{"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":"2026-07-26T09:15:16Z","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":4.0371999999999995}},"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":16.698169999999998},"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":71.88452056403746,"medium":63.18373694389047},"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":"2026-07-26T05:19:29Z","match_totals_all":{"draws":35,"losses":41,"wins":68},"match_totals_tracks":{"highest":{"draws":21,"losses":24,"wins":41},"medium":{"draws":14,"losses":17,"wins":27}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":64.0053579652587,"min":47.007104823449374},"per_game":{"GB2-01":76.41213732030407,"GB2-02":69.21456465029283,"GB2-03":61.84380589799165,"GB2-04":100.0,"GB2-05":73.28703251274473,"GB2-06":55.71539736125434,"GB2-07":47.281027543041205,"GB2-08":91.3221992266709},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":11,"wins":11},"GB2-02":{"draws":13,"losses":2,"wins":3},"GB2-03":{"draws":8,"losses":3,"wins":3},"GB2-04":{"draws":7,"losses":0,"wins":11},"GB2-05":{"draws":0,"losses":10,"wins":14},"GB2-06":{"draws":7,"losses":6,"wins":7},"GB2-07":{"draws":0,"losses":7,"wins":9},"GB2-08":{"draws":0,"losses":2,"wins":10}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":6,"wins":6},"GB2-02":{"draws":7,"losses":2,"wins":3},"GB2-03":{"draws":8,"losses":3,"wins":3},"GB2-04":{"draws":3,"losses":0,"wins":7},"GB2-05":{"draws":0,"losses":6,"wins":10},"GB2-06":{"draws":3,"losses":4,"wins":3},"GB2-07":{"draws":0,"losses":3,"wins":3},"GB2-08":{"draws":0,"losses":0,"wins":6}},"medium":{"GB2-01":{"draws":0,"losses":5,"wins":5},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-04":{"draws":4,"losses":0,"wins":4},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-06":{"draws":4,"losses":2,"wins":4},"GB2-07":{"draws":0,"losses":4,"wins":6},"GB2-08":{"draws":0,"losses":2,"wins":4}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1507.0491924575642,"GB2-02":1513.3455175755498,"GB2-03":1499.379748634163,"GB2-04":1588.114001952077,"GB2-05":1560.969119598614,"GB2-06":1490.0543435409977,"GB2-07":1514.176433952995,"GB2-08":1595.5814065397624},"medium":{"GB2-01":1505.206871653205,"GB2-02":1499.952050185748,"GB2-04":1551.883974396835,"GB2-05":1504.8943549334751,"GB2-06":1525.6313508711555,"GB2-07":1536.1451766434732,"GB2-08":1525.643658731033}},"per_game_tracks":{"highest":{"GB2-01":76.41213732030407,"GB2-02":69.21456465029283,"GB2-03":61.84380589799165,"GB2-04":100.0,"GB2-05":73.28703251274473,"GB2-06":55.71539736125434,"GB2-07":47.281027543041205,"GB2-08":91.3221992266709},"medium":{"GB2-01":55.42144731226924,"GB2-02":47.007104823449374,"GB2-04":100.0,"GB2-05":56.1511915355172,"GB2-06":61.0518694513118,"GB2-07":60.6950851313887,"GB2-08":61.95946035329696}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.9014141609278,"medium":61.10930176958958},"reasoning_agg":{"highest":{"max":91.3221992266709,"mean":66.9014141609278,"min":47.281027543041205},"medium":{"max":100.0,"mean":61.10930176958958,"min":47.007104823449374}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":5.792112391338222},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":91.3221992266709,"expected_score":61.836813452855104,"reliability_score":5.910330561954808,"uncertainty_avg":94.08966943804519,"uncertainty_penalty":-5.064600708072696},"medium":{"ceiling_score":100.0,"expected_score":65.8873118085211,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":4.7780100389315265}}},{"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":7.1388750000000005},"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":33.78345000000001},"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":62.81584881824258,"highest":71.47376466099449,"medium":72.86131776467748,"none":48.65436657195233},"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":"2026-07-26T05:19:30Z","match_totals_all":{"draws":64,"losses":79,"wins":181},"match_totals_tracks":{"highest":{"draws":15,"losses":33,"wins":72},"medium":{"draws":19,"losses":37,"wins":76},"none":{"draws":30,"losses":9,"wins":33}},"model_slug":"claude-opus-5","overall":{"max":99.27521220425331,"mean":63.609095448807295,"min":27.070673410619115},"per_game":{"GB2-01":40.571738173961435,"GB2-02":59.27756537510363,"GB2-03":95.24700081553266,"GB2-04":81.44092311685907,"GB2-05":70.47764245262715,"GB2-07":90.0023265070076,"GB2-08":63.29915618586994},"per_game_all":{"GB2-01":58.44332780055837,"GB2-02":49.67609362178258,"GB2-03":94.0477232155884,"GB2-04":63.850260231493984,"GB2-05":75.22605327405297,"GB2-08":35.65163476597914},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":15,"wins":22},"GB2-02":{"draws":21,"losses":13,"wins":12},"GB2-03":{"draws":2,"losses":9,"wins":49},"GB2-04":{"draws":20,"losses":11,"wins":17},"GB2-05":{"draws":0,"losses":9,"wins":41},"GB2-07":{"draws":0,"losses":3,"wins":25},"GB2-08":{"draws":0,"losses":19,"wins":15}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":5,"wins":5},"GB2-02":{"draws":7,"losses":10,"wins":7},"GB2-03":{"draws":0,"losses":3,"wins":17},"GB2-04":{"draws":8,"losses":4,"wins":10},"GB2-05":{"draws":0,"losses":4,"wins":16},"GB2-07":{"draws":0,"losses":0,"wins":8},"GB2-08":{"draws":0,"losses":7,"wins":9}},"medium":{"GB2-01":{"draws":0,"losses":10,"wins":10},"GB2-02":{"draws":9,"losses":3,"wins":4},"GB2-03":{"draws":0,"losses":4,"wins":18},"GB2-04":{"draws":10,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":3,"wins":17},"GB2-07":{"draws":0,"losses":3,"wins":17},"GB2-08":{"draws":0,"losses":10,"wins":6}},"none":{"GB2-01":{"draws":21,"losses":0,"wins":7},"GB2-02":{"draws":5,"losses":0,"wins":1},"GB2-03":{"draws":2,"losses":2,"wins":14},"GB2-04":{"draws":2,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":2,"wins":8},"GB2-08":{"draws":0,"losses":2,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1520.8639407727017,"GB2-02":1503.7395185461662,"GB2-03":1589.465451118175,"GB2-04":1514.3971657708964,"GB2-05":1572.5394209061035,"GB2-08":1486.4462123914843},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1504.3187865397167,"GB2-02":1491.7210674552805,"GB2-03":1593.1702216698036,"GB2-04":1540.7851653709674,"GB2-05":1577.4451500786656,"GB2-07":1611.1993973653332,"GB2-08":1517.118867669573},"medium":{"GB2-01":1504.4025512724556,"GB2-02":1511.7052568903732,"GB2-03":1598.4041041929434,"GB2-04":1500.162143662236,"GB2-05":1594.2291735099725,"GB2-07":1598.7226099854302,"GB2-08":1470.1978139717671},"none":{"GB2-01":1553.8704845059324,"GB2-02":1507.792231292845,"GB2-03":1576.8220274917776,"GB2-04":1502.2441882794865,"GB2-05":1545.9439391296726,"GB2-08":1472.0219555331128}},"per_game_tracks":{"highest":{"GB2-01":40.571738173961435,"GB2-02":59.27756537510363,"GB2-03":95.24700081553266,"GB2-04":81.44092311685907,"GB2-05":70.47764245262715,"GB2-07":90.0023265070076,"GB2-08":63.29915618586994},"medium":{"GB2-01":54.53496905917403,"GB2-02":62.680042079625,"GB2-03":99.2752122042533,"GB2-04":69.91714889851902,"GB2-05":98.38193282305971,"GB2-07":81.58417117604387,"GB2-08":43.655748112067485},"none":{"GB2-01":80.22327616853967,"GB2-02":27.070673410619115,"GB2-03":87.62095662697925,"GB2-04":40.19270867910388,"GB2-05":56.81858454647206,"GB2-08":0.0}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":64.9263449955337,"medium":70.46915029045569,"none":55.43179106043248},"reasoning_agg":{"highest":{"max":95.24700081553266,"mean":64.9263449955337,"min":40.571738173961435},"medium":{"max":99.27521220425331,"mean":70.46915029045569,"min":43.655748112067485},"none":{"max":87.62095662697925,"mean":55.43179106043248,"min":27.070673410619115}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":99.27521220425331,"expected_score":64.01129202183304,"reasoning_variance":15.037359230023206,"reliability_score":1.611301224657879,"uncertainty_avg":98.38869877534212,"uncertainty_penalty":0.40219657302574774},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":95.24700081553266,"expected_score":69.2199642644287,"reliability_score":1.4499859839122138,"uncertainty_avg":98.55001401608779,"uncertainty_penalty":4.293619268895},"medium":{"ceiling_score":99.27521220425331,"expected_score":66.75433902679963,"reliability_score":1.0874894879341497,"uncertainty_avg":98.91251051206585,"uncertainty_penalty":-3.7148112636560597},"none":{"ceiling_score":87.62095662697925,"expected_score":65.52242270562407,"reliability_score":2.2964282021271885,"uncertainty_avg":97.70357179787281,"uncertainty_penalty":10.090631645191586}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":2.642580625,"median":2.681945,"min":1.562975,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":21.140645},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.712055,"mean":0.49864374999999994,"median":0.5065824999999999,"min":0.29423750000000004,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":3.989149999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.1598575,"mean":0.093565,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":8,"token_priced_attempt_count":10,"total":0.74852}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":1.078263125,"median":0.5065824999999999,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":28},"run_count":24,"token_priced_attempt_count":28,"total":25.878315},"codegen_latency_ms":{"attempt_count":28,"max_ms":1461887,"mean_ms":367273.6666666667,"min_ms":21601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1461887,"mean_ms":911419.875,"min_ms":461183,"run_count":8},"medium":{"attempt_count":9,"max_ms":292880,"mean_ms":161490.125,"min_ms":88006,"run_count":8},"none":{"attempt_count":10,"max_ms":50293,"mean_ms":28911.0,"min_ms":21601,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":218271,"output_mean":69498.70833333333,"output_min":3346,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":218271,"output_mean":172117.75,"output_min":103016,"run_count":8},"medium":{"attempt_count":9,"output_max":45034,"output_mean":31797.75,"output_min":18396,"run_count":8},"none":{"attempt_count":10,"output_max":7647,"output_mean":4580.625,"output_min":3346,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":57.92894677061806,"highest":58.56006372038064,"medium":49.60216959599164,"none":67.15660310382877},"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":"2026-07-26T05:17:59Z","match_totals_all":{"draws":47,"losses":38,"wins":77},"match_totals_tracks":{"highest":{"draws":10,"losses":22,"wins":30},"medium":{"draws":15,"losses":13,"wins":18},"none":{"draws":22,"losses":3,"wins":29}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":58.43961214006702,"min":25.92719442513856},"per_game":{"GB2-01":38.70369401546394,"GB2-02":69.18710290810589,"GB2-04":34.8823266516462,"GB2-05":61.19374250559991,"GB2-06":100.0,"GB2-07":50.099920378847195,"GB2-08":55.8536595830013},"per_game_all":{"GB2-01":61.313673770307865,"GB2-02":68.54140199845357,"GB2-04":32.32426276518387,"GB2-05":59.628600078455236,"GB2-06":83.86098754469452,"GB2-07":51.99050913465493,"GB2-08":47.84319210257646},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":4,"wins":14},"GB2-02":{"draws":20,"losses":3,"wins":5},"GB2-03":{"draws":6,"losses":0,"wins":4},"GB2-04":{"draws":5,"losses":9,"wins":4},"GB2-05":{"draws":0,"losses":5,"wins":15},"GB2-06":{"draws":4,"losses":1,"wins":17},"GB2-07":{"draws":0,"losses":14,"wins":14},"GB2-08":{"draws":10,"losses":2,"wins":4}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":2},"GB2-02":{"draws":4,"losses":3,"wins":5},"GB2-04":{"draws":2,"losses":8,"wins":2},"GB2-05":{"draws":0,"losses":3,"wins":7},"GB2-06":{"draws":1,"losses":1,"wins":8},"GB2-07":{"draws":0,"losses":4,"wins":4},"GB2-08":{"draws":3,"losses":1,"wins":2}},"medium":{"GB2-01":{"draws":0,"losses":2,"wins":4},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-04":{"draws":2,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":2,"wins":2},"GB2-06":{"draws":2,"losses":0,"wins":4},"GB2-07":{"draws":0,"losses":7,"wins":5},"GB2-08":{"draws":3,"losses":1,"wins":2}},"none":{"GB2-01":{"draws":2,"losses":0,"wins":8},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":0,"wins":4},"GB2-04":{"draws":1,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":0,"wins":6},"GB2-06":{"draws":1,"losses":0,"wins":5},"GB2-07":{"draws":0,"losses":3,"wins":5},"GB2-08":{"draws":4,"losses":0,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1541.707305603825,"GB2-02":1504.814728121811,"GB2-04":1482.1764081270542,"GB2-05":1544.7982644674669,"GB2-06":1578.9299751350784,"GB2-07":1500.958681081218,"GB2-08":1509.6732833339663},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1497.2143366743176,"GB2-02":1513.2857565694662,"GB2-04":1429.3430091761702,"GB2-05":1547.3401211800676,"GB2-06":1595.5864302706073,"GB2-07":1503.9038388143845,"GB2-08":1515.6252253403404},"medium":{"GB2-01":1529.712588032533,"GB2-02":1500.0,"GB2-04":1501.1862152049923,"GB2-05":1502.9304233504108,"GB2-06":1564.5508091632882,"GB2-07":1475.0293296840614,"GB2-08":1514.4687601735634},"none":{"GB2-01":1598.1949921046248,"GB2-02":1501.1584277959664,"GB2-03":1551.7538641291055,"GB2-04":1516.0,"GB2-05":1584.1242488719224,"GB2-06":1576.6526859713404,"GB2-07":1523.9428747452082,"GB2-08":1498.9258644879949}},"per_game_tracks":{"highest":{"GB2-01":38.70369401546394,"GB2-02":69.18710290810589,"GB2-04":34.8823266516462,"GB2-05":61.19374250559991,"GB2-06":100.0,"GB2-07":50.099920378847195,"GB2-08":55.8536595830013},"medium":{"GB2-01":53.116332192424274,"GB2-02":57.38107590489985,"GB2-04":36.16326721876682,"GB2-05":36.490537144330006,"GB2-06":64.10935300148437,"GB2-07":43.0889482228784,"GB2-08":56.86567348715776},"none":{"GB2-01":92.12099510303536,"GB2-02":79.05602718235497,"GB2-03":77.88057586225675,"GB2-04":25.92719442513856,"GB2-05":81.2015205854358,"GB2-06":87.47360963259923,"GB2-07":62.78265880223919,"GB2-08":30.81024323757033}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":58.56006372038064,"medium":49.60216959599164,"none":67.15660310382877},"reasoning_agg":{"highest":{"max":100.0,"mean":58.56006372038064,"min":34.8823266516462},"medium":{"max":64.10935300148437,"mean":49.60216959599164,"min":36.16326721876682},"none":{"max":92.12099510303536,"mean":67.15660310382877,"min":25.92719442513856}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":58.76828073627932,"reasoning_variance":17.554433507837132,"reliability_score":0.724992991956114,"uncertainty_avg":99.27500700804389,"uncertainty_penalty":0.32866859621230304},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":49.84103982600532,"reliability_score":1.4499859839122138,"uncertainty_avg":98.55001401608779,"uncertainty_penalty":-8.719023894375319},"medium":{"ceiling_score":64.10935300148437,"expected_score":55.418783794159914,"reliability_score":0.724992991956114,"uncertainty_avg":99.27500700804389,"uncertainty_penalty":5.816614198168274},"none":{"ceiling_score":92.12099510303536,"expected_score":72.75573716867567,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":5.5991340648468935}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.341716425,"mean":0.30867194062500003,"median":0.31836633750000004,"min":0.2745495,"recorded_attempt_count":33,"run_count":16,"total":4.9387510500000005},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.25698975,"mean":0.172479834375,"median":0.166217925,"min":0.10864875,"recorded_attempt_count":29,"run_count":16,"total":2.75967735},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","max":0.058529250000000005,"mean":0.03888066562499999,"median":0.038104875,"min":0.029012250000000003,"recorded_attempt_count":20,"run_count":16,"total":0.62209065}},"codegen_cost_usd":{"admitted_cell_count":40,"cell_count":24,"cost_basis_counts":{"provider_reported":82},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.341716425,"mean":0.17334414687500002,"median":0.166217925,"min":0.029012250000000003,"recorded_attempt_count":82,"run_count":48,"total":8.320519050000001},"codegen_latency_ms":{"attempt_count":82,"max_ms":190231,"mean_ms":91741.70833333331,"min_ms":16474,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":33,"max_ms":190231,"mean_ms":162520.375,"min_ms":111427,"run_count":16},"medium":{"attempt_count":29,"max_ms":131703,"mean_ms":90173.1875,"min_ms":44747,"run_count":16},"none":{"attempt_count":20,"max_ms":46243,"mean_ms":22531.5625,"min_ms":16474,"run_count":16}},"codegen_output_tokens":{"attempt_count":82,"output_max":45822,"output_mean":20391.416666666668,"output_min":1873,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":33,"output_max":45822,"output_mean":37854.8125,"output_min":25990,"run_count":16},"medium":{"attempt_count":29,"output_max":31826,"output_mean":20126.3125,"output_min":8874,"run_count":16},"none":{"attempt_count":20,"output_max":6181,"output_mean":3193.125,"output_min":1873,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"medium":57.50792140911991},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":4,"first_pass_rate":0.25,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":12,"repaired_rate":0.75}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-07-26T05:18:21Z","match_totals_all":{"draws":40,"losses":41,"wins":57},"match_totals_tracks":{"medium":{"draws":40,"losses":41,"wins":57}},"model_slug":"google-gemini-3-6-flash","overall":{"max":81.03716261142714,"mean":57.5079214091199,"min":30.27434194877536},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":8,"wins":12},"GB2-02":{"draws":14,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":10,"wins":7},"GB2-04":{"draws":14,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":4,"wins":12},"GB2-06":{"draws":1,"losses":2,"wins":15},"GB2-07":{"draws":0,"losses":8,"wins":8},"GB2-08":{"draws":4,"losses":5,"wins":1}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":8,"wins":12},"GB2-02":{"draws":14,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":10,"wins":7},"GB2-04":{"draws":14,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":4,"wins":12},"GB2-06":{"draws":1,"losses":2,"wins":15},"GB2-07":{"draws":0,"losses":8,"wins":8},"GB2-08":{"draws":4,"losses":5,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1522.2207952679128,"GB2-02":1499.2975359763532,"GB2-03":1478.2516889131407,"GB2-04":1484.292467416579,"GB2-05":1557.78878727771,"GB2-06":1586.4985797846623,"GB2-07":1494.9444318503906,"GB2-08":1469.9817440738443}},"per_game_tracks":{"medium":{"GB2-01":63.71009078749498,"GB2-02":51.8008799197924,"GB2-03":50.40983661431383,"GB2-04":63.61287066183908,"GB2-05":76.97725300062868,"GB2-06":81.03716261142714,"GB2-07":42.240935728687745,"GB2-08":30.27434194877536}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":57.5079214091199},"reasoning_agg":{"medium":{"max":81.03716261142714,"mean":57.5079214091199,"min":30.27434194877536}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":81.03716261142714},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":81.03716261142714,"expected_score":46.447443847139795,"reliability_score":0.634368867961598,"uncertainty_avg":99.3656311320384,"uncertainty_penalty":-11.060477561980107}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":12.915325,"mean":10.059243749999998,"median":10.0094025,"min":8.401555,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":80.47395},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6689649999999999,"mean":0.46799875,"median":0.4352825,"min":0.366615,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":9,"token_priced_attempt_count":10,"total":4.1199200000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.147405,"mean":0.121464375,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":12.915325,"mean":3.549568958333333,"median":0.4352825,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":27},"run_count":26,"token_priced_attempt_count":27,"total":85.663355},"codegen_latency_ms":{"attempt_count":27,"max_ms":422464,"mean_ms":160017.42307692306,"min_ms":18406,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":422464,"mean_ms":390133.625,"min_ms":351613,"run_count":8},"medium":{"attempt_count":10,"max_ms":132971,"mean_ms":90177.0,"min_ms":75382,"run_count":9},"none":{"attempt_count":9,"max_ms":34692,"mean_ms":25310.11111111111,"min_ms":18406,"run_count":9}},"codegen_output_tokens":{"attempt_count":27,"output_max":428840,"output_mean":108480.34615384616,"output_min":1810,"run_count":26},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":428840,"output_mean":334016.875,"output_min":278832,"run_count":8},"medium":{"attempt_count":10,"output_max":20628,"output_mean":13803.555555555557,"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":56.46584925093118,"highest":55.18211184871696,"medium":45.624032402905684,"none":68.5914035011709},"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":"2026-07-26T05:19:00Z","match_totals_all":{"draws":52,"losses":61,"wins":75},"match_totals_tracks":{"highest":{"draws":16,"losses":29,"wins":29},"medium":{"draws":12,"losses":20,"wins":18},"none":{"draws":24,"losses":12,"wins":28}},"model_slug":"gpt-5-6-sol","overall":{"max":99.3611381452175,"mean":56.46584925093118,"min":7.823038137998366},"per_game":{"GB2-01":71.62104733589932,"GB2-02":99.3611381452175,"GB2-03":41.96959061824195,"GB2-04":82.29938502461472,"GB2-05":7.823038137998366,"GB2-06":58.25894415801768,"GB2-07":45.69698297081824,"GB2-08":34.42676839892792},"per_game_all":{"GB2-01":76.29594385602034,"GB2-02":86.19058589818376,"GB2-03":47.74181056792776,"GB2-04":68.94639395947173,"GB2-05":29.03873654788578,"GB2-06":53.39650569063011,"GB2-07":45.2398705220317,"GB2-08":44.876946965298266},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":10,"wins":18},"GB2-02":{"draws":18,"losses":5,"wins":11},"GB2-03":{"draws":5,"losses":11,"wins":10},"