13},"claude-opus-4-8":{"draws":7,"losses":18,"wins":1},"claude-opus-5":{"draws":4,"losses":18,"wins":8},"claude-sonnet-5":{"draws":13,"losses":25,"wins":8},"cohere/north-mini-code":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4-flash":{"draws":13,"losses":17,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":15,"wins":28},"google/gemini-3.5-flash":{"draws":9,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":16,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":12,"wins":9},"gpt-4.1":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":11,"losses":10,"wins":11},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":34,"losses":62,"wins":31},"gpt-5.4-nano":{"draws":31,"losses":46,"wins":41},"gpt-5.5":{"draws":2,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":17,"wins":15},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":5,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":17,"losses":16,"wins":17},"mistralai/mistral-medium-3-5":{"draws":1,"losses":7,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":21,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":14,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":18,"wins":10},"o3":{"draws":4,"losses":12,"wins":6},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":16,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":18,"losses":32,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":11},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":13,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":35,"wins":19},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":35,"losses":33,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":18,"wins":11},"z-ai/glm-5.2":{"draws":23,"losses":24,"wins":26}},"gpt-5.5":{"claude-fable-5":{"draws":4,"losses":6,"wins":4},"claude-opus-4-5":{"draws":8,"losses":7,"wins":7},"claude-opus-4-8":{"draws":4,"losses":4,"wins":6},"claude-opus-5":{"draws":6,"losses":18,"wins":2},"claude-sonnet-5":{"draws":8,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":7,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":6},"gpt-5.5":{"draws":4,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":8,"losses":5,"wins":7},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":8},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":9,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":2,"wins":5},"o3":{"draws":2,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":8},"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":3,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"gpt-5.6-luna":{"claude-fable-5":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-opus-4-8":{"draws":5,"losses":6,"wins":3},"claude-opus-5":{"draws":1,"losses":4,"wins":1},"claude-sonnet-5":{"draws":7,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":1,"wins":4},"gpt-5.4":{"draws":10,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":22,"losses":7,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":16},"gpt-5.5":{"draws":3,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":5,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":2,"losses":0,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":0,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":4},"z-ai/glm-5.2":{"draws":19,"losses":14,"wins":3}},"gpt-5.6-sol":{"claude-fable-5":{"draws":3,"losses":18,"wins":5},"claude-opus-4-5":{"draws":4,"losses":2,"wins":12},"claude-opus-4-8":{"draws":1,"losses":3,"wins":6},"claude-opus-5":{"draws":5,"losses":22,"wins":5},"claude-sonnet-5":{"draws":3,"losses":1,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":2},"gpt-5.4":{"draws":0,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":18},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":10},"o3":{"draws":2,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":23,"wins":20},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":17}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":5,"wins":1},"claude-opus-4-5":{"draws":11,"losses":8,"wins":9},"claude-opus-4-8":{"draws":3,"losses":0,"wins":5},"claude-opus-5":{"draws":3,"losses":8,"wins":1},"claude-sonnet-5":{"draws":3,"losses":6,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":3,"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":5},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":1,"wins":4},"gpt-5.4":{"draws":9,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":26,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":16},"gpt-5.5":{"draws":6,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":7,"losses":4,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":1,"wins":5},"o3":{"draws":3,"losses":2,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":8,"losses":2,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":8,"wins":5}},"inclusionai/ling-3.0-flash":{"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":16,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":20,"losses":20,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":9,"wins":11},"meituan/longcat-2.0":{"draws":6,"losses":22,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":2},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":18,"wins":14},"x-ai/grok-4.5":{"draws":8,"losses":17,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":0,"losses":1,"wins":1},"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":0,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":20,"losses":36,"wins":27},"google/gemini-3.6-flash":{"draws":25,"losses":42,"wins":23},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":21},"meituan/longcat-2.0":{"draws":13,"losses":16,"wins":23},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":5},"poolside/laguna-s-2.1":{"draws":12,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":17,"losses":15,"wins":32},"x-ai/grok-4.5":{"draws":15,"losses":36,"wins":7}},"minimax/minimax-m3":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":3,"losses":6,"wins":1},"claude-opus-4-8":{"draws":8,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":9,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":10,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":5,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":7,"wins":2},"gpt-5.4":{"draws":3,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":21,"wins":9},"gpt-5.4-nano":