GB2-04":{"draws":17,"losses":3,"wins":6},"GB2-05":{"draws":0,"losses":9,"wins":5},"GB2-06":{"draws":2,"losses":10,"wins":10},"GB2-07":{"draws":0,"losses":8,"wins":10},"GB2-08":{"draws":8,"losses":5,"wins":5}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":5,"wins":5},"GB2-02":{"draws":3,"losses":3,"wins":8},"GB2-03":{"draws":2,"losses":6,"wins":4},"GB2-04":{"draws":7,"losses":1,"wins":4},"GB2-05":{"draws":0,"losses":4,"wins":0},"GB2-06":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":4,"wins":4},"GB2-08":{"draws":4,"losses":2,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":5,"wins":5},"GB2-02":{"draws":5,"losses":1,"wins":2},"GB2-03":{"draws":1,"losses":2,"wins":3},"GB2-04":{"draws":4,"losses":2,"wins":2},"GB2-05":{"draws":0,"losses":4,"wins":0},"GB2-06":{"draws":1,"losses":2,"wins":3},"GB2-07":{"draws":0,"losses":3,"wins":1},"GB2-08":{"draws":1,"losses":1,"wins":2}},"none":{"GB2-01":{"draws":2,"losses":0,"wins":8},"GB2-02":{"draws":10,"losses":1,"wins":1},"GB2-03":{"draws":2,"losses":3,"wins":3},"GB2-04":{"draws":6,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":1,"wins":5},"GB2-06":{"draws":1,"losses":4,"wins":3},"GB2-07":{"draws":0,"losses":1,"wins":5},"GB2-08":{"draws":3,"losses":2,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1544.6125519773977,"GB2-02":1527.5365849538575,"GB2-03":1495.948457476453,"GB2-04":1511.731745763934,"GB2-05":1479.9628272943262,"GB2-06":1508.1359986910982,"GB2-07":1507.663727428575,"GB2-08":1499.6439275127416},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1506.831230597087,"GB2-02":1571.288649242778,"GB2-03":1461.5448344468975,"GB2-04":1537.9186227575392,"GB2-05":1441.3630304436242,"GB2-06":1508.8445189622585,"GB2-07":1492.0645620814976,"GB2-08":1467.322915426663},"medium":{"GB2-01":1513.4882229298012,"GB2-02":1514.8738520950371,"GB2-03":1513.9631449032056,"GB2-04":1497.3838724472191,"GB2-05":1446.6320321381015,"GB2-06":1522.1275798307493,"GB2-07":1470.1336201642364,"GB2-08":1518.6171531836808},"none":{"GB2-01":1613.5182024053051,"GB2-02":1496.447253523757,"GB2-03":1512.3373930792568,"GB2-04":1499.892742087044,"GB2-05":1551.8934193012526,"GB2-06":1493.4358972802863,"GB2-07":1560.7930000399908,"GB2-08":1512.9917139278812}},"per_game_tracks":{"highest":{"GB2-01":71.62104733589932,"GB2-02":99.3611381452175,"GB2-03":41.96959061824195,"GB2-04":82.29938502461472,"GB2-05":7.823038137998366,"GB2-06":58.25894415801768,"GB2-07":45.69698297081824,"GB2-08":34.42676839892792},"medium":{"GB2-01":58.56346987680263,"GB2-02":66.0010431962754,"GB2-03":50.53101352785617,"GB2-04":63.85336770352967,"GB2-05":13.196018175424785,"GB2-06":48.55345146522425,"GB2-07":18.16344930167765,"GB2-08":46.13044597645492},"none":{"GB2-01":98.70331435535908,"GB2-02":93.20957635305837,"GB2-03":50.72482755768516,"GB2-04":60.68642915027083,"GB2-05":66.09715333023419,"GB2-06":53.37712144864839,"GB2-07":71.8591792935992,"GB2-08":54.07362652051197}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.18211184871696,"medium":45.62403240290568,"none":68.5914035011709},"reasoning_agg":{"highest":{"max":99.3611381452175,"mean":55.18211184871696,"min":7.823038137998366},"medium":{"max":66.0010431962754,"mean":45.62403240290568,"min":13.196018175424785},"none":{"max":98.70331435535908,"mean":68.5914035011709,"min":50.72482755768516}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":99.3611381452175,"expected_score":49.5578240957202,"reasoning_variance":22.967371098265225,"reliability_score":1.2448086648957428,"uncertainty_avg":98.75519133510426,"uncertainty_penalty":-6.908025155210979},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.3611381452175,"expected_score":37.887363224961675,"reliability_score":3.100057126725602,"uncertainty_avg":96.8999428732744,"uncertainty_penalty":-17.294748623755282},"medium":{"ceiling_score":66.0010431962754,"expected_score":47.43786099713576,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":1.8138285942300811},"none":{"ceiling_score":98.70331435535908,"expected_score":63.34824806506316,"reliability_score":0.634368867961598,"uncertainty_avg":99.3656311320384,"uncertainty_penalty":-5.243155436107742}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":20,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.14454373333333334,"mean":0.08818255,"median":0.07401653333333333,"min":0.052337466666666665,"recorded_attempt_count":37,"run_count":24,"total":2.1163812},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12366493333333332,"mean":0.09185773333333332,"median":0.09170913333333332,"min":0.04980146666666666,"recorded_attempt_count":39,"run_count":24,"total":2.2045855999999997},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","max":0.116343,"mean":0.07787519999999999,"median":0.0843883,"min":0.041110400000000005,"recorded_attempt_count":28,"run_count":16,"total":1.2460032}},"codegen_cost_usd":{"admitted_cell_count":59,"cell_count":24,"cost_basis_counts":{"provider_reported":104},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.14454373333333334,"mean":0.08597182777777779,"median":0.08538879999999999,"min":0.041110400000000005,"recorded_attempt_count":104,"run_count":64,"total":5.56697},"codegen_latency_ms":{"attempt_count":104,"max_ms":194096,"mean_ms":104338.484375,"min_ms":45373,"run_count":64},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":37,"max_ms":194096,"mean_ms":109560.20833333331,"min_ms":52667,"run_count":24},"medium":{"attempt_count":39,"max_ms":151974,"mean_ms":106852.375,"min_ms":48934,"run_count":24},"none":{"attempt_count":28,"max_ms":139814,"mean_ms":92735.0625,"min_ms":45373,"run_count":16}},"codegen_output_tokens":{"attempt_count":104,"output_max":26179,"output_mean":9948.484375,"output_min":3846,"run_count":64},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":37,"output_max":26179,"output_mean":10515.25,"output_min":4776,"run_count":24},"medium":{"attempt_count":39,"output_max":19479,"output_mean":10751.083333333334,"output_min":5204,"run_count":24},"none":{"attempt_count":28,"output_max":14459,"output_mean":7894.4375,"output_min":3846,"run_count":16}},"display_name":"Grok 4.5","economics":{"all":49.49898315093899,"highest":15.595542988301121,"medium":59.38932068715211,"none":79.04439629471989},"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":"2026-07-26T06:47:11Z","match_totals_all":{"draws":69,"losses":72,"wins":131},"match_totals_tracks":{"highest":{"draws":5,"losses":11,"wins":12},"medium":{"draws":45,"losses":54,"wins":81},"none":{"draws":19,"losses":7,"wins":38}},"model_slug":"x-ai-grok-4-5","overall":{"max":100.0,"mean":51.34308665672438,"min":5.240502637512705},"per_game":{"GB2-01":14.817715095058,"GB2-02":8.27642442699688,"GB2-03":12.695009622584724,"GB2-05":5.240502637512705,"GB2-06":9.478479160581506,"GB2-07":43.065126987072915},"per_game_all":{"GB2-01":46.72158704385895,"GB2-02":55.888487590654876,"GB2-03":37.02760795878796,"GB2-05":54.20492474967108,"GB2-06":37.538855159275066,"GB2-07":65.61243640338597},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":12,"wins":20},"GB2-02":{"draws":25,"losses":4,"wins":7},"GB2-03":{"draws":16,"losses":8,"wins":8},"GB2-04":{"draws":22,"losses":1,"wins":5},"GB2-05":{"draws":0,"losses":18,"wins":22},"GB2-06":{"draws":6,"losses":12,"wins":14},"GB2-07":{"draws":0,"losses":6,"wins":30},"GB2-08":{"draws":0,"losses":11,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":2},"GB2-02":{"draws":2,"losses":1,"wins":1},"GB2-03":{"draws":1,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":3,"wins":1},"GB2-06":{"draws":2,"losses":3,"wins":1},"GB2-07":{"draws":0,"losses":2,"wins":6}},"medium":{"GB2-01":{"draws":0,"losses":9,"wins":11},"GB2-02":{"draws":15,"losses":3,"wins":6},"GB2-03":{"draws":10,"losses":7,"wins":5},"GB2-04":{"draws":16,"losses":1,"wins":3},"GB2-05":{"draws":0,"losses":15,"wins":13},"GB2-06":{"draws":4,"losses":5,"wins":9},"GB2-07":{"draws":0,"losses":4,"wins":16},"GB2-08":{"draws":0,"losses":10,"wins":18}},"none":{"GB2-01":{"draws":0,"losses":1,"wins":7},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":1,"wins":2},"GB2-04":{"draws":6,"losses":0,"wins":2},"GB2-05":{"draws":0,"losses":0,"wins":8},"GB2-06":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":0,"wins":8},"GB2-08":{"draws":0,"losses":1,"wins":7}}},"per_game_raw_elo_all":{"GB2-01":1528.9902737336986,"GB2-02":1506.5150918092415,"GB2-03":1507.10245860375,"GB2-05":1531.8793579137655,"GB2-06":1502.8287348877548,"GB2-07":1563.105357815842},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1500.0,"GB2-02":1500.7347507644877,"GB2-03":1514.5304984710244,"GB2-05":1485.469480043168,"GB2-06":1490.205375850927,"GB2-07":1530.5397388828414},"medium":{"GB2-01":1511.6731975837345,"GB2-02":1518.8105246632372,"GB2-03":1492.407410276997,"GB2-04":1510.0804506709655,"GB2-05":1503.7831980569088,"GB2-06":1515.7150796553908,"GB2-07":1556.935465141435,"GB2-08":1539.6975715294964},"none":{"GB2-01":1575.297623617361,"GB2-02":1500.0,"GB2-03":1514.3694670632278,"GB2-04":1530.8668970290169,"GB2-05":1606.3853956412192,"GB2-06":1502.565749156946,"GB2-07":1601.8408694232498,"GB2-08":1579.7792894100853}},"per_game_tracks":{"highest":{"GB2-01":14.817715095058,"GB2-02":8.27642442699688,"GB2-03":12.695009622584724,"GB2-05":5.240502637512705,"GB2-06":9.478479160581506,"GB2-07":43.065126987072915},"medium":{"GB2-01":48.529814342908246,"GB2-02":81.26026790227202,"GB2-03":46.604741273379055,"GB2-04":62.20358759998041,"GB2-05":57.374271611500546,"GB2-06":44.99849161750772,"GB2-07":53.77218222308499,"GB2-08":80.37120892658383},"none":{"GB2-01":76.81723169361061,"GB2-02":78.12877044269572,"GB2-03":51.7830729804001,"GB2-04":87.35184953492146,"GB2-05":100.0,"GB2-06":58.13959469973598,"GB2-07":100.0,"GB2-08":80.13465100639527}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":15.59554298830112,"medium":59.389320687152114,"none":79.0443962947199},"reasoning_agg":{"highest":{"max":43.065126987072915,"mean":15.59554298830112,"min":5.240502637512705},"medium":{"max":81.26026790227202,"mean":59.389320687152114,"min":44.99849161750772},"none":{"max":100.0,"mean":79.0443962947199,"min":51.7830729804001}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":57.832547896076015,"reasoning_variance":63.44885330641878,"reliability_score":0.5532482955092064,"uncertainty_avg":99.4467517044908,"uncertainty_penalty":6.489461239351634},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":43.065126987072915,"expected_score":40.35788839797019,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":24.762345409669074},"medium":{"ceiling_score":81.26026790227202,"expected_score":61.22993168926083,"reliability_score":1.2448086648957428,"uncertainty_avg":98.75519133510426,"uncertainty_penalty":1.8406110021087159},"none":{"ceiling_score":100.0,"expected_score":77.01345379553194,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-2.030942499187958}}},{"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":0.06608082000000001},"codegen_latency_ms":{"attempt_count":45,"max_ms":490920,"mean_ms":93765.89285714286,"min_ms":17974,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":22,"max_ms":490920,"mean_ms":102055.21428571428,"min_ms":17974,"run_count":14},"none":{"attempt_count":23,"max_ms":199208,"mean_ms":85476.57142857143,"min_ms":34688,"run_count":14}},"codegen_output_tokens":{"attempt_count":45,"output_max":42038,"output_mean":6248.107142857143,"output_min":1564,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":22,"output_max":42038,"output_mean":7478.214285714285,"output_min":1564,"run_count":14},"none":{"attempt_count":23,"output_max":11735,"output_mean":5018.0,"output_min":1646,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"none":52.866637141874826},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.42857142857142855,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.42857142857142855}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-07-26T05:15:37Z","match_totals_all":{"draws":38,"losses":30,"wins":34},"match_totals_tracks":{"none":{"draws":38,"losses":30,"wins":34}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":60.9354619727948,"mean":51.10848673006848,"min":45.989420740830575},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":4,"wins":8},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":12,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":11,"wins":11},"GB2-06":{"draws":0,"losses":5,"wins":3},"GB2-07":{"draws":0,"losses":3,"wins":7},"GB2-08":{"draws":16,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":4,"losses":4,"wins":8},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":12,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":11,"wins":11},"GB2-06":{"draws":0,"losses":5,"wins":3},"GB2-07":{"draws":0,"losses":3,"wins":7},"GB2-08":{"draws":16,"losses":2,"wins":0}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1527.293584570779,"GB2-02":1501.3884841133663,"GB2-03":1495.203775108513,"GB2-05":1505.4655152099836,"GB2-06":1466.8971488519112,"GB2-07":1532.0592164729596,"GB2-08":1485.909615534699}},"per_game_tracks":{"none":{"GB2-01":56.19636281526691,"GB2-02":64.9502807462417,"GB2-03":50.947419099211174,"GB2-05":60.9354619727948,"GB2-06":39.53351465031776,"GB2-07":51.51399996846085,"GB2-08":45.98942074083058}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":51.10848673006848},"reasoning_agg":{"none":{"max":60.9354619727948,"mean":51.10848673006848,"min":45.989420740830575}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":60.9354619727948},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":60.9354619727948,"expected_score":51.08267017769892,"reliability_score":0.724992991956114,"uncertainty_avg":99.27500700804389,"uncertainty_penalty":-0.025816552369555268}}},{"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":0.633501456},"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":0.7838332079999999},"codegen_latency_ms":{"attempt_count":58,"max_ms":848935,"mean_ms":404316.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":33,"max_ms":848935,"mean_ms":690334.25,"min_ms":443841,"run_count":16},"none":{"attempt_count":25,"max_ms":266268,"mean_ms":118299.25,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":57,"output_max":40000,"output_mean":18334.0625,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":32,"output_max":40000,"output_mean":31078.25,"output_min":16796,"run_count":16},"none":{"attempt_count":25,"output_max":13510,"output_mean":5589.875,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"none":52.21144351330453},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.375}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-07-26T05:11:10Z","match_totals_all":{"draws":44,"losses":31,"wins":37},"match_totals_tracks":{"none":{"draws":44,"losses":31,"wins":37}},"model_slug":"meituan-longcat-2-0","overall":{"max":83.32268046567685,"mean":49.55588662477515,"min":37.27224276566582},"per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":4,"wins":7},"GB2-02":{"draws":4,"losses":0,"wins":0},"GB2-03":{"draws":18,"losses":5,"wins":5},"GB2-04":{"draws":4,"losses":2,"wins":2},"GB2-05":{"draws":0,"losses":6,"wins":6},"GB2-06":{"draws":0,"losses":3,"wins":11},"GB2-07":{"draws":0,"losses":8,"wins":6},"GB2-08":{"draws":11,"losses":3,"wins":0}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":7,"losses":4,"wins":7},"GB2-02":{"draws":4,"losses":0,"wins":0},"GB2-03":{"draws":18,"losses":5,"wins":5},"GB2-04":{"draws":4,"losses":2,"wins":2},"GB2-05":{"draws":0,"losses":6,"wins":6},"GB2-06":{"draws":0,"losses":3,"wins":11},"GB2-07":{"draws":0,"losses":8,"wins":6},"GB2-08":{"draws":11,"losses":3,"wins":0}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1510.1747654808723,"GB2-02":1500.0,"GB2-03":1493.893468693063,"GB2-04":1496.5232553078963,"GB2-05":1499.1817204627305,"GB2-06":1559.7689606505637,"GB2-07":1483.9254251136852,"GB2-08":1478.8603987361544}},"per_game_tracks":{"none":{"GB2-01":51.57663671108389,"GB2-02":41.66685508609087,"GB2-03":56.770903607889274,"GB2-04":68.5959369536977,"GB2-05":39.08746477420855,"GB2-06":83.32268046567685,"GB2-07":39.398827742123245,"GB2-08":37.27224276566582}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":49.55588662477515},"reasoning_agg":{"none":{"max":83.32268046567685,"mean":49.55588662477515,"min":37.27224276566582}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":83.32268046567685},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":83.32268046567685,"expected_score":51.38498235113954,"reliability_score":1.8313193908024346,"uncertainty_avg":98.16868060919757,"uncertainty_penalty":1.8290957263643932}}},{"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":67.27387000000002},"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":49.15125951534492,"highest":41.408803862845,"medium":43.95271471085361,"none":62.09225997233615},"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":"2026-07-26T05:18:50Z","match_totals_all":{"draws":69,"losses":60,"wins":51},"match_totals_tracks":{"highest":{"draws":10,"losses":26,"wins":20},"medium":{"draws":31,"losses":17,"wins":8},"none":{"draws":28,"losses":17,"wins":23}},"model_slug":"gpt-5-6-terra","overall":{"max":88.31746019814003,"mean":49.15125951534492,"min":6.673684019420697},"per_game":{"GB2-01":62.25903486028491,"GB2-02":44.20393397455431,"GB2-03":26.805513866933644,"GB2-04":35.26398545463592,"GB2-05":43.40818203739033,"GB2-06":32.48226686328385,"GB2-07":32.14911025699666,"GB2-08":54.69840358868034},"per_game_all":{"GB2-01":59.27913732082319,"GB2-02":59.85209591701882,"GB2-03":54.43225179314112,"GB2-04":59.87663307226713,"GB2-05":42.69994501887974,"GB2-06":35.3485309279388,"GB2-07":33.423200460557105,"GB2-08":48.298281612133444},"per_game_match_totals_all":{"GB2-01":{"draws":9,"losses":9,"wins":10},"GB2-02":{"draws":22,"losses":6,"wins":2},"GB2-03":{"draws":7,"losses":2,"wins":9},"GB2-04":{"draws":15,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":10,"wins":10},"GB2-06":{"draws":2,"losses":12,"wins":6},"GB2-07":{"draws":0,"losses":12,"wins":8},"GB2-08":{"draws":14,"losses":5,"wins":3}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":4,"wins":3},"GB2-02":{"draws":6,"losses":6,"wins":2},"GB2-03":{"draws":0,"losses":2,"wins":2},"GB2-04":{"draws":0,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":2,"wins":4},"GB2-06":{"draws":0,"losses":4,"wins":2},"GB2-07":{"draws":0,"losses":2,"wins":2},"GB2-08":{"draws":1,"losses":2,"wins":3}},"medium":{"GB2-01":{"draws":4,"losses":2,"wins":2},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":7,"losses":0,"wins":1},"GB2-04":{"draws":7,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-06":{"draws":2,"losses":4,"wins":0},"GB2-07":{"draws":0,"losses":4,"wins":0},"GB2-08":{"draws":5,"losses":3,"wins":0}},"none":{"GB2-01":{"draws":2,"losses":3,"wins":5},"GB2-02":{"draws":10,"losses":0,"wins":0},"GB2-03":{"draws":0,"losses":0,"wins":6},"GB2-04":{"draws":8,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":2},"GB2-06":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":6,"wins":6},"GB2-08":{"draws":8,"losses":0,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1508.9423586342773,"GB2-02":1483.752675527958,"GB2-03":1531.2065300137456,"GB2-04":1494.317002208715,"GB2-05":1500.0203094880064,"GB2-06":1467.3956920606652,"GB2-07":1478.832385704999,"GB2-08":1491.7375707127167},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1487.5204436380857,"GB2-02":1451.258026583874,"GB2-03":1494.777129497228,"GB2-04":1470.4626817300843,"GB2-05":1523.1830949187577,"GB2-06":1465.2700593410232,"GB2-07":1501.187120185032,"GB2-08":1513.0209495922652},"medium":{"GB2-01":1497.2627183372574,"GB2-02":1500.0,"GB2-03":1518.396994550828,"GB2-04":1512.48832489606,"GB2-05":1506.870451611897,"GB2-06":1440.4407419477154,"GB2-07":1436.5564692345683,"GB2-08":1462.4682143100013},"none":{"GB2-01":1542.0439139274883,"GB2-02":1500.0,"GB2-03":1580.4454659931812,"GB2-04":1500.0,"GB2-05":1470.007381933365,"GB2-06":1496.476274893257,"GB2-07":1498.753567695397,"GB2-08":1499.7235482358838}},"per_game_tracks":{"highest":{"GB2-01":62.25903486028491,"GB2-02":44.20393397455431,"GB2-03":26.805513866933644,"GB2-04":35.26398545463592,"GB2-05":43.40818203739033,"GB2-06":32.48226686328385,"GB2-07":32.14911025699666,"GB2-08":54.69840358868034},"medium":{"GB2-01":47.577936091374326,"GB2-02":47.03489357836214,"GB2-03":59.59474052087733,"GB2-04":73.87124049966715,"GB2-05":56.96883872877877,"GB2-06":18.600229447251525,"GB2-07":6.673684019420697,"GB2-08":41.30015480109701},"none":{"GB2-01":68.00044101081032,"GB2-02":88.31746019814003,"GB2-03":76.8965009916124,"GB2-04":70.4946732624983,"GB2-05":27.72281429047013,"GB2-06":54.963096473281034,"GB2-07":61.446807105253974,"GB2-08":48.89628644662298}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.40880386284499,"medium":43.95271471085363,"none":62.09225997233615},"reasoning_agg":{"highest":{"max":62.25903486028491,"mean":41.40880386284499,"min":26.805513866933644},"medium":{"max":73.87124049966715,"mean":43.95271471085363,"min":6.673684019420697},"none":{"max":88.31746019814003,"mean":62.09225997233615,"min":27.72281429047013}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":88.31746019814003,"expected_score":39.64901957206277,"reasoning_variance":20.68345610949116,"reliability_score":0.821896086254668,"uncertainty_avg":99.17810391374533,"uncertainty_penalty":-9.502239943282149},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.25903486028491,"expected_score":29.69631135186467,"reliability_score":1.8313193908024346,"uncertainty_avg":98.16868060919757,"uncertainty_penalty":-11.712492510980322},"medium":{"ceiling_score":73.87124049966715,"expected_score":33.23547251855438,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-10