{"draws":24,"losses":23,"wins":19},"gpt-5.5":{"draws":2,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":3},"o3":{"draws":2,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":11,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":2}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":8,"wins":2},"claude-opus-4-5":{"draws":4,"losses":8,"wins":8},"claude-opus-4-8":{"draws":2,"losses":3,"wins":3},"claude-opus-5":{"draws":5,"losses":8,"wins":1},"claude-sonnet-5":{"draws":5,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":5,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":20},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":9},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"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":1,"wins":1},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":8,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":8}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-5":{"draws":11,"losses":4,"wins":9},"claude-opus-4-8":{"draws":7,"losses":4,"wins":9},"claude-opus-5":{"draws":5,"losses":15,"wins":4},"claude-sonnet-5":{"draws":8,"losses":0,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":9},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":30,"losses":12,"wins":18},"google/gemini-3.6-flash":{"draws":28,"losses":12,"wins":14},"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":5,"wins":7},"gpt-5.4-mini":{"draws":20,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":15,"losses":11,"wins":16},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":7},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":5,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":1,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":24,"losses":11,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":5},"o3":{"draws":5,"losses":3,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":22,"losses":7,"wins":5},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":18,"losses":6,"wins":8},"x-ai/grok-4.5":{"draws":19,"losses":39,"wins":28},"x-ai/grok-build-0.1":{"draws":14,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":17,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":4}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":7,"wins":1},"claude-opus-4-8":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5":{"draws":2,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":4,"wins":2},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":22,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":12,"wins":16},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":8,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":14,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":2}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":2,"wins":4},"claude-opus-4-8":{"draws":4,"losses":4,"wins":0},"claude-sonnet-5":{"draws":6,"losses":2,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":3},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":5,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":5,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":6,"wins":13},"gpt-5.5":{"draws":2,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":4},"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":3,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":2}},"o3":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":3,"losses":8,"wins":7},"claude-opus-4-8":{"draws":4,"losses":5,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":3,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":4},"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":2,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":7,"wins":3},"gpt-5.4":{"draws":1,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":15},"gpt-5.5":{"draws":3,"losses":10,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":2,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":14,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":6}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":6,"losses":8,"wins":2},"claude-opus-4-8":{"draws":3,"losses":4,"wins":3},"claude-sonnet-5":{"draws":1,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4":{"draws":6,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":13,"losses":15,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":11,"wins":14},"gpt-5.5":{"draws":2,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":7,"losses":5,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":2,"wins":3},"o3":{"draws":4,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":3,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":10,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":15,"losses":2,"wins":7}},"poolside/laguna-s-2.1":{"claude-opus-5":{"draws":0,"losses":14,"wins":2},"google/gemini-3.5-flash-lite":{"draws":51,"losses":25,"wins":30},"google/gemini-3.6-flash":{"draws":38,"losses":33,"wins":7},"inclusionai/ling-3.0-flash":{"draws":20,"losses":5,"wins":7},"meituan/longcat-2.0":{"draws":24,"losses":13,"wins":19},"moonshotai/kimi-k3":{"draws":24,"losses":13,"wins":3},"poolside/laguna-s-2.1":{"draws":23,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":11,"wins":14},"x-ai/grok-4.5":{"draws":20,"losses":16,"wins":6}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":1,"losses":9,"wins":2},"claude-opus-4-5":{"draws":8,"losses":7,"wins":3},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":5,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":0},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":3},"gpt-5.4":{"draws":2,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":17,"losses":11,"wins":14},"gpt-5.4-nano":{"draws":17,"losses":9,"wins":16},"gpt-5.5":{"draws":4,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":5},"o3":{"draws":7,"losses":1,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":7,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":5}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":6,"losses":8,"wins":4},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-sonnet-5":{"draws":6,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":4,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":2,"wins":28},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":18,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":15,"losses":10,"wins":3}