.717242192299246},"none":{"ceiling_score":88.31746019814003,"expected_score":56.01527484576927,"reliability_score":0.634368867961598,"uncertainty_avg":99.3656311320384,"uncertainty_penalty":-6.076985126566882}}},{"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":1.2846227784},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":37.23902225844053,"none":61.63057074818037},"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":"2026-07-26T04:31:37Z","match_totals_all":{"draws":23,"losses":14,"wins":25},"match_totals_tracks":{"medium":{"draws":0,"losses":0,"wins":6},"none":{"draws":23,"losses":14,"wins":19}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":77.27499314364869,"mean":46.977735160913845,"min":25.272783516280047},"per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":4,"wins":3},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":10,"losses":4,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":8},"GB2-06":{"draws":0,"losses":2,"wins":4},"GB2-07":{"draws":0,"losses":2,"wins":10}},"per_game_match_totals_tracks":{"medium":{"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":0,"wins":4}},"none":{"GB2-01":{"draws":5,"losses":4,"wins":3},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":10,"losses":4,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":6},"GB2-06":{"draws":0,"losses":2,"wins":4},"GB2-07":{"draws":0,"losses":2,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-05":1527.8739306203415,"GB2-07":1560.8487541064978},"none":{"GB2-01":1490.052051577521,"GB2-02":1498.9333705407796,"GB2-03":1447.7586655611296,"GB2-05":1551.3167529233426,"GB2-06":1529.4269304655472,"GB2-07":1545.146495516197}},"per_game_tracks":{"medium":{"GB2-05":25.272783516280047,"GB2-07":49.205261000601006},"none":{"GB2-01":49.8180747875321,"GB2-02":77.27499314364869,"GB2-03":32.74523100574487,"GB2-05":74.19312456626272,"GB2-06":62.83888385640988,"GB2-07":72.9131171294839}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.654815061916,"none":59.300655259911686},"reasoning_agg":{"medium":{"max":49.205261000601006,"mean":34.654815061916,"min":25.272783516280047},"none":{"max":77.27499314364869,"mean":59.300655259911686,"min":32.74523100574487}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":77.27499314364869,"reasoning_variance":24.64584019799569},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":49.205261000601006,"expected_score":69.56700286295377,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":34.912187801037774},"none":{"ceiling_score":77.27499314364869,"expected_score":56.51486417947558,"reliability_score":3.2875843450186863,"uncertainty_avg":96.71241565498131,"uncertainty_penalty":-2.7857910804361055}}},{"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":36.53971288154446,"none":57.019879024448564},"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":"2026-07-26T06:28:39Z","match_totals_all":{"draws":29,"losses":28,"wins":31},"match_totals_tracks":{"highest":{"draws":6,"losses":11,"wins":11},"none":{"draws":23,"losses":17,"wins":20}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":100.0,"mean":44.575924347942276,"min":0.0},"per_game":{"GB2-01":54.51495232871399,"GB2-04":50.41408923627391,"GB2-05":26.998682978937527,"GB2-06":25.54933224135539,"GB2-07":27.354571332191433,"GB2-08":34.40664917179452},"per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":3,"wins":2},"GB2-02":{"draws":9,"losses":0,"wins":1},"GB2-03":{"draws":2,"losses":9,"wins":1},"GB2-04":{"draws":0,"losses":1,"wins":3},"GB2-05":{"draws":0,"losses":10,"wins":10},"GB2-06":{"draws":1,"losses":1,"wins":6},"GB2-07":{"draws":0,"losses":2,"wins":8},"GB2-08":{"draws":12,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":0,"wins":2},"GB2-04":{"draws":0,"losses":1,"wins":3},"GB2-05":{"draws":0,"losses":6,"wins":2},"GB2-06":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":2,"wins":2},"GB2-08":{"draws":4,"losses":2,"wins":0}},"none":{"GB2-01":{"draws":3,"losses":3,"wins":0},"GB2-02":{"draws":9,"losses":0,"wins":1},"GB2-03":{"draws":2,"losses":9,"wins":1},"GB2-05":{"draws":0,"losses":4,"wins":8},"GB2-06":{"draws":1,"losses":1,"wins":4},"GB2-07":{"draws":0,"losses":0,"wins":6},"GB2-08":{"draws":8,"losses":0,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1529.8278203282016,"GB2-04":1532.853049011223,"GB2-05":1454.8274391689108,"GB2-06":1528.5029005001643,"GB2-07":1488.2948467146311,"GB2-08":1467.277560963625},"none":{"GB2-01":1456.7005783546986,"GB2-02":1514.5950719527063,"GB2-03":1392.5407932842982,"GB2-05":1544.462558099597,"GB2-06":1541.5472884572305,"GB2-07":1580.4445259032711,"GB2-08":1500.120683656794}},"per_game_tracks":{"highest":{"GB2-01":54.51495232871399,"GB2-04":50.41408923627391,"GB2-05":26.998682978937527,"GB2-06":25.54933224135539,"GB2-07":27.354571332191433,"GB2-08":34.40664917179452},"none":{"GB2-01":18.203262384714016,"GB2-02":100.0,"GB2-03":0.0,"GB2-05":81.47522885067282,"GB2-06":69.1613172878398,"GB2-07":81.24809291240497,"GB2-08":49.051251735508345}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.00403435776086,"none":55.1478143381237},"reasoning_agg":{"highest":{"max":54.51495232871399,"mean":34.00403435776086,"min":25.54933224135539},"none":{"max":100.0,"mean":55.1478143381237,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":21.143779980362844},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.51495232871399,"expected_score":37.44902306009635,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":3.4449887023354933},"none":{"ceiling_score":100.0,"expected_score":57.47394786740689,"reliability_score":1.4499859839122138,"uncertainty_avg":98.55001401608779,"uncertainty_penalty":2.32613352928319}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.213668025,"mean":0.180929025625,"median":0.1746528825,"min":0.16318875,"recorded_attempt_count":37,"run_count":16,"total":2.8948644100000003},"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.07934969,"mean":0.053583788125,"median":0.0553142075,"min":0.02549349,"recorded_attempt_count":37,"run_count":16,"total":0.85734061},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.053540475,"mean":0.026315053125,"median":0.024512850000000003,"min":0.012912625,"recorded_attempt_count":28,"run_count":16,"total":0.42104085}},"codegen_cost_usd":{"admitted_cell_count":28,"cell_count":24,"cost_basis_counts":{"provider_reported":102},"evidence_basis":"Provider-reported","failed_cell_count":20,"max":0.213668025,"mean":0.08694262229166666,"median":0.059337825,"min":0.012912625,"recorded_attempt_count":102,"run_count":48,"total":4.173245870000001},"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":{"medium":44.85999401221693,"none":52.55098121231353},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-06","GB2-08"],"model_code_failure_rate":0.3125,"model_code_failures":5,"repaired_admitted":11,"repaired_rate":0.6875},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.25,"model_code_failures":4,"repaired_admitted":5,"repaired_rate":0.3125}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-07-26T05:11:06Z","match_totals_all":{"draws":58,"losses":76,"wins":64},"match_totals_tracks":{"medium":{"draws":23,"losses":43,"wins":34},"none":{"draws":35,"losses":33,"wins":30}},"model_slug":"thinkingmachines-inkling","overall":{"max":79.12075981345919,"mean":44.527106732506496,"min":19.422709121800484},"per_game_match_totals_all":{"GB2-01":{"draws":13,"losses":24,"wins":7},"GB2-02":{"draws":9,"losses":0,"wins":1},"GB2-03":{"draws":12,"losses":4,"wins":10},"GB2-04":{"draws":23,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":18,"wins":12},"GB2-06":{"draws":0,"losses":10,"wins":6},"GB2-07":{"draws":0,"losses":15,"wins":15},"GB2-08":{"draws":1,"losses":2,"wins":11}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":10,"wins":6},"GB2-02":{"draws":4,"losses":0,"wins":0},"GB2-04":{"draws":17,"losses":1,"wins":2},"GB2-05":{"draws":0,"losses":11,"wins":9},"GB2-06":{"draws":0,"losses":7,"wins":1},"GB2-07":{"draws":0,"losses":12,"wins":14},"GB2-08":{"draws":0,"losses":2,"wins":2}},"none":{"GB2-01":{"draws":11,"losses":14,"wins":1},"GB2-02":{"draws":5,"losses":0,"wins":1},"GB2-03":{"draws":12,"losses":4,"wins":10},"GB2-04":{"draws":6,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":7,"wins":3},"GB2-06":{"draws":0,"losses":3,"wins":5},"GB2-07":{"draws":0,"losses":3,"wins":1},"GB2-08":{"draws":1,"losses":0,"wins":9}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1476.2003944006829,"GB2-02":1500.491089088295,"GB2-04":1506.345745212221,"GB2-05":1478.193586989465,"GB2-06":1411.0738932905365,"GB2-07":1518.5715766614346,"GB2-08":1504.0300810129856},"none":{"GB2-01":1420.3593504187047,"GB2-02":1514.4240184842015,"GB2-03":1540.6405615671874,"GB2-04":1487.410066529168,"GB2-05":1466.1458206720115,"GB2-06":1528.9567108426024,"GB2-07":1468.0307168267104,"GB2-08":1617.9601769139642}},"per_game_tracks":{"medium":{"GB2-01":42.00140465536613,"GB2-02":31.266490413278632,"GB2-04":77.22329871496011,"GB2-05":50.37002496806187,"GB2-06":14.378090697803776,"GB2-07":59.29934012212921,"GB2-08":39.4813085139188},"none":{"GB2-01":21.525848382531617,"GB2-02":75.38449783124601,"GB2-03":79.12075981345919,"GB2-04":38.74186739504911,"GB2-05":19.422709121800484,"GB2-06":71.90611038875046,"GB2-07":14.306056765671352,"GB2-08":100.0}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":52.10659842163039,"none":36.94761504338259},"reasoning_agg":{"medium":{"max":77.22329871496011,"mean":52.10659842163039,"min":42.00140465536613},"none":{"max":79.12075981345919,"mean":36.94761504338259,"min":19.422709121800484}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":79.12075981345919,"reasoning_variance":15.158983378247797},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":77.22329871496011,"expected_score":38.305718207127654,"reliability_score":1.7714612152717848,"uncertainty_avg":98.22853878472822,"uncertainty_penalty":-13.800880214502733},"none":{"ceiling_score":79.12075981345919,"expected_score":59.333899650837274,"reliability_score":2.4656882587640183,"uncertainty_avg":97.53431174123598,"uncertainty_penalty":22.386284607454684}}},{"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":3.542855},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566349999999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":45.9941907150673,"highest":43.37230218934159,"medium":32.52838190333569,"none":57.488236385910376},"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":"2026-07-26T05:15:11Z","match_totals_all":{"draws":55,"losses":33,"wins":50},"match_totals_tracks":{"highest":{"draws":4,"losses":13,"wins":23},"medium":{"draws":12,"losses":8,"wins":14},"none":{"draws":39,"losses":12,"wins":13}},"model_slug":"gpt-5-5","overall":{"max":100.0,"mean":43.359162823432236,"min":0.0},"per_game":{"GB2-01":100.0,"GB2-03":6.347504811292362,"GB2-04":0.0,"GB2-05":52.772081820663296,"GB2-06":14.791384532630431,"GB2-07":67.29608626609144,"GB2-08":62.39905789471359},"per_game_all":{"GB2-01":65.53795320278009,"GB2-03":33.82213276939447,"GB2-04":15.489779810817295,"GB2-05":60.82924125373692,"GB2-07":59.56532810215759,"GB2-08":40.720709151517376},"per_game_match_totals_all":{"GB2-01":{"draws":14,"losses":1,"wins":9},"GB2-02":{"draws":12,"losses":1,"wins":1},"GB2-03":{"draws":10,"losses":5,"wins":5},"GB2-04":{"draws":6,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":9,"wins":15},"GB2-06":{"draws":0,"losses":3,"wins":1},"GB2-07":{"draws":0,"losses":7,"wins":15},"GB2-08":{"draws":13,"losses":5,"wins":4}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":1,"wins":7},"GB2-03":{"draws":2,"losses":0,"wins":0},"GB2-04":{"draws":0,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":5},"GB2-06":{"draws":0,"losses":1,"wins":1},"GB2-07":{"draws":0,"losses":2,"wins":6},"GB2-08":{"draws":2,"losses":4,"wins":4}},"medium":{"GB2-01":{"draws":2,"losses":0,"wins":2},"GB2-02":{"draws":4,"losses":1,"wins":1},"GB2-03":{"draws":2,"losses":0,"wins":2},"GB2-04":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":6},"GB2-06":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":3,"wins":3},"GB2-08":{"draws":2,"losses":0,"wins":0}},"none":{"GB2-01":{"draws":12,"losses":0,"wins":0},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":5,"wins":3},"GB2-04":{"draws":4,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":2,"wins":6},"GB2-08":{"draws":9,"losses":1,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1535.8694969248609,"GB2-03":1503.2415791313324,"GB2-04":1489.8231671763251,"GB2-05":1531.4463825388896,"GB2-07":1531.957500081051,"GB2-08":1493.1944827230698},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1578.0965758468692,"GB2-03":1500.0,"GB2-04":1469.4695015289756,"GB2-05":1534.1497334474177,"GB2-06":1502.866254736599,"GB2-07":1550.1434620060425,"GB2-08":1499.7991643052028},"medium":{"GB2-01":1529.675327133244,"GB2-02":1497.5726454334863,"GB2-03":1530.5361225264053,"GB2-04":1500.0,"GB2-05":1550.3360440806064,"GB2-06":1472.0102622777906,"GB2-07":1497.4443863231063,"GB2-08":1496.4007386034534},"none":{"GB2-01":1499.8365877944696,"GB2-02":1498.5950719527063,"GB2-03":1479.1886148675924,"GB2-04":1500.0,"GB2-05":1509.853370088645,"GB2-07":1548.2846519140037,"GB2-08":1483.383545260553}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-03":6.347504811292362,"GB2-04":0.0,"GB2-05":52.772081820663296,"GB2-06":14.791384532630431,"GB2-07":67.29608626609144,"GB2-08":62.39905789471359},"medium":{"GB2-01":42.59268769872406,"GB2-02":45.62814858491845,"GB2-03":46.00585292708215,"GB2-04":0.8517978296460202,"GB2-05":74.9535456884988,"GB2-06":0.9316552430733096,"GB2-07":36.98746327285279,"GB2-08":12.275903981889948},"none":{"GB2-01":54.021171909616186,"GB2-02":77.00420402161589,"GB2-03":49.11304056980891,"GB2-04":45.617541602805865,"GB2-05":54.76209625204864,"GB2-07":74.41243476752854,"GB2-08":47.48716557794859}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.948311877849314,"medium":32.52838190333569,"none":55.600794689111716},"reasoning_agg":{"highest":{"max":100.0,"mean":41.948311877849314,"min":0.0},"medium":{"max":74.9535456884988,"mean":32.52838190333569,"min":0.8517978296460202},"none":{"max":77.00420402161589,"mean":55.600794689111716,"min":45.617541602805865}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":51.16363165366133,"reasoning_variance":23.072412785776024,"reliability_score":1.0958614483395621,"uncertainty_avg":98.90413855166044,"uncertainty_penalty":7.804468830229091},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":50.66194917408762,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":8.713637296238304},"medium":{"ceiling_score":74.9535456884988,"expected_score":49.650592974694405,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":17.122211071358713},"none":{"ceiling_score":77.00420402161589,"expected_score":49.49520666881015,"reliability_score":2.8179294385874556,"uncertainty_avg":97.18207056141254,"uncertainty_penalty":-6.1055880203015676}}},{"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":22.978848600000003},"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":49.48707706565849,"highest":36.52002128575301,"medium":23.495760321489755,"none":72.74607071959099},"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":"2026-07-24T08:37:40Z","match_totals_all":{"draws":38,"losses":21,"wins":59},"match_totals_tracks":{"highest":{"draws":8,"losses":8,"wins":16},"medium":{"draws":10,"losses":2,"wins":10},"none":{"draws":20,"losses":11,"wins":33}},"model_slug":"moonshotai-kimi-k3","overall":{"max":100.0,"mean":43.26354160132316,"min":0.0},"per_game":{"GB2-01":30.9270397564896,"GB2-02":41.899831320349506,"GB2-05":31.1829174342122,"GB2-07":42.07029663196073},"per_game_all":{"GB2-01":49.50426479535522,"GB2-02":58.50729961892233,"GB2-05":43.191048953537056,"GB2-07":46.74569489481936},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":3,"wins":11},"GB2-02":{"draws":20,"losses":1,"wins":3},"GB2-03":{"draws":5,"losses":1,"wins":4},"GB2-04":{"draws":5,"losses":2,"wins":3},"GB2-05":{"draws":0,"losses":5,"wins":13},"GB2-06":{"draws":0,"losses":1,"wins":9},"GB2-07":{"draws":0,"losses":4,"wins":14},"GB2-08":{"draws":4,"losses":4,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":2,"wins":3},"GB2-02":{"draws":7,"losses":1,"wins":2},"GB2-05":{"draws":0,"losses":3,"wins":5},"GB2-07":{"draws":0,"losses":2,"wins":6}},"medium":{"GB2-01":{"draws":2,"losses":0,"wins":2},"GB2-02":{"draws":5,"losses":0,"wins":1},"GB2-03":{"draws":1,"losses":0,"wins":1},"GB2-04":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-06":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":0,"wins":2},"GB2-08":{"draws":0,"losses":2,"wins":0}},"none":{"GB2-01":{"draws":1,"losses":1,"wins":6},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":4,"losses":1,"wins":3},"GB2-04":{"draws":3,"losses":2,"wins":3},"GB2-05":{"draws":0,"losses":2,"wins":6},"GB2-06":{"draws":0,"losses":1,"wins":7},"GB2-07":{"draws":0,"losses":2,"wins":6},"GB2-08":{"draws":4,"losses":2,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1536.0090754630721,"GB2-02":1507.5316906509022,"GB2-05":1530.154534649588,"GB2-07":1537.4690121365613},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1507.2009628530575,"GB2-02":1508.0,"GB2-05":1513.2572820021278,"GB2-07":1527.8646902085245},"medium":{"GB2-01":1530.5304984710244,"GB2-02":1514.5950719527063,"GB2-03":1516.0,"GB2-04":1500.0,"GB2-05":1530.5304984710244,"GB2-06":1530.5304984710244,"GB2-07":1530.5304984710244,"GB2-08":1469.4695015289756},"none":{"GB2-01":1570.2957650651342,"GB2-02":1500.0,"GB2-03":1526.1105732388585,"GB2-04":1507.4441984450789,"GB2-05":1546.6758234756114,"GB2-06":1582.8138218996285,"GB2-07":1554.0118477301348,"GB2-08":1496.264637804127}},"per_game_tracks":{"highest":{"GB2-01":30.9270397564896,"GB2-02":41.899831320349506,"GB2-05":31.1829174342122,"GB2-07":42.07029663196073},"medium":{"GB2-01":42.917147747586114,"GB2-02":55.49329709372177,"GB2-03":18.92371683814101,"GB2-04":0.8517978296460202,"GB2-05":26.3719884643672,"GB2-06":22.39006485552579,"GB2-07":21.018069742930145,"GB2-08":0.0},"none":{"GB2-01":74.66860688198996,"GB2-02":78.12877044269572,"GB2-03":57.89750186733002,"GB2-04":74.5601342408928,"GB2-05":72.01824096203177,"GB2-06":100.0,"GB2-07":77.1487183095672,"GB2-08":47.54659305222047}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.32916064572464,"medium":22.71539343865386,"none":72.74607071959099},"reasoning_agg":{"highest":{"max":42.07029663196073,"mean":34.32916064572464,"min":30.9270397564896},"medium":{"max":55.49329709372177,"mean":22.71539343865386,"min":0.0},"none":{"max":100.0,"mean":72.74607071959099,"min":47.54659305222047}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":62.15609189121233,"reasoning_variance":50.03067728093713,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":18.892550289889165},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.07029663196073,"expected_score":49.89140583340638,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":15.56224518768174},"medium":{"ceiling_score":55.49329709372177,"expected_score":52.43688393863654,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":29.721490499982682},"none":{"ceiling_score":100.0,"expected_score":67.8046338160533,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-4.941436903537692}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":34,"run_count":15,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":29,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"provider_reported":63},"evidence_basis":"Provider-reported","failed_cell_count":14,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":63,"run_count":31,"total":0.0},"codegen_latency_ms":{"attempt_count":64,"max_ms":235183,"mean_ms":106145.67741935483,"min_ms":16415,"run_count":31},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":235183,"mean_ms":183971.06666666668,"min_ms":161500,"run_count":15},"none":{"attempt_count":29,"max_ms":62224,"mean_ms":33184.375,"min_ms":16415,"run_count":16}},"codegen_output_tokens":{"attempt_count":63,"output_max":52074,"output_mean":22315.225806451617,"output_min":1505,"run_count":31},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":34,"output_max":52074,"output_mean":40986.933333333334,"output_min":20000,"run_count":15},"none":{"attempt_count":29,"output_max":10355,"output_mean":4810.5,"output_min":1505,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"none":52.25025183547791},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":10,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":6,"first_pass_rate":0.375,"model_code_failure_rate":0.375,"model_code_failures":6,"repaired_admitted":4,"repaired_rate":0.25}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-07-26T04:32:16Z","match_totals_all":{"draws":39,"losses":39,"wins":26},"match_totals_tracks":{"none":{"draws":39,"losses":39,"wins":26}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":68.63526718212648,"mean":42.931921916617426,"min":40.43765192244375},"per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":6,"wins":11},"GB2-02":{"draws":5,"losses":1,"wins":0},"GB2-03":{"draws":8,"losses":15,"wins":7},"GB2-04":{"draws":5,"losses":0,"wins":1},"GB2-06":{"draws":0,"losses":13,"wins":7},"GB2-08":{"draws":14,"losses":4,"wins":0}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":7,"losses":6,"wins":11},"GB2-02":{"draws":5,"losses":1,"wins":0},"GB2-03":{"draws":8,"losses":15,"wins":7},"GB2-04":{"draws":5,"losses":0,"wins":1},"GB2-06":{"draws":0,"losses":13,"wins":7},"GB2-08":{"draws":14,"losses":4,"wins":0}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1533.8572493015513,"GB2-02":1485.5924254497254,"GB2-03":1459.397225499314,"GB2-04":1513.3869352166955,"GB2-06":1458.6016859587244,"GB2-08":1476.2498972721646}},"per_game_tracks":{"none":{"GB2-01":68.63526718212648,"GB2-02":52.3064181706765,"GB2-03":40.43765192244375,"GB2-04":68.05594193371711,"GB2-06":41.84610725849672,"GB2-08":42.22012454540691}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":42.931921916617426},"reasoning_agg":{"none":{"max":68.63526718212648,"mean":42.931921916617426,"min":40.43765192244375}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":68.63526718212648},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":68.63526718212648,"expected_score":37.33815736315709,"reliability_score":3.9402203746365245,"uncertainty_avg":96.05977962536348,"uncertainty_penalty":-5.593764553460339}}},{"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":38.32728584401388,"none":51.01437321088952},"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":"2026-07-24T08:34:37Z","match_totals_all":{"draws":16,"losses":21,"wins":21},"match_totals_tracks":{"medium":{"draws":0,"losses":3,"wins":5},"none":{"draws":16,"losses":18,"wins":16}},"model_slug":"google-gemma-4-31b-it","overall":{"max":68.7156083808307,"mean":41.204570224505346,"min":29.298800729002252},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":6,"wins":3},"GB2-04":{"draws":5,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":6,"wins":6},"GB2-06":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":5,"wins":7},"GB2-08":{"draws":8,"losses":0,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-05":{"draws":0,"losses":1,"wins":3},"GB2-07":{"draws":0,"losses":2,"wins":2}},"none":{"GB2-01":{"draws":3,"losses":6,"wins":3},"GB2-04":{"draws":5,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":5,"wins":3},"GB2-06":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":3,"wins":5},"GB2-08":{"draws":8,"losses":0,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-05":1529.1896126785723,"GB2-07":1502.6750486743172},"none":{"GB2-01":1462.627075398662,"GB2-04":1514.594839551769,"GB2-05":1462.1445527352714,"GB2-06":1503.0016716830082,"GB2-07":1518.6932236665784,"GB2-08":1498.163619535671}},"per_game_tracks":{"medium":{"GB2-05":47.355770959025506,"GB2-07":29.298800729002252},"none":{"GB2-01":38.03725698536375,"GB2-04":68.7156083808307,"GB2-05":32.404263449865645,"GB2-06":58.366988243241835,"GB2-07":60.27453190924189,"GB2-08":48.28759029679328}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.32334224278927,"none":49.08579820622142},"reasoning_agg":{"medium":{"max":47.355770959025506,"mean":33.32334224278927,"min":29.298800729002252},"none":{"max":68.7156083808307,"mean":49.08579820622142,"min":32.404263449865645}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":68.7156083808307,"reasoning_variance":15.762455963432146},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.355770959025506,"expected_score":54.37304093654688,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":21.049698693757605},"none":{"ceiling_score":68.7156083808307,"expected_score":47.0503847873888,"reliability_score":0.8458251572821354,"uncertainty_avg":99.15417484271786,"uncertainty_penalty":-2.0354134188326185}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","max":0.04815395,"mean":0.0408814375,"median":0.040641,"min":0.0341807,"recorded_attempt_count":34,"run_count":16,"total":0.654103},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","max":0.03261155,"mean":0.02559155625,"median":0.02516155,"min":0.017927,"recorded_attempt_count":32,"run_count":16,"total":0.4094649},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0148808,"mean":0.0114004875,"median":0.01124825,"min":0.00845595,"recorded_attempt_count":23,"run_count":16,"total":0.1824078}},"codegen_cost_usd":{"admitted_cell_count":47,"cell_count":24,"cost_basis_counts":{"provider_reported":89},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.04815395,"mean":0.025957827083333333,"median":0.02516155,"min":0.00845595,"recorded_attempt_count":89,"run_count":48,"total":1.2459757000000002},"codegen_latency_ms":{"attempt_count":89,"max_ms":61871,"mean_ms":33706.5625,"min_ms":13028,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":34,"max_ms":61871,"mean_ms":50306.25,"min_ms":38302,"run_count":16},"medium":{"attempt_count":32,"max_ms":47168,"mean_ms":32849.5625,"min_ms":19840,"run_count":16},"none":{"attempt_count":23,"max_ms":28160,"mean_ms":17963.875,"min_ms":13028,"run_count":16}},"codegen_output_tokens":{"attempt_count":89,"output_max":18224,"output_mean":8477.208333333334,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":34,"output_max":18224,"output_mean":14154.25,"output_min":11410,"run_count":16},"medium":{"attempt_count":32,"output_max":11113,"output_mean":8141.625,"output_min":4066,"run_count":16},"none":{"attempt_count":23,"output_max":4635,"output_mean":3135.75,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"medium":39.64017570226612},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":1,"first_pass_rate":0.0625,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":15,"repaired_rate":0.9375}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-07-26T04:34:17Z","match_totals_all":{"draws":32,"losses":67,"wins":31},"match_totals_tracks":{"medium":{"draws":32,"losses":67,"wins":31}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":62.67657685465536,"mean":39.64017570226612,"min":16.111729191242272},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":10,"wins":12},"GB2-02":{"draws":14,"losses":2,"wins":0},"GB2-03":{"draws":5,"losses":8,"wins":5},"GB2-04":{"draws":11,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":14,"wins":4},"GB2-06":{"draws":0,"losses":13,"wins":5},"GB2-07":{"draws":0,"losses":15,"wins":3},"GB2-08":{"draws":2,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":10,"wins":12},"GB2-02":{"draws":14,"losses":2,"wins":0},"GB2-03":{"draws":5,"losses":8,"wins":5},"GB2-04":{"draws":11,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":14,"wins":4},"GB2-06":{"draws":0,"losses":13,"wins":5},"GB2-07":{"draws":0,"losses":15,"wins":3},"GB2-08":{"draws":2,"losses":2,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1513.923044125282,"GB2-02":1485.008082955302,"GB2-03":1475.206998054715,"GB2-04":1495.6095654879705,"GB2-05":1430.625154228144,"GB2-06":1452.8710525902393,"GB2-07":1412.2212669680532,"GB2-08":1470.8744295762692}},"per_game_tracks":{"medium":{"GB2-01":60.561845959539106,"GB2-02":48.692685450659056,"GB2-03":44.61795699298699,"GB2-04":62.67657685465536,"GB2-05":28.05430126148497,"GB2-06":32.03814277547159,"GB2-07":16.111729191242272,"GB2-08":24.368167132089653}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.64017570226612},"reasoning_agg":{"medium":{"max":62.67657685465536,"mean":39.64017570226612,"min":16.111729191242272}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":62.67657685465536},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":62.67657685465536,"expected_score":19.644128886202292,"reliability_score":0.317184433980799,"uncertainty_avg":99.6828155660192,"uncertainty_penalty":-19.996046816063828}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":46},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.02904086,"mean":0.020196066154166664,"median":0.0210709803,"min":0.0085050301,"recorded_attempt_count":46,"run_count":21,"total":0.426437947},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.004834030033333333,"mean":0.0027724950333333333,"median":0.002243999216666667,"min":0.00169122,"recorded_attempt_count":35,"run_count":24,"total":0.0665398808}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":16,"cost_basis_counts":{"provider_reported":81},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.02904086,"mean":0.01148428059375,"median":0.006669530066666667,"min":0.00169122,"recorded_attempt_count":81,"run_count":45,"total":0.4929778278},"codegen_latency_ms":{"attempt_count":81,"max_ms":2511116,"mean_ms":633843.1555555556,"min_ms":19112,"run_count":45},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":46,"max_ms":2511116,"mean_ms":1185686.761904762,"min_ms":46510,"run_count":21},"none":{"attempt_count":35,"max_ms":1132276,"mean_ms":150980.0,"min_ms":19112,"run_count":24}},"codegen_output_tokens":{"attempt_count":79,"output_max":146589,"output_mean":36322.91111111111,"output_min":1540,"run_count":45},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":46,"output_max":146589,"output_mean":73252.28571428571,"output_min":6076,"run_count":21},"none":{"attempt_count":33,"output_max":23326,"output_mean":4009.7083333333335,"output_min":1540,"run_count":24}},"display_name":"MiMo-V2.5","economics":{"medium":22.04592389727963,"none":58.64096245506405},"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":"2026-07-26T04:30:14Z","match_totals_all":{"draws":53,"losses":52,"wins":63},"match_totals_tracks":{"medium":{"draws":9,"losses":12,"wins":9},"none":{"draws":44,"losses":40,"wins":54}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":82.8603391562924,"mean":37.95335165138156,"min":18.106525687358957},"per_game_match_totals_all":{"GB2-01":{"draws":8,"losses":11,"wins":9},"GB2-02":{"draws":17,"losses":1,"wins":0},"GB2-03":{"draws":6,"losses":2,"wins":2},"GB2-04":{"draws":14,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":14,"wins":18},"GB2-06":{"draws":0,"losses":9,"wins":19},"GB2-07":{"draws":0,"losses":15,"wins":15},"GB2-08":{"draws":8,"losses":0,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":3,"wins":3},"GB2-02":{"draws":9,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":4},"GB2-07":{"draws":0,"losses":6,"wins":2}},"none":{"GB2-01":{"draws":8,"losses":8,"wins":6},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":2,"wins":2},"GB2-04":{"draws":14,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":12,"wins":14},"GB2-06":{"draws":0,"losses":9,"wins":19},"GB2-07":{"draws":0,"losses":9,"wins":13},"GB2-08":{"draws":8,"losses":0,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1500.7347507644877,"GB2-02":1495.1349760157646,"GB2-05":1515.2652492355123,"GB2-07":1468.2380986095925},"none":{"GB2-01":1488.0770214857585,"GB2-02":1499.7738292764243,"GB2-03":1501.800654125993,"GB2-04":1501.0244056611514,"GB2-05":1510.4504829986288,"GB2-06":1541.470542248405,"GB2-07":1527.1383108394546,"GB2-08":1498.1681974417588}},"per_game_tracks":{"medium":{"GB2-01":21.737345224533023,"GB2-02":18.106525687358957,"GB2-05":30.82500389665052,"GB2-07":17.51482078057601},"none":{"GB2-01":36.060374583248496,"GB2-02":77.94773341261133,"GB2-03":51.86638727823251,"GB2-04":66.1792925871612,"GB2-05":55.75124781304091,"GB2-06":82.8603391562924,"GB2-07":72.69948701485589,"GB2-08":25.762837795069625}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.49193331864001,"none":53.41476998412311},"reasoning_agg":{"medium":{"max":30.82500389665052,"mean":22.49193331864001,"min":18.106525687358957},"none":{"max":82.8603391562924,"mean":53.41476998412311,"min":36.060374583248496}},"reasoning_labels":{"highest":"Highest","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":82.8603391562924,"reasoning_variance":30.9228366654831},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":30.82500389665052,"expected_score":43.28864119604691,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":20.7967078774069},"none":{"ceiling_score":82.8603391562924,"expected_score":54.472166953687484,"reliability_score":0.5286407233013222,"uncertainty_avg":99.47135927669868,"uncertainty_penalty":1.0573969695643726}}},{"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":4.709264999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.1968175,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.29615479166666664,"median":0.1968175,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-07-25":8},"run_count":24,"token_priced_attempt_count":24,"total":7.107714999999999},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333331,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"all":35.07957373334167,"highest":37.8825325873403,"medium":22.55752307374045,"none":52.30410163451241},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-07-26T06:47:11Z","match_totals_all":{"draws":43,"losses":34,"wins":35},"match_totals_tracks":{"highest":{"draws":8,"losses":9,"wins":11},"medium":{"draws":13,"losses":8,"wins":5},"none":{"draws":22,"losses":17,"wins":19}},"model_slug":"claude-opus-4-5","overall":{"max":100.0,"mean":37.581385765197716,"min":0.0},"per_game":{"GB2-01":82.39209479201158,"GB2-02":37.88116184510312,"GB2-03":0.0,"GB2-05":26.833585674632385,"GB2-06":59.38645141084554,"GB2-07":20.80190180144918},"per_game_all":{"GB2-01":49.359628872065514,"GB2-02":49.584977399719975,"GB2-03":22.469682400560533,"GB2-05":29.894769811956124,"GB2-06":36.146590866796224,"GB2-07":23.02179304895161},"per_game_match_totals_all":{"GB2-01":{"draws":8,"losses":5,"wins":7},"GB2-02":{"draws":17,"losses":1,"wins":0},"GB2-03":{"draws":8,"losses":2,"wins":2},"GB2-04":{"draws":8,"losses":1,"wins":5},"GB2-05":{"draws":0,"losses":7,"wins":7},"GB2-06":{"draws":2,"losses":8,"wins":6},"GB2-07":{"draws":0,"losses":9,"wins":5},"GB2-08":{"draws":0,"losses":1,"wins":3}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":1,"wins":5},"GB2-02":{"draws":5,"losses":1,"wins":0},"GB2-03":{"draws":1,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":2},"GB2-06":{"draws":2,"losses":1,"wins":3},"GB2-07":{"draws":0,"losses":3,"wins":1}},"medium":{"GB2-01":{"draws":2,"losses":0,"wins":2},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":1,"losses":1,"wins":0},"GB2-04":{"draws":4,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":2,"wins":0},"GB2-06":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":0},"GB2-08":{"draws":0,"losses":0,"wins":2}},"none":{"GB2-01":{"draws":6,"losses":4,"wins":0},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":0,"wins":2},"GB2-04":{"draws":4,"losses":0,"wins":4},"GB2-05":{"draws":0,"losses":3,"wins":5},"GB2-06":{"draws":0,"losses":5,"wins":3},"GB2-07":{"draws":0,"losses":4,"wins":4},"GB2-08":{"draws":0,"losses":1,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1508.9699047711736,"GB2-02":1495.1349760157646,"GB2-03":1500.8322890120073,"GB2-05":1498.0308448852513,"GB2-06":1494.6667910222284,"GB2-07":1477.813080755105},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1559.6296498373777,"GB2-02":1485.4049280472937,"GB2-03":1485.4695015289756,"GB2-05":1499.8714272350912,"GB2-06":1529.3838724472191,"GB2-07":1470.6750486743172},"medium":{"GB2-01":1530.5304984710244,"GB2-02":1500.0,"GB2-03":1484.0,"GB2-04":1502.694512383252,"GB2-05":1469.4695015289756,"GB2-06":1469.4695015289756,"GB2-07":1469.4695015289756,"GB2-08":1530.5304984710244},"none":{"GB2-01":1436.749566005118,"GB2-02":1500.0,"GB2-03":1533.0273655070466,"GB2-04":1554.0267164260392,"GB2-05":1524.7516058916876,"GB2-06":1485.1469990904898,"GB2-07":1493.2946920620216,"GB2-08":1501.2055471453416}},"per_game_tracks":{"highest":{"GB2-01":82.39209479201158,"GB2-02":37.88116184510312,"GB2-03":0.0,"GB2-05":26.833585674632385,"GB2-06":59.38645141084554,"GB2-07":20.80190180144918},"medium":{"GB2-01":42.917147747586114,"GB2-02":47.03489357836214,"GB2-03":5.9094797523808555,"GB2-04":55.53513722889381,"GB2-05":1.1068517366976147,"GB2-06":0.0,"GB2-07":0.12360718908514348,"GB2-08":27.83306735691794},"none":{"GB2-01":22.769644076598837,"GB2-02":63.83887677569468,"GB2-03":61.49956744930075,"GB2-04":100.0,"GB2-05":61.74387202453837,"GB2-06":49.05332118954312,"GB2-07":48.13987015632052,"GB2-08":11.38766140410304}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.8825325873403,"medium":22.55752307374045,"none":52.304101634512406},"reasoning_agg":{"highest":{"max":82.39209479201158,"mean":37.8825325873403,"min":0.0},"medium":{"max":55.53513722889381,"mean":22.55752307374045,"min":0.0},"none":{"max":100.0,"mean":52.304101634512406,"min":11.38766140410304}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":43.73380817403039,"reasoning_variance":29.746578560771955,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":6.1524224088326775},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.39209479201158,"expected_score":43.52439088287229,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":5.641858295531989},"medium":{"ceiling_score":55.53513722889381,"expected_score":43.641722119652385,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":21.084199045911934},"none":{"ceiling_score":100.0,"expected_score":54.92726848329775,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":2.6231668487853455}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.38568888333333334,"mean":0.29249454166666666,"median":0.2834616125,"min":0.2238526,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":25},"run_count":17,"token_priced_attempt_count":25,"total":5.07700365},"medium":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":49},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":0.0362005625,"mean":0.024352715625,"median":0.02520601875,"min":0.016582062499999998,"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":0.02520601875,"min":0.005806287500000001,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":130},"run_count":81,"token_priced_attempt_count":130,"total":6.144237299999999},"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":38.03503839494704,"highest":30.940100665563623,"medium":30.77690160601426,"none":48.24646781834065},"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":"2026-07-26T06:28:39Z","match_totals_all":{"draws":129,"losses":151,"wins":118},"match_totals_tracks":{"highest":{"draws":22,"losses":33,"wins":15},"medium":{"draws":40,"losses":54,"wins":44},"none":{"draws":67,"losses":64,"wins":59}},"model_slug":"gpt-5-4-nano","overall":{"max":80.37644697587939,"mean":36.50243212056372,"min":20.286570945301907},"per_game":{"GB2-01":23.232585171948244,"GB2-02":44.78176036427169,"GB2-04":21.01821571038539,"GB2-05":11.21124878648498,"GB2-06":67.88642915214035,"GB2-07":19.383166112214784,"GB2-08":29.06729936149991},"per_game_all":{"GB2-01":27.813136607405426,"GB2-02":58.539343390746005,"GB2-04":20.68847823351139,"GB2-05":26.877431526308346,"GB2-06":65.38820772234585,"GB2-07":33.88398848230424,"GB2-08":33.05468280200801},"per_game_match_totals_all":{"GB2-01":{"draws":11,"losses":29,"wins":16},"GB2-02":{"draws":66,"losses":3,"wins":1},"GB2-03":{"draws":7,"losses":14,"wins":13},"GB2-04":{"draws":13,"losses":8,"wins":1},"GB2-05":{"draws":0,"losses":39,"wins":21},"GB2-06":{"draws":2,"losses":23,"wins":41},"GB2-07":{"draws":0,"losses":26,"wins":20},"GB2-08":{"draws":30,"losses":9,"wins":5}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":2,"wins":1},"GB2-02":{"draws":10,"losses":1,"wins":1},"GB2-04":{"draws":3,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":10,"wins":2},"GB2-06":{"draws":0,"losses":4,"wins":6},"GB2-07":{"draws":0,"losses":8,"wins":2},"GB2-08":{"draws":6,"losses":4,"wins":2}},"medium":{"GB2-01":{"draws":6,"losses":14,"wins":2},"GB2-02":{"draws":20,"losses":0,"wins":0},"GB2-03":{"draws":0,"losses":2,"wins":0},"GB2-04":{"draws":6,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":11,"wins":7},"GB2-06":{"draws":2,"losses":12,"wins":22},"GB2-07":{"draws":0,"losses":10,"wins":10},"GB2-08":{"draws":6,"losses":3,"wins":3}},"none":{"GB2-01":{"draws":2,"losses":13,"wins":13},"GB2-02":{"draws":36,"losses":2,"wins":0},"GB2-03":{"draws":7,"losses":12,"wins":13},"GB2-04":{"draws":4,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":18,"wins":12},"GB2-06":{"draws":0,"losses":7,"wins":13},"GB2-07":{"draws":0,"losses":8,"wins":8},"GB2-08":{"draws":18,"losses":2,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1480.7435347319108,"GB2-02":1497.8806918967064,"GB2-04":1482.7916437187444,"GB2-05":1466.6924360475825,"GB2-06":1528.9292242015792,"GB2-07":1485.23684549067,"GB2-08":1493.3447108078137},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1491.3298054886754,"GB2-02":1500.421699644565,"GB2-04":1477.7198673955838,"GB2-05":1448.6777457922456,"GB2-06":1519.0584286182077,"GB2-07":1453.0103154279705,"GB2-08":1491.0591362947932},"medium":{"GB2-01":1452.5707076219967,"GB2-02":1499.9589359537877,"GB2-03":1469.4695015289756,"GB2-04":1486.0814642419975,"GB2-05":1482.833551542155,"GB2-06":1535.256560526864,"GB2-07":1501.3274236905345,"GB2-08":1497.7954168504823},"none":{"GB2-01":1498.3300910850603,"GB2-02":1493.2614400917662,"GB2-03":1496.7458667666378,"GB2-04":1484.5735995186524,"GB2-05":1468.5660108083473,"GB2-06":1532.4726834596663,"GB2-07":1501.3727973535056,"GB2-08":1491.179579278166}},"per_game_tracks":{"highest":{"GB2-01":23.232585171948244,"GB2-02":44.78176036427169,"GB2-04":21.01821571038539,"GB2-05":11.21124878648498,"GB2-06":67.88642915214035,"GB2-07":19.383166112214784,"GB2-08":29.06729936149991},"medium":{"GB2-01":20.286570945301904,"GB2-02":50.45982283208693,"GB2-03":0.0,"GB2-04":18.068587967984445,"GB2-05":28.521053935574997,"GB2-06":60.74636089063402,"GB2-07":31.49341726742192,"GB2-08":36.63939900910986},"none":{"GB2-01":39.92025370496613,"GB2-02":80.37644697587939,"GB2-03":50.031853759896784,"GB2-04":22.978631022164336,"GB2-05":40.89999185686506,"GB2-06":67.5318331242632,"GB2-07":50.775382067276034,"GB2-08":33.457350035414244}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.17184354476289,"medium":33.151456258750876,"none":48.18399655817738},"reasoning_agg":{"highest":{"max":29.06729936149991,"mean":28.17184354476289,"min":29.06729936149991},"medium":{"max":60.74636089063402,"mean":33.151456258750876,"min":20.286570945301907},"none":{"max":80.37644697587939,"mean":48.18399655817738,"min":33.457350035414244}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":80.37644697587939,"expected_score":37.173082654071536,"reasoning_variance":20.012153013414487,"reliability_score":0.28194171909403565,"uncertainty_avg":99.71805828090596,"uncertainty_penalty":0.6706505335078177},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":29.06729936149991,"expected_score":27.414944193427925,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-0.7568993513349653},"medium":{"ceiling_score":60.74636089063402,"expected_score":36.03662768318566,"reliability_score":0.317184433980799,"uncertainty_avg":99.6828155660192,"uncertainty_penalty":2.8851714244347804},"none":{"ceiling_score":80.37644697587939,"expected_score":45.10352961725711,"reliability_score":1.0333523755751912,"uncertainty_avg":98.96664762442481,"uncertainty_penalty":-3.0804669409202674}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625,"median":0.113468875,"min":0.061553,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.2156775,"mean":0.157461515625,"median":0.15705206249999998,"min":0.098579625,"recorded_attempt_count":33,"run_count":16,"total":2.5193842500000003}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.2156775,"mean":0.12996646093750003,"median":0.12798825,"min":0.061553,"recorded_attempt_count":50,"run_count":24,"total":3.3391555},"codegen_latency_ms":{"attempt_count":50,"max_ms":1200477,"mean_ms":884695.