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":9,"losses":6,"wins":1},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":1,"losses":3,"wins":0},"claude-sonnet-5":{"draws":2,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":0,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":3},"gpt-5.5":{"draws":4,"losses":4,"wins":2},"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":4,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"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":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":8,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":7},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":0}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":4,"losses":1,"wins":3},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":1,"losses":13,"wins":2},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":16},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":23,"losses":36,"wins":37},"google/gemini-3.6-flash":{"draws":23,"losses":33,"wins":28},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":22},"gpt-5.5":{"draws":3,"losses":4,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":13,"losses":23,"wins":18},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":7,"losses":19,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":17},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":5},"xiaomi/mimo-v2.5":{"draws":11,"losses":8,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":10,"wins":6}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":11,"losses":17,"wins":14},"claude-opus-4-5":{"draws":13,"losses":15,"wins":32},"claude-opus-4-8":{"draws":3,"losses":7,"wins":20},"claude-opus-5":{"draws":12,"losses":78,"wins":20},"claude-sonnet-5":{"draws":7,"losses":3,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":11},"google/gemini-3.5-flash-lite":{"draws":20,"losses":11,"wins":47},"google/gemini-3.6-flash":{"draws":13,"losses":26,"wins":29},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":15},"gpt-4.1":{"draws":1,"losses":3,"wins":4},"gpt-5":{"draws":8,"losses":3,"wins":17},"gpt-5.4":{"draws":13,"losses":19,"wins":18},"gpt-5.4-mini":{"draws":26,"losses":19,"wins":49},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":43},"gpt-5.5":{"draws":11,"losses":15,"wins":18},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":22},"gpt-5.6-terra":{"draws":15,"losses":6,"wins":27},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":19},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":32},"minimax/minimax-m3":{"draws":10,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":31},"moonshotai/kimi-k3":{"draws":18,"losses":31,"wins":43},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":7,"wins":2},"o3":{"draws":2,"losses":8,"wins":14},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":21},"qwen/qwen3.7-max":{"draws":9,"losses":14,"wins":19},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":14},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":24},"x-ai/grok-4.5":{"draws":32,"losses":38,"wins":40},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":14,"losses":5,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":13,"losses":21,"wins":30}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":1,"losses":1,"wins":2},"claude-opus-4-5":{"draws":9,"losses":9,"wins":2},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":4,"losses":2,"wins":2},"claude-sonnet-5":{"draws":3,"losses":10,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":5},"gpt-5":{"draws":6,"losses":7,"wins":3},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":15},"gpt-5.5":{"draws":9,"losses":2,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":0},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":4},"o3":{"draws":3,"losses":7,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":25,"losses":10,"wins":7},"claude-opus-4-8":{"draws":12,"losses":13,"wins":3},"claude-opus-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":25,"losses":14,"wins":5},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":10},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":4},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":14,"losses":6,"wins":10},"gpt-5.4":{"draws":9,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":33,"losses":23,"wins":26},"gpt-5.4-nano":{"draws":34,"losses":24,"wins":32},"gpt-5.5":{"draws":15,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":5,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":15,"losses":7,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":21,"losses":13,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":7,"wins":5},"o3":{"draws":8,"losses":22,"wins":0},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":9,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":10,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":12},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":34,"losses":14,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":14}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":1,"losses":6,"wins":5},"claude-opus-4-8":{"draws":2,"losses":12,"wins":2},"claude-opus-5":{"draws":5,"losses":3,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":8},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":5,"losses":5,"wins":4},"gpt-5.4":{"draws":4,"losses":14,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":10,"wins":20},"gpt-5.5":{"draws":1,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":4,"wins":10},"z-ai/glm-5.2":{"draws":0,"losses":6,"wins":4}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":8,"wins":4},"claude-opus-4-5":{"draws":9,"losses":11,"wins":8},"claude-opus-4-8":{"draws":12,"losses":11,"wins":7},"claude-opus-5":{"draws":2,"losses":20,"wins":2},"claude-sonnet-5":{"draws":13,"losses":5,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":3},"gpt-4.1":{"draws":1,"losses":2,"wins":5},"gpt-5":{"draws":2,"losses":3,"wins":11},"gpt-5.4":{"draws":10,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":12,"wins":21},"gpt-5.4-nano":{"draws":25,"losses":18,"wins":23},"gpt-5.5":{"draws":9,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":4},"o3":{"draws":4,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":17,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":17,