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":33,"max_ms":1200477,"mean_ms":915965.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":50,"output_max":131072,"output_mean":108502.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":33,"output_max":131072,"output_mean":115220.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":11.118062072734334,"none":61.91883129040855},"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":"2026-07-24T08:32:26Z","match_totals_all":{"draws":31,"losses":15,"wins":18},"match_totals_tracks":{"medium":{"draws":0,"losses":2,"wins":2},"none":{"draws":31,"losses":13,"wins":16}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":88.31746019814003,"mean":35.90217086107381,"min":2.206056684784772},"per_game_match_totals_all":{"GB2-02":{"draws":10,"losses":0,"wins":0},"GB2-03":{"draws":3,"losses":4,"wins":1},"GB2-04":{"draws":10,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":5,"wins":5},"GB2-06":{"draws":0,"losses":3,"wins":5},"GB2-07":{"draws":0,"losses":1,"wins":7},"GB2-08":{"draws":8,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-05":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":0,"wins":2}},"none":{"GB2-02":{"draws":10,"losses":0,"wins":0},"GB2-03":{"draws":3,"losses":4,"wins":1},"GB2-04":{"draws":10,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":5},"GB2-06":{"draws":0,"losses":3,"wins":5},"GB2-07":{"draws":0,"losses":1,"wins":5},"GB2-08":{"draws":8,"losses":2,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-05":1472.1260693796585,"GB2-07":1527.6432069611562},"none":{"GB2-02":1500.0,"GB2-03":1453.532635368453,"GB2-04":1500.0000621593915,"GB2-05":1529.4022582265975,"GB2-06":1521.685155836366,"GB2-07":1557.0965622422768,"GB2-08":1478.13128869641}},"per_game_tracks":{"medium":{"GB2-05":2.206056684784772,"GB2-07":20.030067460683895},"none":{"GB2-02":88.31746019814003,"GB2-03":20.101008655328517,"GB2-04":77.44621740853889,"GB2-05":63.923312075521814,"GB2-06":68.11299450046917,"GB2-07":70.09313143444155,"GB2-08":45.43769476041992}},"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":9.885510431739068,"none":61.918831290408555},"reasoning_agg":{"medium":{"max":20.030067460683895,"mean":9.885510431739068,"min":2.206056684784772},"none":{"max":88.31746019814003,"mean":61.918831290408555,"min":20.101008655328517}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":88.31746019814003,"reasoning_variance":52.033320858669484},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":20.030067460683895,"expected_score":43.62733917834114,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":33.74182874660207},"none":{"ceiling_score":88.31746019814003,"expected_score":52.87029348091429,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-9.048537809494263}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":15},"evidence_basis":"Standard list-price estimate","max":1.5164726249999998,"mean":1.0182428035714286,"median":0.9670455,"min":0.8356068750000001,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":15},"run_count":12,"token_priced_attempt_count":15,"total":12.214044},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.29749325,"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":35.75888487233347,"highest":30.280501231022594,"medium":31.348248130917945,"none":46.60693623096692},"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":"2026-07-26T05:19:30Z","match_totals_all":{"draws":140,"losses":147,"wins":93},"match_totals_tracks":{"highest":{"draws":17,"losses":31,"wins":16},"medium":{"draws":34,"losses":39,"wins":31},"none":{"draws":89,"losses":77,"wins":46}},"model_slug":"gpt-5-4-mini","overall":{"max":84.66959623266185,"mean":35.83490897565397,"min":15.111004980264804},"per_game":{"GB2-01":9.274252026937374,"GB2-02":36.02181753738935,"GB2-04":52.429805396744776,"GB2-05":15.111004980264804,"GB2-06":22.38763169438503,"GB2-07":41.87731419569299,"GB2-08":34.86168278574382},"per_game_all":{"GB2-01":25.680154055021603,"GB2-02":52.42396642489282,"GB2-04":50.24215677647939,"GB2-05":24.505600511979456,"GB2-06":31.207750291164853,"GB2-07":30.19947732163368,"GB2-08":36.0530887251625},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":25,"wins":16},"GB2-02":{"draws":52,"losses":2,"wins":0},"GB2-03":{"draws":25,"losses":3,"wins":10},"GB2-04":{"draws":23,"losses":8,"wins":9},"GB2-05":{"draws":0,"losses":38,"wins":16},"GB2-06":{"draws":1,"losses":30,"wins":17},"GB2-07":{"draws":0,"losses":36,"wins":20},"GB2-08":{"draws":36,"losses":5,"wins":5}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":4,"wins":0},"GB2-02":{"draws":10,"losses":2,"wins":0},"GB2-04":{"draws":3,"losses":1,"wins":2},"GB2-05":{"draws":0,"losses":6,"wins":2},"GB2-06":{"draws":1,"losses":9,"wins":4},"GB2-07":{"draws":0,"losses":4,"wins":6},"GB2-08":{"draws":3,"losses":5,"wins":2}},"medium":{"GB2-01":{"draws":0,"losses":10,"wins":6},"GB2-02":{"draws":14,"losses":0,"wins":0},"GB2-03":{"draws":9,"losses":1,"wins":2},"GB2-04":{"draws":7,"losses":3,"wins":6},"GB2-05":{"draws":0,"losses":10,"wins":6},"GB2-06":{"draws":0,"losses":7,"wins":5},"GB2-07":{"draws":0,"losses":8,"wins":4},"GB2-08":{"draws":4,"losses":0,"wins":2}},"none":{"GB2-01":{"draws":3,"losses":11,"wins":10},"GB2-02":{"draws":28,"losses":0,"wins":0},"GB2-03":{"draws":16,"losses":2,"wins":8},"GB2-04":{"draws":13,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":22,"wins":8},"GB2-06":{"draws":0,"losses":14,"wins":8},"GB2-07":{"draws":0,"losses":24,"wins":10},"GB2-08":{"draws":29,"losses":0,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1470.3606399599237,"GB2-02":1493.82385691198,"GB2-04":1502.8973919443276,"GB2-05":1463.1453633540875,"GB2-06":1471.8674696167052,"GB2-07":1477.1032152212047,"GB2-08":1498.415122291273},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1436.5109690978472,"GB2-02":1481.3587067359008,"GB2-04":1509.7689882955772,"GB2-05":1475.970576167065,"GB2-06":1460.9683997556665,"GB2-07":1513.4959456677282,"GB2-08":1482.1531607108873},"medium":{"GB2-01":1481.3196577531423,"GB2-02":1500.4272320299333,"GB2-03":1503.971359420517,"GB2-04":1514.0383344470172,"GB2-05":1478.1183230943618,"GB2-06":1483.4211426548072,"GB2-07":1483.789325760388,"GB2-08":1510.6666666666667},"none":{"GB2-01":1493.251293028781,"GB2-02":1499.6856319701062,"GB2-03":1520.921179477109,"GB2-04":1484.8848530903886,"GB2-05":1435.3471908008353,"GB2-06":1471.2128664396416,"GB2-07":1434.024374235498,"GB2-08":1502.4255394962645}},"per_game_tracks":{"highest":{"GB2-01":9.274252026937374,"GB2-02":36.02181753738935,"GB2-04":52.429805396744776,"GB2-05":15.111004980264804,"GB2-06":22.38763169438503,"GB2-07":41.87731419569299,"GB2-08":34.86168278574382},"medium":{"GB2-01":26.926882988824577,"GB2-02":36.58048550462725,"GB2-03":27.263789353843617,"GB2-04":54.757958247487515,"GB2-05":33.86489774494873,"GB2-06":32.555034570883585,"GB2-07":20.05828038125196,"GB2-08":18.778656255476346},"none":{"GB2-01":40.83932714930287,"GB2-02":84.66959623266185,"GB2-03":57.40461183939059,"GB2-04":43.53870668520589,"GB2-05":24.540898810724837,"GB2-06":38.680584608225935,"GB2-07":28.66283738795609,"GB2-08":54.51892713426735}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.051890238695204,"medium":30.845900457299766,"none":46.606936230966916},"reasoning_agg":{"highest":{"max":41.877314195692996,"mean":30.051890238695204,"min":15.111004980264804},"medium":{"max":54.757958247487515,"mean":30.845900457299766,"min":18.778656255476346},"none":{"max":84.66959623266185,"mean":46.606936230966916,"min":24.540898810724837}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":84.66959623266185,"expected_score":34.5198507776176,"reasoning_variance":16.55504599227171,"reliability_score":0.6664839303503385,"uncertainty_avg":99.33351606964966,"uncertainty_penalty":-1.3150581980363683},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":41.877314195692996,"expected_score":22.833011607017234,"reliability_score":0.3624964959780499,"uncertainty_avg":99.63750350402195,"uncertainty_penalty":-7.2188786316779705},"medium":{"ceiling_score":54.757958247487515,"expected_score":42.7930986384748,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":11.947198181175036},"none":{"ceiling_score":84.66959623266185,"expected_score":40.17956810851355,"reliability_score":1.4323358831888129,"uncertainty_avg":98.56766411681119,"uncertainty_penalty":-6.427368122453366}}},{"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":7.449890000000001},"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":1.7435249999999998},"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":51.6221750692961,"highest":64.97845054085393,"medium":30.362338532951828,"none":59.147376631578375},"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":"2026-07-26T05:16:01Z","match_totals_all":{"draws":36,"losses":52,"wins":70},"match_totals_tracks":{"highest":{"draws":8,"losses":23,"wins":37},"medium":{"draws":15,"losses":15,"wins":10},"none":{"draws":13,"losses":14,"wins":23}},"model_slug":"claude-opus-4-8","overall":{"max":68.79367100881747,"mean":35.66607173822596,"min":0.9741198055830358},"per_game":{"GB2-01":63.227948753432344,"GB2-02":100.0,"GB2-04":49.3356690118293,"GB2-05":20.09000511727103,"GB2-06":75.68862492648985,"GB2-07":100.0,"GB2-08":46.50690597695495},"per_game_all":{"GB2-01":59.1569752900588,"GB2-02":62.32136723038442,"GB2-04":53.56261802669553,"GB2-05":43.00523060110768,"GB2-06":44.90994792203498,"GB2-07":56.4020864280542,"GB2-08":41.99699998673714},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":10,"wins":13},"GB2-02":{"draws":13,"losses":5,"wins":8},"GB2-03":{"draws":1,"losses":2,"wins":1},"GB2-04":{"draws":16,"losses":7,"wins":3},"GB2-05":{"draws":0,"losses":9,"wins":11},"GB2-06":{"draws":1,"losses":9,"wins":10},"GB2-07":{"draws":0,"losses":3,"wins":15},"GB2-08":{"draws":2,"losses":7,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":5,"wins":4},"GB2-02":{"draws":4,"losses":2,"wins":8},"GB2-04":{"draws":3,"losses":6,"wins":3},"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-06":{"draws":0,"losses":4,"wins":6},"GB2-07":{"draws":0,"losses":0,"wins":10},"GB2-08":{"draws":0,"losses":6,"wins":4}},"medium":{"GB2-01":{"draws":0,"losses":2,"wins":4},"GB2-02":{"draws":3,"losses":3,"wins":0},"GB2-03":{"draws":1,"losses":2,"wins":1},"GB2-04":{"draws":9,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":5,"wins":3},"GB2-06":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":0,"wins":2},"GB2-08":{"draws":2,"losses":0,"wins":0}},"none":{"GB2-01":{"draws":2,"losses":3,"wins":5},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-04":{"draws":4,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":6},"GB2-06":{"draws":1,"losses":3,"wins":4},"GB2-07":{"draws":0,"losses":3,"wins":3},"GB2-08":{"draws":0,"losses":1,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1514.7593413562172,"GB2-02":1510.474168347182,"GB2-04":1483.3925031862816,"GB2-05":1508.1389274552712,"GB2-06":1504.068077858834,"GB2-07":1555.7108744976824,"GB2-08":1507.94746793035},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1489.5189978827975,"GB2-02":1572.67891162782,"GB2-04":1462.43828266857,"GB2-05":1531.1715084338457,"GB2-06":1537.6513921332432,"GB2-07":1625.3538418911696,"GB2-08":1463.973731649933},"medium":{"GB2-01":1521.1845854955018,"GB2-02":1458.743593413726,"GB2-03":1485.5588422359165,"GB2-04":1486.3367163870994,"GB2-05":1466.1790747178925,"GB2-06":1472.1260693796585,"GB2-07":1530.5304984710244,"GB2-08":1502.5656763485465},"none":{"GB2-01":1533.5744406903525,"GB2-02":1500.0,"GB2-04":1501.402510503175,"GB2-05":1527.066199214075,"GB2-06":1502.4267720635996,"GB2-07":1511.2482831308532,"GB2-08":1557.30299579257}},"per_game_tracks":{"highest":{"GB2-01":63.227948753432344,"GB2-02":100.0,"GB2-04":49.3356690118293,"GB2-05":20.09000511727103,"GB2-06":75.68862492648985,"GB2-07":100.0,"GB2-08":46.50690597695495},"medium":{"GB2-01":49.880727819804974,"GB2-02":23.12522491545858,"GB2-03":27.7138220154225,"GB2-04":64.96869777438559,"GB2-05":40.132015677234506,"GB2-06":0.9741198055830358,"GB2-07":21.018069742930145,"GB2-08":15.086030512795292},"none":{"GB2-01":64.3622492969391,"GB2-02":63.83887677569468,"GB2-04":46.38348729387168,"GB2-05":68.79367100881747,"GB2-06":58.06709903403206,"GB2-07":48.18818954123245,"GB2-08":64.39806347046118}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.430414290850603,"medium":30.362338532951828,"none":57.20546239087546},"reasoning_agg":{"highest":{"max":20.09000511727103,"mean":19.430414290850603,"min":20.09000511727103},"medium":{"max":64.96869777438559,"mean":30.362338532951828,"min":0.9741198055830358},"none":{"max":68.79367100881747,"mean":57.20546239087546,"min":46.38348729387168}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":68.79367100881747,"expected_score":49.056451316114014,"reasoning_variance":37.77504810002486,"reliability_score":0.9393098128624757,"uncertainty_avg":99.06069018713752,"uncertainty_penalty":13.390379577888055},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":20.09000511727103,"expected_score":54.61226798358931,"reliability_score":2.8179294385874556,"uncertainty_avg":97.18207056141254,"uncertainty_penalty":35.18185369273871},"medium":{"ceiling_score":64.96869777438559,"expected_score":31.425122712277552,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":1.0627841793257247},"none":{"ceiling_score":68.79367100881747,"expected_score":59.04232704258219,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":1.8368646517067262}}},{"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":0.14255357568},"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":0.19590749698000004},"codegen_latency_ms":{"attempt_count":60,"max_ms":1394682,"mean_ms":253119.97435897432,"min_ms":18361,"run_count":39},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":26,"max_ms":1394682,"mean_ms":546872.0,"min_ms":61403,"run_count":15},"none":{"attempt_count":34,"max_ms":161045,"mean_ms":69524.95833333333,"min_ms":18361,"run_count":24}},"codegen_output_tokens":{"attempt_count":60,"output_max":82048,"output_mean":14181.94871794872,"output_min":1698,"run_count":39},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":26,"output_max":82048,"output_mean":31146.866666666665,"output_min":4091,"run_count":15},"none":{"attempt_count":34,"output_max":7189,"output_mean":3578.875,"output_min":1698,"run_count":24}},"display_name":"DeepSeek V4 Flash","economics":{"highest":21.864258187400097,"none":54.51853465453375},"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":"2026-07-26T04:25:31Z","match_totals_all":{"draws":81,"losses":74,"wins":51},"match_totals_tracks":{"highest":{"draws":10,"losses":19,"wins":11},"none":{"draws":71,"losses":55,"wins":40}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":70.50265973927989,"mean":35.526474264972215,"min":8.00911100758693},"per_game":{"GB2-01":10.557812724081783,"GB2-02":25.99672485762664,"GB2-05":8.00911100758693,"GB2-06":23.462037897739805,"GB2-07":36.07322145174686,"GB2-08":27.086641185618543},"per_game_match_totals_all":{"GB2-01":{"draws":10,"losses":3,"wins":3},"GB2-02":{"draws":25,"losses":2,"wins":1},"GB2-03":{"draws":5,"losses":5,"wins":4},"GB2-04":{"draws":16,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":20,"wins":14},"GB2-06":{"draws":0,"losses":21,"wins":9},"GB2-07":{"draws":0,"losses":22,"wins":18},"GB2-08":{"draws":25,"losses":1,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":1,"wins":0},"GB2-02":{"draws":7,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":5,"wins":1},"GB2-06":{"draws":0,"losses":8,"wins":2},"GB2-07":{"draws":0,"losses":3,"wins":5},"GB2-08":{"draws":0,"losses":0,"wins":2}},"none":{"GB2-01":{"draws":7,"losses":2,"wins":3},"GB2-02":{"draws":18,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":5,"wins":4},"GB2-04":{"draws":16,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":15,"wins":13},"GB2-06":{"draws":0,"losses":13,"wins":7},"GB2-07":{"draws":0,"losses":19,"wins":13},"GB2-08":{"draws":25,"losses":1,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1491.2132068434712,"GB2-02":1490.493483018467,"GB2-05":1467.9630380761726,"GB2-06":1457.624295558111,"GB2-07":1511.7388573686103,"GB2-08":1530.5304984710244},"none":{"GB2-01":1499.211568165747,"GB2-02":1500.6408480449,"GB2-03":1494.4834288569448,"GB2-04":1500.0146239057158,"GB2-05":1497.146850528454,"GB2-06":1460.959198822065,"GB2-07":1478.785016902578,"GB2-08":1495.855114172026}},"per_game_tracks":{"highest":{"GB2-01":10.557812724081783,"GB2-02":25.99672485762664,"GB2-05":8.00911100758693,"GB2-06":23.462037897739805,"GB2-07":36.07322145174686,"GB2-08":27.086641185618543},"none":{"GB2-01":53.75268517253613,"GB2-02":83.73607838190517,"GB2-03":36.778477181844096,"GB2-04":70.50265973927989,"GB2-05":52.78416588226375,"GB2-06":42.27664829635107,"GB2-07":48.34014548737608,"GB2-08":47.97741709471381}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.266442279587753,"none":51.78650625035668},"reasoning_agg":{"highest":{"max":36.07322145174686,"mean":19.266442279587753,"min":8.00911100758693},"none":{"max":70.50265973927989,"mean":51.78650625035668,"min":47.977417094713815}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":70.50265973927989,"reasoning_variance":32.52006397076893},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":36.07322145174686,"expected_score":30.480848570970817,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":11.214406291383064},"none":{"ceiling_score":70.50265973927989,"expected_score":46.03883151235066,"reliability_score":1.5859221699039665,"uncertainty_avg":98.41407783009603,"uncertainty_penalty":-5.747674738006019}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.055222,"mean":0.046879,"median":0.046959,"min":0.039474,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.375032},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.03731,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"evidence_basis":"Standard list-price