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":14,"wins":13}}},"none":{"claude-opus-4-5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":2,"wins":6},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":3,"losses":15,"wins":2},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":5},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":5,"losses":5,"wins":8},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":22},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":20},"gpt-5.5":{"draws":7,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":4},"o3":{"draws":4,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":8,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":2,"losses":2,"wins":10},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":4},"claude-sonnet-5":{"draws":2,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":0,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":25},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":21},"gpt-5.5":{"draws":3,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":1},"o3":{"draws":1,"losses":7,"wins":10},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":12,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":7},"z-ai/glm-5.2":{"draws":8,"losses":11,"wins":3}},"claude-opus-5":{"claude-fable-5":{"draws":7,"losses":10,"wins":7},"claude-opus-4-5":{"draws":9,"losses":7,"wins":22},"claude-opus-4-8":{"draws":5,"losses":5,"wins":8},"claude-opus-5":{"draws":19,"losses":60,"wins":35},"claude-sonnet-5":{"draws":8,"losses":3,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":8},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":14,"wins":9},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":1,"wins":8},"gpt-5.4":{"draws":9,"losses":15,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":15},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":21},"gpt-5.5":{"draws":6,"losses":7,"wins":15},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":9,"losses":3,"wins":22},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":8,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":8,"wins":50},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":5,"wins":29}},"claude-sonnet-5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":5,"losses":1,"wins":2},"claude-opus-4-8":{"draws":4,"losses":6,"wins":4},"claude-opus-5":{"draws":5,"losses":12,"wins":5},"claude-sonnet-5":{"draws":3,"losses":1,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":12,"losses":5,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":0},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":4,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":16,"losses":6,"wins":8},"gpt-5.5":{"draws":4,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":6},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":12,"wins":11}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":4,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":3},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":5,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":4,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":18,"wins":6},"gpt-5.4-nano":{"draws":10,"losses":21,"wins":13},"gpt-5.5":{"draws":7,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":2,"losses":8,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":2},"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":4,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":9,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":0,"wins":1}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":23,"losses":14,"wins":1},"claude-opus-4-8":{"draws":10,"losses":16,"wins":2},"claude-opus-5":{"draws":2,"losses":1,"wins":1},"claude-sonnet-5":{"draws":13,"losses":4,"wins":9},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":33,"losses":32,"wins":27},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":5,"losses":7,"wins":0},"google/gemini-3.6-flash":{"draws":9,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":8,"wins":10},"gpt-4.1":{"draws":2,"losses":4,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":14,"losses":12,"wins":6},"gpt-5.4-mini":{"draws":54,"losses":38,"wins":36},"gpt-5.4-nano":{"draws":43,"losses":23,"wins":36},"gpt-5.5":{"draws":17,"losses":15,"wins":2},"gpt-5.6-luna":{"draws":23,"losses":13,"wins":14},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":27,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":14,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":21,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":15,"losses":16,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":5},"o3":{"draws":7,"losses":13,"wins":6},"openai/gpt-oss-120b":{"draws":18,"losses":10,"wins":14},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":14,"losses":19,"wins":3},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":11},"stepfun/step-3.7-flash":{"draws":16,"losses":11,"wins":9},"tencent/hy3-preview":{"draws":12,"losses":7,"wins":7},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":7},"x-ai/grok-4.5":{"draws":23,"losses":30,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":28,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":7},"z-ai/glm-5.2":{"draws":21,"losses":14,"wins":13}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":2,"losses":5,"wins":5},"claude-opus-4-8":{"draws":6,"losses":8,"wins":6},"claude-opus-5":{"draws":0,"losses":5,"wins":1},"claude-sonnet-5":{"draws":3,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":3,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":19,"losses":4,"wins":19},"gpt-5.4-nano":{"draws":16,"losses":13,"wins":17},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":9,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":4,"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":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":4,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":9,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":18,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":5,"losses":7,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":6}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":5,"wins":3},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":13,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":10,"wins":10},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":7,"wins":1},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":1}},"google/gemini-3.5-flash-lite":{"claude-opus-5":{"draws":5,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":48,"losses":35,"wins":41},"google/gemini-3.6-flash":{"draws":47,"losses":42,"wins":21},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":17},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":36},"moonshotai/kimi-k3":{"draws":23,"losses":21,"wins":12},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":22,"wins":23},"x-ai/grok-4.5":{"draws":14,"losses":35,"wins":19}},"google/gemini-3.6-flash":{"claude-opus-5":{"draws":0,"losses":18,"wins":2},"google/gemini-3.5-flash-lite":{"draws":71,"losses":33,"wins":36},"google/gemini-3.6-flash":{"draws":43,"losses":31,"wins":26},"inclusionai/ling-3.0-flash":{"draws":30,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":25,"losses":21,"wins":24},"moonshotai/kimi-k3":{"draws":26,"losses":22,"wins":6},"poolside/laguna-s-2.1":{"draws":28,"losses":18,"wins":18},"thinkingmachines/inkling":{"draws":34,"losses":26,"wins":32},"x-ai/grok-4.5":{"draws":15,"losses":28,"wins":19}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":3,"wins":1},"claude-opus-4-8":{"draws":4,"losses":6,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":12,"losses":12,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":13},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"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":5,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":6,"losses":16,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-4.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":6,"losses":2,"wins":2},"claude-opus-4-8":{"draws":1,"losses":7,"wins":2},"claude-opus-5":{"draws":6,"losses":18,"wins":0},"claude-sonnet-5":{"draws":5,"losses":8,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":7},"gpt-5.5":{"draws":3,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":5},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":6},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":17,"wins":11}},"gpt-5.4":{"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":8,"losses":8,"wins":4},"claude-opus-4-8":{"draws":0,"losses":4,"wins":6},"claude-opus-5":{"draws":2,"losses":8,"wins":4},"claude-sonnet-5":{"draws":1,"losses":0,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":12},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":4,"losses":6,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":4,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":24,"losses":6,"wins":24},"gpt-5.4-nano":{"draws":19,"losses":9,"wins":17},"gpt-5.5":{"draws":4,"losses":6,"wins":6},"gpt-5.6-luna":{"draws":10,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":10},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"o3":{"draws":4,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":10,"losses":9,"wins":19},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":8},"z-ai/glm-5.2":{"draws":20,"losses":3,"wins":3}},"gpt-5.4-mini":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":22,"losses":23,"wins":7},"claude-opus-4-8":{"draws":17,"losses":19,"wins":6},"claude-opus-5":{"draws":4,"losses":4,"wins":0},"claude-sonnet-5":{"draws":15,"losses":11,"wins":0},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":57,"losses":37,"wins":42},"deepseek/deepseek-v4-pro":{"draws":18,"losses":18,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":16},"google/gemini-3.5-flash":{"draws":8,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":8,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":14,"wins":11},"gpt-4.1":{"draws":5,"losses":2,"wins":5},"gpt-5":{"draws":6,"losses":4,"wins":0},"gpt-5.4":{"draws":26,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":47,"losses":41,"wins":30},"gpt-5.4-nano":{"draws":59,"losses":50,"wins":45},"gpt-5.5":{"draws":26,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":26,"losses":10,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":22,"wins":4},"gpt-5.6-terra":{"draws":21,"losses":24,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":19,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":25,"wins":8},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":14,"losses":21,"wins":3},"openai/gpt-oss-120b":{"draws":14,"losses":17,"wins":21},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":10,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":13,"losses":16,"wins":17},"tencent/hy3-preview":{"draws":13,"losses":12,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":10,"wins":10},"x-ai/grok-4.5":{"draws":35,"losses":32,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":46,"losses":42,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":11},"z-ai/glm-5.2":{"draws":25,"losses":19,"wins":12}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-opus-4-5":{"draws":17,"losses":22,"wins":7},"claude-opus-4-8":{"draws":11,"losses":19,"wins":12},"claude-opus-5":{"draws":1,"losses":12,"wins":1},"claude-sonnet-5":{"draws":6,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":15},"deepseek/deepseek-v4-flash":{"draws":51,"losses":42,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":15,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":9,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":13,"wins":14},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":7,"losses":2,"wins":3},"gpt-5.4":{"draws":14,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":54,"losses":43,"wins":49},"gpt-5.4-nano":{"draws":53,"losses":49,"wins":40},"gpt-5.5":{"draws":22,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":22,"wins":12},"gpt-5.6-terra":{"draws":21,"losses":8,"wins":19},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":8},"minimax/minimax-m3":{"draws":13,"losses":19,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":36,"wins":14},"nex-agi/nex-n2-pro":{"draws":17,"losses":13,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":3,"wins":5},"o3":{"draws":20,"losses":14,"wins":15},"openai/gpt-oss-120b":{"draws":33,"losses":10,"wins":17},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":19,"losses":11,"wins":6},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":3},"tencent/hy3-preview":{"draws":22,"losses":16,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":16,"wins