estimate","max":0.136952,"mean":0.07424775,"median":0.070604,"min":0.041758,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13},"run_count":8,"token_priced_attempt_count":13,"total":0.5939820000000001}},"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":33.63057405494346,"highest":9.987464116685963,"medium":39.3520875210354,"none":57.44107383453547},"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":"2026-07-24T08:30:46Z","match_totals_all":{"draws":34,"losses":37,"wins":31},"match_totals_tracks":{"highest":{"draws":0,"losses":4,"wins":0},"medium":{"draws":14,"losses":12,"wins":8},"none":{"draws":20,"losses":21,"wins":23}},"model_slug":"o3","overall":{"max":98.3326998110139,"mean":34.683260604702696,"min":9.987464116685963},"per_game":{"GB2-07":9.987464116685963},"per_game_all":{"GB2-07":33.63057405494346},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":8,"wins":3},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":3,"wins":0},"GB2-04":{"draws":8,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":7,"wins":5},"GB2-06":{"draws":2,"losses":4,"wins":8},"GB2-07":{"draws":0,"losses":11,"wins":7},"GB2-08":{"draws":8,"losses":1,"wins":5}},"per_game_match_totals_tracks":{"highest":{"GB2-07":{"draws":0,"losses":4,"wins":0}},"medium":{"GB2-01":{"draws":2,"losses":3,"wins":1},"GB2-04":{"draws":6,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":1},"GB2-06":{"draws":2,"losses":3,"wins":1},"GB2-07":{"draws":0,"losses":3,"wins":3},"GB2-08":{"draws":4,"losses":0,"wins":2}},"none":{"GB2-01":{"draws":1,"losses":5,"wins":2},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":3,"wins":0},"GB2-04":{"draws":2,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-06":{"draws":0,"losses":1,"wins":7},"GB2-07":{"draws":0,"losses":4,"wins":4},"GB2-08":{"draws":4,"losses":1,"wins":3}}},"per_game_raw_elo_all":{"GB2-07":1481.1450988588422},"per_game_raw_elo_tracks":{"highest":{"GB2-07":1441.595570908634},"medium":{"GB2-01":1471.1627795027389,"GB2-04":1497.5209163083844,"GB2-05":1473.4793070591224,"GB2-06":1473.0854473443942,"GB2-07":1493.9529766935357,"GB2-08":1526.695489466503},"none":{"GB2-01":1453.6133183842512,"GB2-02":1500.0,"GB2-03":1459.9869606636355,"GB2-04":1502.819604171326,"GB2-05":1496.2104323421324,"GB2-06":1579.6175406909322,"GB2-07":1507.8867489743568,"GB2-08":1527.011786370561}},"per_game_tracks":{"highest":{"GB2-07":9.987464116685963},"medium":{"GB2-01":30.901984146395755,"GB2-04":52.10380282255489,"GB2-05":24.30458347265825,"GB2-06":30.570506835857817,"GB2-07":35.79273781112405,"GB2-08":62.438910037621625},"none":{"GB2-01":24.54587802002869,"GB2-02":78.12877044269572,"GB2-03":23.462234798774787,"GB2-04":72.03452887188533,"GB2-05":48.36859211616061,"GB2-06":98.3326998110139,"GB2-07":55.11152023702036,"GB2-08":59.54436637870439}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":9.987464116685963,"medium":36.62124386288664,"none":57.44107383453548},"reasoning_agg":{"highest":{"max":9.987464116685963,"mean":9.987464116685963,"min":9.987464116685963},"medium":{"max":62.438910037621625,"mean":36.62124386288664,"min":24.30458347265825},"none":{"max":98.3326998110139,"mean":57.44107383453548,"min":23.462234798774787}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":98.3326998110139,"expected_score":34.94372999062846,"reasoning_variance":47.45360971784952,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":0.2604693859257665},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":9.987464116685963,"expected_score":5.896012273123721,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-4.0914518435622425},"medium":{"ceiling_score":62.438910037621625,"expected_score":38.85091889302483,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":2.2296750301381962},"none":{"ceiling_score":98.3326998110139,"expected_score":52.37888790200913,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-5.062185932526347}}},{"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":0.175742}},"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":29.297331},"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":34.64260728049801,"highest":32.364076219711784,"medium":29.94130070441072,"none":41.622444917371546},"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":"2026-07-26T04:33:44Z","match_totals_all":{"draws":52,"losses":57,"wins":31},"match_totals_tracks":{"highest":{"draws":7,"losses":20,"wins":13},"medium":{"draws":14,"losses":10,"wins":8},"none":{"draws":31,"losses":27,"wins":10}},"model_slug":"gpt-5-6-luna","overall":{"max":85.51402220849519,"mean":34.64260728049801,"min":0.0},"per_game":{"GB2-01":42.295507720147306,"GB2-02":7.938787272130405,"GB2-03":30.25564189080981,"GB2-04":48.23091288238881,"GB2-05":24.37774563050526,"GB2-06":23.45031550917826,"GB2-07":40.95532147493775,"GB2-08":41.40837737759667},"per_game_all":{"GB2-01":45.12836396596845,"GB2-02":44.74233923808936,"GB2-03":34.179322638519295,"GB2-04":56.21735196048567,"GB2-05":24.223535423255893,"GB2-06":20.268184383089356,"GB2-07":21.60617034088216,"GB2-08":30.775590293693938},"per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":8,"wins":7},"GB2-02":{"draws":16,"losses":0,"wins":0},"GB2-03":{"draws":8,"losses":9,"wins":5},"GB2-04":{"draws":12,"losses":0,"wins":4},"GB2-05":{"draws":0,"losses":11,"wins":5},"GB2-06":{"draws":2,"losses":10,"wins":4},"GB2-07":{"draws":0,"losses":16,"wins":4},"GB2-08":{"draws":9,"losses":3,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":4,"wins":2},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-03":{"draws":0,"losses":2,"wins":2},"GB2-04":{"draws":2,"losses":0,"wins":2},"GB2-05":{"draws":0,"losses":4,"wins":2},"GB2-06":{"draws":2,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":7,"wins":3},"GB2-08":{"draws":1,"losses":1,"wins":2}},"medium":{"GB2-01":{"draws":0,"losses":3,"wins":3},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":3,"losses":1,"wins":0},"GB2-04":{"draws":4,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":1,"wins":3},"GB2-06":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":4,"wins":0},"GB2-08":{"draws":1,"losses":1,"wins":0}},"none":{"GB2-01":{"draws":5,"losses":1,"wins":2},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":5,"losses":6,"wins":3},"GB2-04":{"draws":6,"losses":0,"wins":2},"GB2-05":{"draws":0,"losses":6,"wins":0},"GB2-06":{"draws":0,"losses":8,"wins":2},"GB2-07":{"draws":0,"losses":5,"wins":1},"GB2-08":{"draws":7,"losses":1,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1497.7392974671964,"GB2-02":1500.4683093490978,"GB2-03":1486.3186335016344,"GB2-04":1518.215983954652,"GB2-05":1468.9727436539508,"GB2-06":1469.681541665246,"GB2-07":1450.3521336532258,"GB2-08":1494.2309555707307},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1476.9234311963903,"GB2-02":1500.0,"GB2-03":1502.6750486743172,"GB2-04":1527.854010262026,"GB2-05":1464.6134865335616,"GB2-06":1471.446185107028,"GB2-07":1466.5856778496336,"GB2-08":1510.7610977307845},"medium":{"GB2-01":1504.4866893935418,"GB2-02":1500.0,"GB2-03":1486.7455327157995,"GB2-04":1499.2922598334735,"GB2-05":1531.4543789735717,"GB2-06":1530.5304984710244,"GB2-07":1442.0113333727763,"GB2-08":1484.0},"none":{"GB2-01":1511.8077718116565,"GB2-02":1501.4049280472937,"GB2-03":1469.5353191147865,"GB2-04":1527.5016817684566,"GB2-05":1410.8503654547196,"GB2-06":1407.0679414176852,"GB2-07":1442.4593897372677,"GB2-08":1487.931768981408}},"per_game_tracks":{"highest":{"GB2-01":42.295507720147306,"GB2-02":7.938787272130405,"GB2-03":30.25564189080981,"GB2-04":48.23091288238881,"GB2-05":24.37774563050526,"GB2-06":23.45031550917826,"GB2-07":40.95532147493775,"GB2-08":41.40837737759667},"medium":{"GB2-01":43.54538898677351,"GB2-02":47.03489357836214,"GB2-03":28.196442992066643,"GB2-04":34.907120790573025,"GB2-05":48.292860639262415,"GB2-06":22.39006485552579,"GB2-07":8.54028397978935,"GB2-08":6.623349812932906},"none":{"GB2-01":49.54419519098453,"GB2-02":79.25333686377554,"GB2-03":44.08588303268143,"GB2-04":85.51402220849519,"GB2-05":0.0,"GB2-06":14.96417278456402,"GB2-07":15.322905567919376,"GB2-08":44.295043690552234}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.364076219711784,"medium":29.94130070441072,"none":41.62244491737154},"reasoning_agg":{"highest":{"max":48.23091288238881,"mean":32.364076219711784,"min":7.938787272130405},"medium":{"max":48.292860639262415,"mean":29.94130070441072,"min":6.623349812932906},"none":{"max":85.51402220849519,"mean":41.62244491737154,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":85.51402220849519,"expected_score":36.633095293179,"reasoning_variance":11.68114421296082,"reliability_score":0.6104397969341449,"uncertainty_avg":99.38956020306586,"uncertainty_penalty":1.9904880126809843},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.23091288238881,"expected_score":31.686207950162565,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-0.6778682695492186},"medium":{"ceiling_score":48.292860639262415,"expected_score":41.00164453224083,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":11.060343827830113},"none":{"ceiling_score":85.51402220849519,"expected_score":37.211433397133575,"reliability_score":1.8313193908024346,"uncertainty_avg":98.16868060919757,"uncertainty_penalty":-4.411011520237963}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.121855,"mean":0.09110296875,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.0216425,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.121855,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112225},"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":18.095828691445565,"none":53.366612421968746},"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":"2026-07-26T04:27:53Z","match_totals_all":{"draws":24,"losses":23,"wins":23},"match_totals_tracks":{"medium":{"draws":2,"losses":5,"wins":5},"none":{"draws":22,"losses":18,"wins":18}},"model_slug":"qwen-qwen3-7-max","overall":{"max":88.78538412158109,"mean":34.55810063172774,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":5,"wins":5},"GB2-02":{"draws":9,"losses":0,"wins":1},"GB2-03":{"draws":7,"losses":5,"wins":0},"GB2-05":{"draws":0,"losses":5,"wins":5},"GB2-06":{"draws":0,"losses":5,"wins":1},"GB2-07":{"draws":0,"losses":2,"wins":8},"GB2-08":{"draws":8,"losses":1,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":1},"GB2-07":{"draws":0,"losses":0,"wins":4}},"none":{"GB2-01":{"draws":0,"losses":3,"wins":5},"GB2-02":{"draws":7,"losses":0,"wins":1},"GB2-03":{"draws":7,"losses":5,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":4},"GB2-06":{"draws":0,"losses":5,"wins":1},"GB2-07":{"draws":0,"losses":2,"wins":4},"GB2-08":{"draws":8,"losses":1,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1469.4695015289756,"GB2-02":1500.0,"GB2-05":1470.8103873214277,"GB2-07":1558.404429091366},"none":{"GB2-01":1538.3483955736565,"GB2-02":1513.3133758629065,"GB2-03":1442.1110052239967,"GB2-05":1522.509871553963,"GB2-06":1448.5159654071874,"GB2-07":1529.7871016863971,"GB2-08":1526.328449134532}},"per_game_tracks":{"medium":{"GB2-01":0.0,"GB2-02":0.8142096436771892,"GB2-05":23.200267698842175,"GB2-07":48.368837423262896},"none":{"GB2-01":60.94512589214032,"GB2-02":88.78538412158109,"GB2-03":25.81473425769878,"GB2-05":52.32711072358359,"GB2-06":20.63268905546018,"GB2-07":57.04548475706871,"GB2-08":68.01575814624856}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":17.5017102463939,"none":51.61449101706158},"reasoning_agg":{"medium":{"max":48.368837423262896,"mean":17.5017102463939,"min":0.0},"none":{"max":88.78538412158109,"mean":51.61449101706158,"min":20.63268905546018}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":88.78538412158109,"reasoning_variance":34.11278077066768},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":48.368837423262896,"expected_score":45.608667323051705,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":28.106957076657807},"none":{"ceiling_score":88.78538412158109,"expected_score":56.50016508787075,"reliability_score":1.449985983912228,"uncertainty_avg":98.55001401608777,"uncertainty_penalty":4.885674070809166}}},{"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":4.168735999999999},"codegen_latency_ms":{"attempt_count":19,"max_ms":417022,"mean_ms":186639.61111111112,"min_ms":23645,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":417022,"mean_ms":302024.2,"min_ms":185272,"run_count":10},"medium":{"attempt_count":9,"max_ms":95118,"mean_ms":42408.875,"min_ms":23645,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43177,"output_mean":20523.777777777777,"output_min":3136,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43177,"output_mean":32906.3,"output_min":21120,"run_count":10},"medium":{"attempt_count":9,"output_max":10845,"output_mean":5045.625,"output_min":3136,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"highest":37.217520746614596,"medium":26.060974093967044},"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":"2026-07-26T05:18:34Z","match_totals_all":{"draws":32,"losses":52,"wins":22},"match_totals_tracks":{"highest":{"draws":22,"losses":34,"wins":16},"medium":{"draws":10,"losses":18,"wins":6}},"model_slug":"claude-sonnet-5","overall":{"max":64.23364251811388,"mean":31.21143320771047,"min":13.91653367845897},"per_game":{"GB2-01":52.140505713697905,"GB2-02":64.23364251811388,"GB2-03":35.31821633534032,"GB2-04":16.24469384358224,"GB2-05":37.91604159142834,"GB2-06":44.962076322178525,"GB2-07":22.64626338915258,"GB2-08":24.278726259423003},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":5,"wins":3},"GB2-02":{"draws":10,"losses":3,"wins":3},"GB2-03":{"draws":9,"losses":12,"wins":5},"GB2-04":{"draws":5,"losses":5,"wins":0},"GB2-05":{"draws":0,"losses":5,"wins":5},"GB2-06":{"draws":0,"losses":6,"wins":4},"GB2-07":{"draws":0,"losses":14,"wins":2},"GB2-08":{"draws":4,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":1,"wins":1},"GB2-02":{"draws":6,"losses":3,"wins":3},"GB2-03":{"draws":9,"losses":12,"wins":5},"GB2-04":{"draws":1,"losses":3,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":3},"GB2-06":{"draws":0,"losses":3,"wins":3},"GB2-07":{"draws":0,"losses":7,"wins":1},"GB2-08":{"draws":2,"losses":2,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":4,"wins":2},"GB2-02":{"draws":4,"losses":0,"wins":0},"GB2-04":{"draws":4,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":2},"GB2-06":{"draws":0,"losses":3,"wins":1},"GB2-07":{"draws":0,"losses":7,"wins":1},"GB2-08":{"draws":2,"losses":0,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1497.2304601990168,"GB2-02":1502.5062592423849,"GB2-03":1472.188693859763,"GB2-04":1454.6119434309394,"GB2-05":1506.280039821182,"GB2-06":1495.0099747000645,"GB2-07":1430.082339140544,"GB2-08":1472.145989737974},"medium":{"GB2-01":1479.0178034281334,"GB2-02":1500.0,"GB2-04":1471.1244974235983,"GB2-05":1494.666828786396,"GB2-06":1468.0,"GB2-07":1422.4364408339654,"GB2-08":1500.0}},"per_game_tracks":{"highest":{"GB2-01":52.140505713697905,"GB2-02":64.23364251811388,"GB2-03":35.31821633534032,"GB2-04":16.24469384358224,"GB2-05":37.91604159142834,"GB2-06":44.962076322178525,"GB2-07":22.64626338915258,"GB2-08":24.278726259423003},"medium":{"GB2-01":33.88225410406439,"GB2-02":30.981885466879664,"GB2-04":34.59664938174029,"GB2-05":33.07131936247808,"GB2-06":18.548750393536665,"GB2-07":17.429426270611234,"GB2-08":13.91653367845897}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.2175207466146,"medium":25.205345668806338},"reasoning_agg":{"highest":{"max":64.23364251811388,"mean":37.2175207466146,"min":16.24469384358224},"medium":{"max":34.59664938174029,"mean":25.205345668806338,"min":13.91653367845897}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":64.23364251811388,"reasoning_variance":12.012175077808266},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.23364251811388,"expected_score":25.461422487921308,"reliability_score":0.8458251572821212,"uncertainty_avg":99.15417484271788,"uncertainty_penalty":-11.756098258693296},"medium":{"ceiling_score":34.59664938174029,"expected_score":30.18086588631333,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":4.975520217506993}}},{"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":3.912616499999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","max":0.5145615,"mean":0.34875300000000004,"median":0.335163,"min":0.254883,"recorded_attempt_count":19,"run_count":8,"total":2.7900240000000003}},"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":21.858169745885615,"medium":41.323734677436455},"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":"2026-07-26T05:19:11Z","match_totals_all":{"draws":9,"losses":14,"wins":25},"match_totals_tracks":{"highest":{"draws":0,"losses":0,"wins":4},"medium":{"draws":9,"losses":14,"wins":21}},"model_slug":"google-gemini-3-5-flash","overall":{"max":89.95315028509629,"mean":30.832526827018057,"min":0.07470067028436407},"per_game":{"GB2-05":19.01855617631298,"GB2-07":24.69778331545825},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":0,"wins":8},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-03":{"draws":1,"losses":3,"wins":0},"GB2-04":{"draws":2,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":4,"wins":6},"GB2-06":{"draws":1,"losses":1,"wins":6},"GB2-07":{"draws":0,"losses":2,"wins":4},"GB2-08":{"draws":3,"losses":3,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":0,"wins":2}},"medium":{"GB2-01":{"draws":0,"losses":0,"wins":8},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-03":{"draws":1,"losses":3,"wins":0},"GB2-04":{"draws":2,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-06":{"draws":1,"losses":1,"wins":6},"GB2-07":{"draws":0,"losses":2,"wins":2},"GB2-08":{"draws":3,"losses":3,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1527.8739306203415,"GB2-07":1533.2055471453416},"medium":{"GB2-01":1608.9500238710789,"GB2-02":1498.723968813176,"GB2-03":1462.77657918209,"GB2-04":1499.8714272350912,"GB2-05":1499.018812605407,"GB2-06":1569.4603743368766,"GB2-07":1497.2824410330618,"GB2-08":1462.5349465700135}},"per_game_tracks":{"highest":{"GB2-05":19.01855617631298,"GB2-07":24.69778331545825},"medium":{"GB2-01":89.95315028509629,"GB2-02":0.07470067028436407,"GB2-03":18.448391617527136,"GB2-04":35.291247615211326,"GB2-05":53.72007531236189,"GB2-06":72.45581232805715,"GB2-07":27.453504319336258,"GB2-08":33.19299527161726}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.34131897659966,"medium":41.323734677436455},"reasoning_agg":{"highest":{"max":24.69778331545825,"mean":20.34131897659966,"min":19.01855617631298},"medium":{"max":89.95315028509629,"mean":41.323734677436455,"min":0.07470067028436407}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":89.95315028509629,"reasoning_variance":20.982415700836796},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":24.69778331545825,"expected_score":58.19136861733769,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":37.85004964073803},"medium":{"ceiling_score":89.95315028509629,"expected_score":47.49282178184675,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":6.169087104410295}}},{"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":2.2561125},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477375,"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":1.4205012499999996}},"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":19.504857704271625,"medium":40.81733956037599},"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":"2026-07-24T08:36:34Z","match_totals_all":{"draws":21,"losses":14,"wins":15},"match_totals_tracks":{"highest":{"draws":1,"losses":3,"wins":6},"medium":{"draws":20,"losses":11,"wins":9}},"model_slug":"gpt-5","overall":{"max":58.566505961224365,"mean":29.49104547465272,"min":0.0},"per_game":{"GB2-01":0.0,"GB2-02":14.615930597008015,"GB2-05":20.7509049493766,"GB2-07":42.65259527070188},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":2,"wins":2},"GB2-02":{"draws":1,"losses":0,"wins":1},"GB2-03":{"draws":6,"losses":2,"wins":0},"GB2-04":{"draws":6,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":6},"GB2-06":{"draws":1,"losses":2,"wins":1},"GB2-07":{"draws":0,"losses":3,"wins":5},"GB2-08":{"draws":3,"losses":1,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-02":{"draws":1,"losses":0,"wins":1},"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":1,"wins":3}},"medium":{"GB2-01":{"draws":4,"losses":0,"wins":2},"GB2-03":{"draws":6,"losses":2,"wins":0},"GB2-04":{"draws":6,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":4},"GB2-06":{"draws":1,"losses":2,"wins":1},"GB2-07":{"draws":0,"losses":2,"wins":2},"GB2-08":{"draws":3,"losses":1,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1469.4358728782763,"GB2-02":1514.5304984710244,"GB2-05":1533.2055471453416,"GB2-07":1529.4304618937335},"medium":{"GB2-01":1523.6103336841522,"GB2-03":1469.5281451628723,"GB2-04":1476.996638950421,"GB2-05":1528.5841632136724,"GB2-06":1490.8583571134702,"GB2-07":1501.8613667007814,"GB2-08":1484.0}},"per_game_tracks":{"highest":{"GB2-01":0.0,"GB2-02":14.615930597008015,"GB2-05":20.7509049493766,"GB2-07":42.65259527070188},"medium":{"GB2-01":50.80107949793708,"GB2-03":39.720028269528505,"GB2-04":50.3317446901941,"GB2-05":58.566505961224365,"GB2-06":26.93053457480546,"GB2-07":29.02036689434154,"GB2-08":30.351117034600865}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.504857704271622,"medium":39.477233245033815},"reasoning_agg":{"highest":{"max":42.65259527070188,"mean":19.504857704271622,"min":0.0},"medium":{"max":58.566505961224365,"mean":39.477233245033815,"min":26.93053457480546}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":58.566505961224365,"reasoning_variance":19.972375540762194},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.65259527070188,"expected_score":48.432970715026435,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":28.928113010754814},"medium":{"ceiling_score":58.566505961224365,"expected_score":34.139674185518764,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-5.337559059515051}}},{"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":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.5164659199999999},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.6470588235,"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":14.554287613059696,"none":42.51165766860635},"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":"2026-07-24T08:34:38Z","match_totals_all":{"draws":19,"losses":22,"wins":13},"match_totals_tracks":{"medium":{"draws":2,"losses":4,"wins":4},"none":{"draws":17,"losses":18,"wins":9}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":96.05335144708482,"mean":27.938577607160074,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":5,"wins":0},"GB2-02":{"draws":14,"losses":0,"wins":0},"GB2-04":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":7,"wins":5},"GB2-06":{"draws":0,"losses":3,"wins":5},"GB2-07":{"draws":0,"losses":7,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":2},"GB2-07":{"draws":0,"losses":0,"wins":2}},"none":{"GB2-01":{"draws":3,"losses":3,"wins":0},"GB2-02":{"draws":12,"losses":0,"wins":0},"GB2-04":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":5,"wins":3},"GB2-06":{"draws":0,"losses":3,"wins":5},"GB2-07":{"draws":0,"losses":7,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1469.4695015289756,"GB2-02":1500.0,"GB2-05":1502.6750486743172,"GB2-07":1530.5304984710244},"none":{"GB2-01":1462.803504425782,"GB2-02":1500.0,"GB2-04":1500.736306793522,"GB2-05":1477.1277320955123,"GB2-06":1522.4918807760312,"GB2-07":1418.9930397758658}},"per_game_tracks":{"medium":{"GB2-01":0.0,"GB2-02":0.8142096436771892,"GB2-05":36.38487106563145,"GB2-07":21.018069742930145},"none":{"GB2-01":20.824867582641573,"GB2-02":96.05335144708482,"GB2-04":17.591313863256847,"GB2-05":39.42584641010008,"GB2-06":68.53381249379966,"GB2-07":12.640754214755123}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":13.544290773482851,"none":42.3328644408373},"reasoning_agg":{"medium":{"max":36.38487106563145,"mean":13.544290773482851,"min":0.0},"none":{"max":96.05335144708482,"mean":42.3328644408373,"min":12.640754214755123}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":96.05335144708482,"reasoning_variance":28.78857366735445},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.38487106563