":5},"x-ai/grok-4.5":{"draws":28,"losses":39,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":50,"losses":39,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":35,"wins":18}},"gpt-5.5":{"claude-opus-4-5":{"draws":9,"losses":5,"wins":4},"claude-opus-4-8":{"draws":4,"losses":4,"wins":4},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":20,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":6,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":3},"gpt-4.1":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":6,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":25,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":24,"losses":2,"wins":12},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":6,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":0},"o3":{"draws":9,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":2,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":7,"wins":7}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":9,"losses":5,"wins":0},"claude-opus-4-8":{"draws":5,"losses":2,"wins":1},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":15,"wins":8},"deepseek/deepseek-v4-pro":{"draws":9,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":7,"losses":8,"wins":1},"gpt-5.4-mini":{"draws":19,"losses":23,"wins":8},"gpt-5.4-nano":{"draws":20,"losses":24,"wins":10},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":7,"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":6,"losses":7,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":6,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":1},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"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":2,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":3,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":21,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":5}},"gpt-5.6-sol":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":8,"losses":5,"wins":9},"claude-opus-4-8":{"draws":6,"losses":5,"wins":7},"claude-opus-5":{"draws":5,"losses":7,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":22},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":4},"gpt-4.1":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":15},"gpt-5.5":{"draws":7,"losses":4,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":19,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":3,"losses":4,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":8,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":13,"wins":7}},"gpt-5.6-terra":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":5,"losses":8,"wins":5},"claude-opus-4-8":{"draws":10,"losses":5,"wins":3},"claude-opus-5":{"draws":3,"losses":0,"wins":1},"claude-sonnet-5":{"draws":5,"losses":7,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":8},"gpt-4.1":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":25,"losses":14,"wins":17},"gpt-5.4-nano":{"draws":22,"losses":13,"wins":9},"gpt-5.5":{"draws":7,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":17,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":2},"o3":{"draws":8,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":7,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":5}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":3,"losses":1,"wins":0},"claude-opus-5":{"draws":3,"losses":5,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":39,"losses":32,"wins":7},"google/gemini-3.6-flash":{"draws":55,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":21,"losses":3,"wins":8},"gpt-5.5":{"draws":4,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":12,"wins":10},"meituan/longcat-2.0":{"draws":24,"losses":20,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":11,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":1},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":26,"losses":12,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":21,"losses":20,"wins":13},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":3},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":1,"wins":0},"claude-opus-4-5":{"draws":4,"losses":5,"wins":5},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":4},"claude-sonnet-5":{"draws":5,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":7,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":45,"losses":45,"wins":36},"google/gemini-3.6-flash":{"draws":39,"losses":41,"wins":24},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":0,"losses":5,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":17,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":17},"gpt-5.5":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":19,"losses":14,"wins":21},"meituan/longcat-2.0":{"draws":15,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":19,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":33,"losses":21,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":29,"wins":28},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":18,"losses":10,"wins":4}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":11,"wins":5},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":20},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":3},"gpt-5.4":{"draws":2,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":18,"losses":6,"wins":20},"gpt-5.4-nano":{"draws":15,"losses":9,"wins":18},"gpt-5.5":{"draws":4,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":15,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":4,"losses":5,"wins":5},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":9}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-8":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":11,"wins":5},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":3},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":2},"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":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":11,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":12}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":9,"losses":4,"wins":13},"claude-opus-4-8":{"draws":7,"losses":7,"wins":12},"claude-opus-5":{"draws":6,"losses":32,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":19,"losses":3,"wins":32},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":11},"google/gemini-3.5-flash-lite":{"draws":23,"losses":14,