145,"expected_score":46.74141699579802,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":33.19712622231517},"none":{"ceiling_score":96.05335144708482,"expected_score":42.67152850462376,"reliability_score":0.8458251572821354,"uncertainty_avg":99.15417484271786,"uncertainty_penalty":0.3386640637864602}}},{"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":15.004090823201976,"none":42.446648895106485},"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":"2026-07-26T04:32:24Z","match_totals_all":{"draws":16,"losses":12,"wins":12},"match_totals_tracks":{"highest":{"draws":2,"losses":0,"wins":2},"none":{"draws":14,"losses":12,"wins":10}},"model_slug":"tencent-hy3-preview","overall":{"max":78.12877044269572,"mean":26.795732830413094,"min":1.21320551456183},"per_game":{"GB2-02":7.293186162737853,"GB2-07":22.714995483666097},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":3,"wins":4},"GB2-02":{"draws":10,"losses":0,"wins":0},"GB2-03":{"draws":1,"losses":3,"wins":2},"GB2-04":{"draws":0,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-07":{"draws":0,"losses":0,"wins":2},"GB2-08":{"draws":4,"losses":0,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-07":{"draws":0,"losses":0,"wins":2}},"none":{"GB2-01":{"draws":1,"losses":3,"wins":4},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":1,"losses":3,"wins":2},"GB2-04":{"draws":0,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":4},"GB2-08":{"draws":4,"losses":0,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1498.5950719527063,"GB2-07":1527.8739306203415},"none":{"GB2-01":1522.2377570923338,"GB2-02":1500.0,"GB2-03":1493.8672427563188,"GB2-04":1470.746623126497,"GB2-05":1517.3492959264645,"GB2-08":1500.0}},"per_game_tracks":{"highest":{"GB2-02":7.293186162737853,"GB2-07":22.714995483666097},"none":{"GB2-01":54.02455482628946,"GB2-02":78.12877044269572,"GB2-03":31.80906363947512,"GB2-04":1.21320551456183,"GB2-05":58.2749197902678,"GB2-08":31.229379157349015}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":14.09040794643933,"none":39.50105771438686},"reasoning_agg":{"highest":{"max":22.714995483666097,"mean":14.09040794643933,"min":7.293186162737853},"none":{"max":78.12877044269572,"mean":39.50105771438686,"min":1.21320551456183}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":78.12877044269572,"reasoning_variance":25.410649767947532},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":22.714995483666097,"expected_score":44.53286190356957,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":30.44245395713024},"none":{"ceiling_score":78.12877044269572,"expected_score":47.09147965989764,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":7.590421945510776}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.25293804045,"mean":0.19953128278325,"median":0.20662718916666667,"min":0.13279406625,"recorded_attempt_count":57,"run_count":27,"total":5.24138213703}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.25293804045,"mean":0.19953128278325,"median":0.20662718916666667,"min":0.13279406625,"recorded_attempt_count":57,"run_count":27,"total":5.24138213703},"codegen_latency_ms":{"attempt_count":57,"max_ms":3869582,"mean_ms":1358902.4074074074,"min_ms":364048,"run_count":27},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":57,"max_ms":3869582,"mean_ms":1358902.4074074074,"min_ms":364048,"run_count":27}},"codegen_output_tokens":{"attempt_count":57,"output_max":109372,"output_mean":63750.148148148146,"output_min":27968,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":109372,"output_mean":63750.148148148146,"output_min":27968,"run_count":27}},"display_name":"GLM-5.2","economics":{"highest":39.894476546016364},"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":"2026-07-26T05:11:06Z","match_totals_all":{"draws":32,"losses":44,"wins":30},"match_totals_tracks":{"highest":{"draws":32,"losses":44,"wins":30}},"model_slug":"z-ai-glm-5-2","overall":{"max":41.22509318012413,"mean":25.808795915129807,"min":23.49748362524384},"per_game":{"GB2-01":65.97406121479838,"GB2-02":41.22509318012413,"GB2-03":27.775510687462543,"GB2-04":37.78185331618536,"GB2-05":23.80317652899078,"GB2-06":74.9097608340662,"GB2-07":23.49748362524384,"GB2-08":24.18887298125965},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":4,"wins":8},"GB2-02":{"draws":16,"losses":6,"wins":2},"GB2-03":{"draws":3,"losses":6,"wins":1},"GB2-04":{"draws":8,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":6,"wins":6},"GB2-06":{"draws":1,"losses":2,"wins":5},"GB2-07":{"draws":0,"losses":14,"wins":4},"GB2-08":{"draws":2,"losses":4,"wins":4}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":4,"wins":8},"GB2-02":{"draws":16,"losses":6,"wins":2},"GB2-03":{"draws":3,"losses":6,"wins":1},"GB2-04":{"draws":8,"losses":2,"wins":0},"GB2-05":{"draws":0,"losses":6,"wins":6},"GB2-06":{"draws":1,"losses":2,"wins":5},"GB2-07":{"draws":0,"losses":14,"wins":4},"GB2-08":{"draws":2,"losses":4,"wins":4}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1524.3237849654224,"GB2-02":1482.548988483234,"GB2-03":1438.716713828499,"GB2-04":1490.077921826858,"GB2-05":1498.6631354085737,"GB2-06":1548.5241214622515,"GB2-07":1453.5060810233729,"GB2-08":1497.4133315323743}},"per_game_tracks":{"highest":{"GB2-01":65.97406121479838,"GB2-02":41.22509318012413,"GB2-03":27.775510687462543,"GB2-04":37.78185331618536,"GB2-05":23.80317652899078,"GB2-06":74.9097608340662,"GB2-07":23.49748362524384,"GB2-08":24.18887298125965}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.808795915129807},"reasoning_agg":{"highest":{"max":41.22509318012413,"mean":25.808795915129807,"min":23.49748362524384}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":41.22509318012413},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":41.22509318012413,"expected_score":33.93042032443645,"reliability_score":0.21145628932052318,"uncertainty_avg":99.78854371067948,"uncertainty_penalty":8.12162440930664}}},{"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":0.4396294499999999},"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":0.29741569999999995},"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":{"highest":0.6801616415769609,"medium":46.75696475879187,"none":36.9210833736464},"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":"2026-07-24T08:23:28Z","match_totals_all":{"draws":19,"losses":48,"wins":21},"match_totals_tracks":{"highest":{"draws":0,"losses":4,"wins":0},"medium":{"draws":11,"losses":11,"wins":6},"none":{"draws":8,"losses":33,"wins":15}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":81.89436099219294,"mean":25.210473632620435,"min":0.0},"per_game":{"GB2-01":1.3603232831539218,"GB2-07":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":6,"wins":4},"GB2-02":{"draws":5,"losses":0,"wins":1},"GB2-03":{"draws":5,"losses":1,"wins":2},"GB2-04":{"draws":6,"losses":4,"wins":6},"GB2-05":{"draws":0,"losses":10,"wins":4},"GB2-06":{"draws":0,"losses":14,"wins":2},"GB2-07":{"draws":0,"losses":8,"wins":2},"GB2-08":{"draws":3,"losses":5,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":0}},"medium":{"GB2-02":{"draws":5,"losses":0,"wins":1},"GB2-04":{"draws":6,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":4,"wins":2},"GB2-06":{"draws":0,"losses":6,"wins":2}},"none":{"GB2-01":{"draws":0,"losses":4,"wins":4},"GB2-03":{"draws":5,"losses":1,"wins":2},"GB2-04":{"draws":0,"losses":3,"wins":5},"GB2-05":{"draws":0,"losses":6,"wins":2},"GB2-06":{"draws":0,"losses":8,"wins":0},"GB2-07":{"draws":0,"losses":6,"wins":2},"GB2-08":{"draws":3,"losses":5,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1472.2417773977136,"GB2-07":1466.7944528546584},"medium":{"GB2-02":1513.3133758629065,"GB2-04":1501.1952656711608,"GB2-05":1475.035963055667,"GB2-06":1452.2758962189691},"none":{"GB2-01":1504.3211791150018,"GB2-03":1514.35910728032,"GB2-04":1520.873779904115,"GB2-05":1455.600773851739,"GB2-06":1391.109818636726,"GB2-07":1443.7253057738876,"GB2-08":1437.59330882824}},"per_game_tracks":{"highest":{"GB2-01":1.3603232831539218,"GB2-07":0.0},"medium":{"GB2-02":54.7505050919615,"GB2-04":66.38123507395115,"GB2-05":36.40993030300801,"GB2-06":29.48618856624682},"none":{"GB2-01":46.328214839967146,"GB2-03":51.77767790476365,"GB2-04":81.89436099219294,"GB2-05":29.337645531236213,"GB2-06":0.0,"GB2-07":24.45709410959486,"GB2-08":24.65259023776997}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":0.6047587213572916,"medium":39.31776405381234,"none":35.70889812269167},"reasoning_agg":{"highest":{"max":1.3603232831539218,"mean":0.6047587213572916,"min":0.0},"medium":{"max":66.38123507395115,"mean":39.31776405381234,"min":29.48618856624682},"none":{"max":81.89436099219294,"mean":35.70889812269167,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":81.89436099219294,"reasoning_variance":38.71300533245505},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":1.3603232831539218,"expected_score":22.018367718884875,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":21.413608997527582},"medium":{"ceiling_score":66.38123507395115,"expected_score":44.67889347935542,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":5.3611294255430835},"none":{"ceiling_score":81.89436099219294,"expected_score":34.78540739892261,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-0.9234907237690635}}},{"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":0.5845103399999999},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":8.304788296783649,"none":40.93717438934563},"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":"2026-07-26T03:30:33Z","match_totals_all":{"draws":18,"losses":24,"wins":14},"match_totals_tracks":{"medium":{"draws":2,"losses":6,"wins":2},"none":{"draws":16,"losses":18,"wins":12}},"model_slug":"minimax-minimax-m3","overall":{"max":68.60647273143803,"mean":23.06423031858786,"min":0.8142096436771892},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":6,"wins":4},"GB2-02":{"draws":7,"losses":1,"wins":0},"GB2-03":{"draws":6,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":6,"wins":6},"GB2-07":{"draws":0,"losses":8,"wins":0},"GB2-08":{"draws":1,"losses":0,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":2,"wins":2},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":0}},"none":{"GB2-01":{"draws":4,"losses":4,"wins":2},"GB2-02":{"draws":5,"losses":1,"wins":0},"GB2-03":{"draws":6,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":4,"wins":6},"GB2-07":{"draws":0,"losses":6,"wins":0},"GB2-08":{"draws":1,"losses":0,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1497.3249513256828,"GB2-02":1500.0,"GB2-05":1469.340885792452,"GB2-07":1472.1260693796585},"none":{"GB2-01":1469.389548617265,"GB2-02":1485.4049280472937,"GB2-03":1468.2188678240018,"GB2-05":1526.6667415160332,"GB2-07":1419.7439754715829,"GB2-08":1546.1090094472745}},"per_game_tracks":{"medium":{"GB2-01":30.31865084609639,"GB2-02":0.8142096436771892,"GB2-05":1.0536345550049466,"GB2-07":1.0326581423560668},"none":{"GB2-01":36.79064762139175,"GB2-02":52.156336973834705,"GB2-03":34.377963175077326,"GB2-05":68.60647273143803,"GB2-07":4.470157346753793,"GB2-08":49.22146848757817}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":8.03212723254066,"none":38.09633340463506},"reasoning_agg":{"medium":{"max":30.31865084609639,"mean":8.03212723254066,"min":0.8142096436771892},"none":{"max":68.60647273143803,"mean":38.09633340463506,"min":4.470157346753793}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":68.60647273143803,"reasoning_variance":30.0642061720944},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":30.31865084609639,"expected_score":38.2719216796138,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":30.239794447073137},"none":{"ceiling_score":68.60647273143803,"expected_score":34.88304130035247,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-3.213292104282594}}},{"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":1.2830031540000002}},"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":1.2830031540000002},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":24.653683750712368},"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":"2026-07-24T08:34:38Z","match_totals_all":{"draws":2,"losses":3,"wins":7},"match_totals_tracks":{"medium":{"draws":2,"losses":3,"wins":7}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":59.44395110851627,"mean":22.942837893179405,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":0,"wins":4},"GB2-07":{"draws":0,"losses":1,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":0,"wins":4},"GB2-07":{"draws":0,"losses":1,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1469.4695015289756,"GB2-02":1501.4049280472937,"GB2-05":1558.404429091366,"GB2-07":1526.7656529407611}},"per_game_tracks":{"medium":{"GB2-01":0.0,"GB2-02":1.6284192873543784,"GB2-05":59.44395110851627,"GB2-07":37.54236460697883}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.942837893179405},"reasoning_agg":{"medium":{"max":59.44395110851627,"mean":22.942837893179405,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":59.44395110851627},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.44395110851627,"expected_score":55.337378198563584,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":32.39454030538418}}},{"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":0.2854256}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0445032,"mean":0.030658954687500004,"median":0.0312573,"min":0.01864685,"recorded_attempt_count":52,"run_count":25,"total":0.75384265},"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":{"highest":5.403067906956127,"medium":39.14685590519698},"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":"2026-07-24T08:36:58Z","match_totals_all":{"draws":20,"losses":12,"wins":6},"match_totals_tracks":{"highest":{"draws":4,"losses":6,"wins":0},"medium":{"draws":16,"losses":6,"wins":6}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":60.6918649131083,"mean":20.390893966031264,"min":1.1116094713313929},"per_game":{"GB2-01":0.07863644706498163,"GB2-02":8.231972090890327,"GB2-05":7.898595182913073},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":3,"wins":2},"GB2-02":{"draws":11,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":0},"GB2-06":{"draws":2,"losses":2,"wins":2},"GB2-07":{"draws":0,"losses":2,"wins":0},"GB2-08":{"draws":4,"losses":0,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":0},"GB2-02":{"draws":4,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":0}},"medium":{"GB2-01":{"draws":3,"losses":1,"wins":2},"GB2-02":{"draws":7,"losses":1,"wins":0},"GB2-06":{"draws":2,"losses":2,"wins":2},"GB2-07":{"draws":0,"losses":2,"wins":0},"GB2-08":{"draws":4,"losses":0,"wins":2}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1469.5980742938843,"GB2-02":1500.638015593412,"GB2-05":1441.595570908634},"medium":{"GB2-01":1508.0483159414823,"GB2-02":1485.5281201859304,"GB2-06":1498.9102410147786,"GB2-07":1472.3567930388438,"GB2-08":1522.8627707927917}},"per_game_tracks":{"highest":{"GB2-01":0.07863644706498163,"GB2-02":8.231972090890327,"GB2-05":7.898595182913073},"medium":{"GB2-01":44.89670359791641,"GB2-02":48.99406695490356,"GB2-06":40.04003458872524,"GB2-07":1.1116094713313929,"GB2-08":60.6918649131083}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":6.984740518283821,"medium":33.79704741377871},"reasoning_agg":{"highest":{"max":8.231972090890327,"mean":6.984740518283821,"min":7.898595182913073},"medium":{"max":60.6918649131083,"mean":33.79704741377871,"min":1.1116094713313929}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":60.6918649131083,"reasoning_variance":26.812306895494885},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":8.231972090890327,"expected_score":21.402768386823027,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":14.418027868539205},"medium":{"ceiling_score":60.6918649131083,"expected_score":48.1167404911684,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":14.319693077389694}}},{"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":0.06847673400000001},"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":41.72122134035262,"highest":0.9913939158960788,"medium":29.095424846131447,"none":26.626809324982492},"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":"2026-07-24T08:27:47Z","match_totals_all":{"draws":38,"losses":57,"wins":7},"match_totals_tracks":{"highest":{"draws":1,"losses":3,"wins":0},"medium":{"draws":18,"losses":13,"wins":3},"none":{"draws":19,"losses":41,"wins":4}},"model_slug":"openai-gpt-oss-120b","overall":{"max":78.12877044269572,"mean":18.54948899681229,"min":0.0},"per_game":{"GB2-02":0.0,"GB2-07":1.9827878317921577},"per_game_all":{"GB2-02":41.72122134035262},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":10,"wins":1},"GB2-02":{"draws":15,"losses":1,"wins":0},"GB2-03":{"draws":5,"losses":5,"wins":2},"GB2-04":{"draws":10,"losses":6,"wins":0},"GB2-05":{"draws":0,"losses":12,"wins":2},"GB2-06":{"draws":0,"losses":10,"wins":2},"GB2-07":{"draws":0,"losses":10,"wins":0},"GB2-08":{"draws":7,"losses":3,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":1,"losses":1,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":0}},"medium":{"GB2-01":{"draws":1,"losses":2,"wins":1},"GB2-02":{"draws":6,"losses":0,"wins":0},"GB2-03":{"draws":2,"losses":2,"wins":0},"GB2-04":{"draws":7,"losses":1,"wins":0},"GB2-05":{"draws":0,"losses":4,"wins":2},"GB2-06":{"draws":0,"losses":4,"wins":0},"GB2-08":{"draws":2,"losses":0,"wins":0}},"none":{"GB2-01":{"draws":0,"losses":8,"wins":0},"GB2-02":{"draws":8,"losses":0,"wins":0},"GB2-03":{"draws":3,"losses":3,"wins":2},"GB2-04":{"draws":3,"losses":5,"wins":0},"GB2-05":{"draws":0,"losses":8,"wins":0},"GB2-06":{"draws":0,"losses":6,"wins":2},"GB2-07":{"draws":0,"losses":8,"wins":0},"GB2-08":{"draws":5,"losses":3,"wins":0}}},"per_game_raw_elo_all":{"GB2-02":1494.2413229377253},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1482.723968813176,"GB2-07":1472.1260693796585},"medium":{"GB2-01":1485.4387739660467,"GB2-02":1500.0,"GB2-03":1470.1632457797657,"GB2-04":1486.631434389583,"GB2-05":1467.4809940074406,"GB2-06":1432.27578830108,"GB2-08":1500.0},"none":{"GB2-01":1396.4721138182515,"GB2-02":1500.0,"GB2-03":1485.1738917539578,"GB2-04":1437.9955204504631,"GB2-05":1395.1275746892982,"GB2-06":1443.8930696157672,"GB2-07":1392.535228098371,"GB2-08":1459.350977586987}},"per_game_tracks":{"highest":{"GB2-02":0.0,"GB2-07":1.9827878317921577},"medium":{"GB2-01":25.808923360490382,"GB2-02":47.03489357836214,"GB2-03":21.452511316765065,"GB2-04":56.721923708814785,"GB2-05":33.283919665515235,"GB2-06":5.449268614513586,"GB2-08":13.91653367845897},"none":{"GB2-01":0.0,"GB2-02":78.12877044269572,"GB2-03":36.57886084133818,"GB2-04":36.63249267259896,"GB2-05":0.9980271778302016,"GB2-06":27.533723908026257,"GB2-07":0.0,"GB2-08":33.14259955737062}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":0.8814876939379283,"medium":28.140169971516453,"none":26.626809324982492},"reasoning_agg":{"highest":{"max":1.9827878317921577,"mean":0.8814876939379283,"min":0.0},"medium":{"max":56.721923708814785,"mean":28.140169971516453,"min":5.449268614513586},"none":{"max":78.12877044269572,"mean":26.626809324982492,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":78.12877044269572,"expected_score":48.199609478563836,"reasoning_variance":27.258682277578526,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":29.650120481751546},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":1.9827878317921577,"expected_score":23.722839318964667,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":22.84135162502674},"medium":{"ceiling_score":56.721923708814785,"expected_score":28.22303219440724,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":0.08286222289078538},"none":{"ceiling_score":78.12877044269572,"expected_score":17.7666065120816,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":-8.86020281290089}}},{"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":0.21124250000000003},"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":{"highest":1.9827878317921577,"medium":32.728540540467016},"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":"2026-07-24T08:22:06Z","match_totals_all":{"draws":8,"losses":12,"wins":6},"match_totals_tracks":{"highest":{"draws":0,"losses":2,"wins":0},"medium":{"draws":8,"losses":10,"wins":6}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":52.45790701816219,"mean":16.11015712307726,"min":1.7629753878758565},"per_game":{"GB2-07":1.9827878317921577},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":1,"wins":1},"GB2-04":{"draws":6,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":3},"GB2-06":{"draws":0,"losses":4,"wins":0},"GB2-07":{"draws":0,"losses":4,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-07":{"draws":0,"losses":2,"wins":0}},"medium":{"GB2-01":{"draws":2,"losses":1,"wins":1},"GB2-04":{"draws":6,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":3,"wins":3},"GB2-06":{"draws":0,"losses":4,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":2}}},"per_game_raw_elo_tracks":{"highest":{"GB2-07":1472.1260693796585},"medium":{"GB2-01":1498.5304984710244,"GB2-04":1498.054817076874,"GB2-05":1495.32056874196,"GB2-06":1442.889659305465,"GB2-07":1493.8076933558175}},"per_game_tracks":{"highest":{"GB2-07":1.9827878317921577},"medium":{"GB2-01":30.77604677180444,"GB2-04":52.45790701816219,"GB2-05":44.80306768688403,"GB2-06":9.341200814407326,"GB2-07":26.26448041107709}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":1.7629753878758565,"medium":30.457338858278668},"reasoning_agg":{"highest":{"max":1.9827878317921577,"mean":1.7629753878758565,"min":1.9827878317921577},"medium":{"max":52.45790701816219,"mean":30.457338