"wins":39},"google/gemini-3.6-flash":{"draws":18,"losses":22,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":5},"gpt-5.4":{"draws":8,"losses":12,"wins":10},"gpt-5.4-mini":{"draws":26,"losses":8,"wins":24},"gpt-5.4-nano":{"draws":13,"losses":12,"wins":32},"gpt-5.5":{"draws":10,"losses":8,"wins":6},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":13},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":18,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":6},"o3":{"draws":8,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":13},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":16},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":13},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":22},"x-ai/grok-4.5":{"draws":34,"losses":31,"wins":35},"xiaomi/mimo-v2.5":{"draws":7,"losses":12,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":8}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":4,"wins":2},"claude-opus-4-8":{"draws":7,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":5,"wins":1},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":19,"losses":7,"wins":18},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5.4":{"draws":6,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":20,"losses":7,"wins":11},"gpt-5.5":{"draws":4,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":2},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":7,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":8,"wins":6}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":0,"losses":5,"wins":3},"claude-opus-4-8":{"draws":0,"losses":3,"wins":5},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":3,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":6,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":2,"wins":1},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":12,"losses":5,"wins":3},"gpt-5.5":{"draws":9,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":1,"losses":2,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":7}},"o3":{"claude-opus-4-5":{"draws":4,"losses":4,"wins":2},"claude-opus-4-8":{"draws":1,"losses":8,"wins":5},"claude-opus-5":{"draws":0,"losses":14,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":7,"losses":6,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":4,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":17,"losses":12,"wins":10},"gpt-5.5":{"draws":8,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"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":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":7},"xiaomi/mimo-v2.5":{"draws":4,"losses":6,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":3,"losses":3,"wins":0},"claude-opus-4-8":{"draws":2,"losses":1,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":6,"wins":2},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":13,"losses":19,"wins":14},"gpt-5.4-nano":{"draws":23,"losses":13,"wins":8},"gpt-5.5":{"draws":8,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":1},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":3},"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":8},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":13,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":0}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-8":{"draws":0,"losses":7,"wins":1},"claude-opus-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":5,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":9,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":35,"losses":24,"wins":47},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":19},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":2,"wins":4},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":4,"wins":10},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":13,"losses":6,"wins":13},"meituan/longcat-2.0":{"draws":21,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":21,"losses":15,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":21,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":18,"wins":31},"x-ai/grok-4.5":{"draws":9,"losses":44,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":14}},"qwen/qwen3.7-max":{"claude-opus-4-5":{"draws":3,"losses":11,"wins":4},"claude-opus-4-8":{"draws":2,"losses":5,"wins":5},"claude-opus-5":{"draws":3,"losses":18,"wins":1},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":8,"wins":20},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":0,"losses":3,"wins":1},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":10,"wins":13},"gpt-5.4-nano":{"draws":19,"losses":6,"wins":13},"gpt-5.5":{"draws":5,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":1},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":12,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":9,"losses":8,"wins":7}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":12,"losses":3,"wins":1},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":11,"losses":14,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":8,"wins":2},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":17},"gpt-5.5":{"draws":5,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":4},"o3":{"draws":2,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":10,"wins":0},"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":4,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":8,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":14,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":7}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":4,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":14,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-5.4":{"draws":3,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":15,"wins":12},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":12},"gpt-5.5":{"draws":1,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":16,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":2},"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":2,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":10,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":0}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":1,"wins":4},"claude-opus-4-5":{"draws":5,"losses":6,"wins":3},"claude-opus-4-8":{"draws":1,"losses":6,"wins":1},"claude-opus-5":{"draws":2,"losses":6,"wins":2},"claude-sonnet-5":{"draws":5,"losses":2,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":16,"losses":7,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":10,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":22,"losses":3,"wins":19},"gpt-5.5":{"draws":8,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":4},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":2},"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":5,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":9,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":10,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":1}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":4,"wins":4},"claude-opus-4-8":{"draws":0,"losses":3,"wins":1},"claude-opus-5":{"draws":0,"losses":17,"wins":1},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":9,"losses":6,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":32,"losses":31,"wins":33},"google/gemini-3.6-flash":{"draws":40,"losses":40,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":14},"gpt-5.5":{"draws":2,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":18},"meituan/longcat-2.0":{"draws":16,"losses":31,"wins":15},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":5},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":0},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":19},"x-ai/grok-4.5":{"draws":18,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":11,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":10,"wins":6}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":5,"losses":7,"wins":12},"claude-opus-4-8":{"draws":7,"losses":6,"wins":9},"claude-opus-5":{"draws":4,"losses":27,"wins":3},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":29},"deepseek/deepseek-v4-pro":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash-lite":{"draws":31,"losses":9,"wins":28},"google/gemini-3.6-flash":{"draws":17,"losses":33,"wins":18},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":9},"gpt-5.4":{"draws":8,"losses":13,"wins":7},"gpt-5.4-mini":{"draws":30,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":23,"losses":17,"wins":34},"gpt-5.5":{"draws":8,"losses":3,"wins":13},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":11,"losses":10,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":10},"meituan/longcat-2.0":{"draws":9,"losses":10,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":14},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":32,"wins":25},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":8},"o3":{"draws":9,"losses":7,"wins":16},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":14},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":23},"x-ai/grok-4.5":{"draws":20,"losses":24,"wins":14},"xiaomi/mimo-v2.5":{"draws":15,"losses":7,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":10}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":15,"losses":15,"wins":12},"claude-opus-4-8":{"draws":5,"losses":14,"wins":5},"claude-opus-5":{"draws":2,"losses":1,"wins":1},"claude-sonnet-5":{"draws":7,"losses":6,"wins":7},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":10},"deepseek/deepseek-v4-flash":{"draws":28,"losses":30,"wins":32},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":7,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":7,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":12},"gpt-4.1":{"draws":0,"losses":6,"wins":2},"gpt-5":{"draws":4,"losses":4,"wins":2},"gpt-5.4":{"draws":12,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":35,"losses":33,"wins":42},"gpt-5.4-nano":{"draws":39,"losses":39,"wins":38},"gpt-5.5":{"draws":13,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":3,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":25,"wins":12},"nex-agi/nex-n2-pro":{"draws":9,"losses":9,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":5,"wins":4},"o3":{"draws":6,"losses":11,"wins":7},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":9},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":13},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":7},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":7},"x-ai/grok-4.5":{"draws":20,"losses":36,"wins":8},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":18,"losses":15,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":7},"z-ai/glm-5.2":{"draws":24,"losses":25,"wins":9}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":8},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":3,"losses":10,"wins":1},"claude-sonnet-5":{"draws":0,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":15,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":15},"gpt-5.5":{"draws":5,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":1},"o3":{"draws":4,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":13,"wins":4},"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":{"draws":9,"losses":10,"wins":1}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":6,"wins":2},"claude-opus-4-5":{"draws":17,"losses":22,"wins":11},"claude-opus-4-8":{"draws":6,"losses":8,"wins":12},"claude-opus-5":{"draws":5,"losses":25,"wins":4},"claude-sonnet-5":{"draws":9,"losses":19,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":21,"losses":31,"wins":24},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":3,"losses":6,"wins":11},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":5,"wins":9},"gpt-5":{"draws":7,"losses":12,"wins":11},"gpt-5.4":{"draws":22,"losses":1,"wins":5},"gpt-5.4-mini":{"draws":37,"losses":29,"wins":38},"gpt-5.4-nano":{"draws":26,"losses":38,"wins":44},"gpt-5.5":{"draws":9,"losses":7,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":11,"losses":17,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":15},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":12,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":7},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":17,"wins":11},"o3":{"draws":1,"losses":8,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":5},"poolside/laguna-s-2.1":{"draws":3,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":9},"thinkingmachines/inkling":{"draws":3,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":16,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":25,"losses":19,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":31,"wins":33}}}}}