858278668,"min":9.341200814407326}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":52.45790701816219,"reasoning_variance":28.694363470402813},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":1.9827878317921577,"expected_score":21.530909347692692,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":19.767933959816837},"medium":{"ceiling_score":52.45790701816219,"expected_score":32.832471080790114,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":2.3751322225114464}}},{"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":0.0,"none":38.61103159265851},"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":"2026-07-26T03:29:30Z","match_totals_all":{"draws":16,"losses":22,"wins":10},"match_totals_tracks":{"medium":{"draws":0,"losses":4,"wins":0},"none":{"draws":16,"losses":18,"wins":10}},"model_slug":"cohere-north-mini-code","overall":{"max":60.4248678976658,"mean":15.825243345832424,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":11,"wins":1},"GB2-05":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":7,"wins":9},"GB2-08":{"draws":4,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-05":{"draws":0,"losses":2,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":0}},"none":{"GB2-01":{"draws":12,"losses":11,"wins":1},"GB2-07":{"draws":0,"losses":5,"wins":9},"GB2-08":{"draws":4,"losses":2,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-05":1466.7944528546584,"GB2-07":1469.1082776795804},"none":{"GB2-01":1434.739283643999,"GB2-07":1527.93411330647,"GB2-08":1472.146307721856}},"per_game_tracks":{"medium":{"GB2-05":0.0,"GB2-07":0.0},"none":{"GB2-01":24.23895659367875,"GB2-07":60.4248678976658,"GB2-08":31.169270286630997}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":0.0,"none":31.65048669166485},"reasoning_agg":{"medium":{"max":0.0,"mean":0.0,"min":0.0},"none":{"max":60.4248678976658,"mean":31.65048669166485,"min":24.238956593678754}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":60.4248678976658,"reasoning_variance":31.65048669166485},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":0.0,"expected_score":26.30501453246091,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":26.30501453246091},"none":{"ceiling_score":60.4248678976658,"expected_score":33.82583831402135,"reliability_score":3.7470312469722558,"uncertainty_avg":96.25296875302774,"uncertainty_penalty":2.175351622356498}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.33185775,"mean":0.18266821875,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":13,"run_count":9,"total":1.7932035000000002},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.0429946875,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.3439575}},"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":2.1371610000000003},"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":4.395573334308744,"none":31.339288311360107},"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":"2026-07-24T08:36:59Z","match_totals_all":{"draws":9,"losses":18,"wins":7},"match_totals_tracks":{"highest":{"draws":1,"losses":3,"wins":0},"none":{"draws":8,"losses":15,"wins":7}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":52.307511756100986,"mean":14.971032898152762,"min":0.9555917734408588},"per_game":{"GB2-01":7.835554895176629,"GB2-07":0.9555917734408588},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":2,"wins":4},"GB2-06":{"draws":0,"losses":9,"wins":1},"GB2-07":{"draws":0,"losses":2,"wins":0},"GB2-08":{"draws":8,"losses":0,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":1,"wins":0},"GB2-07":{"draws":0,"losses":2,"wins":0}},"none":{"GB2-01":{"draws":0,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":2,"wins":4},"GB2-06":{"draws":0,"losses":9,"wins":1},"GB2-08":{"draws":8,"losses":0,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1485.5980742938843,"GB2-07":1469.3639909609249},"none":{"GB2-01":1465.0093023277818,"GB2-05":1522.4680498099588,"GB2-06":1382.142709657611,"GB2-08":1500.79660871983}},"per_game_tracks":{"highest":{"GB2-01":7.835554895176629,"GB2-07":0.9555917734408588},"none":{"GB2-01":21.77240179460907,"GB2-05":52.307511756100986,"GB2-06":1.9622368125270648,"GB2-08":49.31500288220331}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":3.588970598680174,"none":26.35309519762535},"reasoning_agg":{"highest":{"max":7.835554895176629,"mean":3.588970598680174,"min":0.9555917734408588},"none":{"max":52.307511756100986,"mean":26.35309519762535,"min":1.9622368125270648}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":52.307511756100986,"reasoning_variance":22.764124598945177},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":7.835554895176629,"expected_score":27.392993548862968,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":23.804022950182794},"none":{"ceiling_score":52.307511756100986,"expected_score":31.724014672849936,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":5.370919475224586}}},{"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":12.682717002734117},"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":"2026-07-24T08:34:13Z","match_totals_all":{"draws":2,"losses":2,"wins":4},"match_totals_tracks":{"medium":{"draws":2,"losses":2,"wins":4}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":26.425205646059872,"mean":12.682717002734117,"min":0.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":0,"wins":2},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":2,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":0,"wins":2},"GB2-02":{"draws":2,"losses":0,"wins":0},"GB2-05":{"draws":0,"losses":0,"wins":2},"GB2-07":{"draws":0,"losses":2,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1533.2055471453416,"GB2-02":1498.5950719527063,"GB2-05":1530.659114207548,"GB2-07":1469.4695015289756}},"per_game_tracks":{"medium":{"GB2-01":24.182055175791454,"GB2-02":0.0,"GB2-05":26.425205646059872,"GB2-07":0.12360718908514348}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":12.682717002734117},"reasoning_agg":{"medium":{"max":26.425205646059872,"mean":12.682717002734117,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":26.425205646059872},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":26.425205646059872,"expected_score":52.43714423886039,"reliability_score":0.0,"uncertainty_avg":100.0,"uncertainty_penalty":39.754427236126276}}}],"public_release_id":"gb2-20260726-11fb0891c89b","results_cut_id":"gb2-20260726-11fb0891c89b","snapshot_id":"20260726_091516","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-07-26 09:15 UTC","versus_totals_all":{"claude-fable-5":{"claude-opus-4-8":{"draws":1,"losses":3,"wins":6},"claude-opus-5":{"draws":7,"losses":11,"wins":8},"claude-sonnet-5":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":1,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":9},"gpt-5.5":{"draws":4,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":2,"wins":5},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":9},"o3":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":3}},"claude-opus-4-5":{"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":3},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"claude-opus-4-8":{"claude-fable-5":{"draws":1,"losses":6,"wins":3},"claude-opus-4-5":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":2,"losses":7,"wins":5},"claude-sonnet-5":{"draws":3,"losses":1,"wins":10},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":8},"gpt-5.5":{"draws":1,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"o3":{"draws":4,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":4}},"claude-opus-5":{"claude-fable-5":{"draws":7,"losses":8,"wins":11},"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":14,"losses":29,"wins":29},"claude-sonnet-5":{"draws":0,"losses":0,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":6},"gpt-5.4":{"draws":2,"losses":3,"wins":13},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":6},"gpt-5.5":{"draws":2,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":13},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":21},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":8}},"claude-sonnet-5":{"claude-fable-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-8":{"draws":3,"losses":10,"wins":1},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":5},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":2},"o3":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":3}},"cohere/north-mini-code":{"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"deepseek/deepseek-v4-flash":{"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":1,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":2,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":9,"losses":5,"wins":8},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":10,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":4}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":1,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":6},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":3,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"google/gemini-3.1-flash-lite":{"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0},"o3":{"draws":2,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":1}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":0,"losses":0,"wins":4},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":0,"losses":2,"wins":0}},"google/gemini-3.5-flash-lite":{"claude-opus-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.6-flash":{"draws":17,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":5,"losses":16,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":1}},"google/gemini-3.6-flash":{"claude-opus-5":{"draws":0,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":18},"google/gemini-3.6-flash":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":10}},"google/gemma-4-31b-it":{"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":1,"wins":0},"claude-opus-4-5":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":0},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":2}},"gpt-5.4":{"claude-fable-5":{"draws":1,"losses":2,"wins":5},"claude-opus-4-8":{"draws":2,"losses":3,"wins":3},"claude-opus-5":{"draws":2,"losses":13,"wins":3},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":10},"gpt-5.5":{"draws":2,"losses":4,"wins":6},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":1,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":8},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":2}},"gpt-5.4-mini":{"claude-fable-5":{"draws":1,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":1,"wins":0},"claude-opus-4-8":{"draws":3,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":3,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":2},"gpt-5":{"draws":6,"losses":2,"wins":0},"gpt-5.4":{"draws":5,"losses":8,"wins":5},"gpt-5.4-mini":{"draws":20,"losses":14,"wins":14},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":15},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":6},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":8,"losses":12,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":4}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":9,"wins":5},"claude-opus-4-5":{"draws":6,"losses":3,"wins":3},"claude-opus-4-8":{"draws":2,"losses":8,"wins":4},"claude-opus-5":{"draws":4,"losses":6,"wins":0},"claude-sonnet-5":{"draws":3,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":4},"gpt-5.4":{"draws":5,"losses":10,"wins":1},"gpt-5.4-mini":{"draws":20,"losses":15,"wins":19},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":16},"gpt-5.5":{"draws":4,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":2},"o3":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":9,"losses":10,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-5.5":{"claude-fable-5":{"draws":4,"losses":4,"wins":4},"claude-opus-4-5":{"draws":0,"losses":2,"wins":2},"claude-opus-4-8":{"draws":1,"losses":0,"wins":3},"claude-opus-5":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":2,"losses":6,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":5,"losses":1,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":2}},"gpt-5.6-luna":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":4,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":5},"gpt-5.5":{"draws":1,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":2}},"gpt-5.6-sol":{"claude-fable-5":{"draws":5,"losses":5,"wins":2},"claude-opus-4-8":{"draws":5,"losses":3,"wins":10},"claude-opus-5":{"draws":5,"losses":13,"wins":8},"claude-sonnet-5":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":10},"gpt-5.5":{"draws":5,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":1}},"gpt-5.6-terra":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-8":{"draws":3,"losses":4,"wins":1},"claude-opus-5":{"draws":4,"losses":3,"wins":1},"claude-sonnet-5":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":0,"wins":1},"gpt-5.4":{"draws":4,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":4},"gpt-5.5":{"draws":6,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-5":{"draws":1,"losses":3,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":13,"wins":8}},"meituan/longcat-2.0":{"claude-opus-5":{"draws":3,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":10},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":14}},"minimax/minimax-m3":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":1},"gpt-5.5":{"draws":2,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":5,"wins":3}},"moonshotai/kimi-k2.7-code":{"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":9,"losses":3,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":6,"losses":1,"wins":11},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":11},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":7,"wins":5},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":1}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":2},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":4}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"o3":{"draws":1,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"o3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":4,"losses":1,"wins":1},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3}},"openai/gpt-oss-120b":{"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":0},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":1},"o3":{"draws":7,"losses":11,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":14,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0}},"poolside/laguna-s-2.1":{"claude-opus-5":{"draws":2,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":10}},"qwen/qwen3.7-max":{"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-5.4":{"draws":4,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":4,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"o3":{"draws":3,"losses":8,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":14},"x-ai/grok-4.5":{"draws":3,"losses":14,"wins":1}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":2},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3}},"thinkingmachines/inkling":{"claude-opus-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":16},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":9},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":1}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":4,"losses":4,"wins":4},"claude-opus-4-5":{"draws":4,"losses":4,"wins":4},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":4,"losses":21,"wins":13},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":6},"gpt-5":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":6},"gpt-5.5":{"draws":1,"losses":2,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":7},"o3":{"draws":5,"losses":3,"wins":8},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":13},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":14},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":9}},"x-ai/grok-build-0.1":{"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":6,"losses":3,"wins":5},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-5.4":{"draws":2,"losses":5,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":0,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":10},"gpt-5.5":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":6,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-8":{"draws":0,"losses":1,"wins":3},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":4}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":3,"wins":2},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":7,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":3},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":4},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":1,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":6}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-opus-4-8":{"draws":1,"losses":3,"wins":4},"claude-opus-5":{"draws":4,"losses":6,"wins":6},"claude-sonnet-5":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":5},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":4},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":7},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":3}},"claude-opus-4-5":{"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":4}},"claude-opus-4-8":{"claude-fable-5":{"draws":1,"losses":4,"wins":3},"claude-opus-5":{"draws":2,"losses":5,"wins":3},"claude-sonnet-5":{"draws":1,"losses":1,"wins":8},"gpt-5.4":{"draws":2,"losses":1,"wins":3},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":4},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":4}},"claude-opus-5":{"claude-fable-5":{"draws":4,"losses":6,"wins":6},"claude-opus-4-8":{"draws":2,"losses":3,"wins":5},"claude-opus-5":{"draws":2,"losses":11,"wins":11},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":3,"wins":11},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":0,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":7},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":8}},"claude-sonnet-5":{"claude-fable-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-8":{"draws":1,"losses":8,"wins":1},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":1,"losses":8,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":3}},"deepseek/deepseek-v4-flash":{"claude-sonnet-5":{"draws":1,"losses":6,"wins":1},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":4}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":6},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0}},"google/gemini-3.1-flash-lite":{"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0}},"google/gemini-3.5-flash":{"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-opus-4-5":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":0,"wins":1}},"gpt-5.4":{"claude-fable-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-8":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":0,"losses":11,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":4},"gpt-5.5":{"draws":2,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":1,"losses":0,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":2}},"gpt-5.4-mini":{"claude-fable-5":{"draws":1,"losses":2,"wins":1},"claude-opus-4-8":{"draws":1,"losses":4,"wins":1},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":1,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":1},"gpt-5.5":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":4}},"gpt-5.4-nano":{"claude-fable-5":{"draws":1,"losses":5,"wins":2},"claude-opus-4-5":{"draws":0,"losses":1,"wins":1},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":1},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":1,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-5.5":{"claude-fable-5":{"draws":2,"losses":2,"wins":4},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":7,"wins":3},"gpt-5.4":{"draws":2,"losses":1,"wins":3},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":2}},"gpt-5.6-luna":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":2}},"gpt-5.6-sol":{"claude-fable-5":{"draws":4,"losses":4,"wins":2},"claude-opus-4-8":{"draws":1,"losses":2,"wins":5},"claude-opus-5":{"draws":3,"losses":7,"wins":6},"claude-sonnet-5":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":1},"gpt-5.5":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":1}},"gpt-5.6-terra":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":3,"wins":1},"claude-sonnet-5":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":3}},"mistralai/mistral-medium-3-5":{"gpt-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":0}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":0,"wins":2}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0}},"o3":{"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0}},"openai/gpt-oss-120b":{"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":0,"wins":2}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":4,"losses":4,"wins":4},"gpt-5":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":4}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":3,"wins":2},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":7,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":3},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":4},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":1,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":6}}},"medium":{"claude-fable-5":{"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":4},"gpt-5.5":{"draws":2,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":0,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":4}},"claude-opus-4-5":{"claude-opus-5":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":1,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":0},"o3":{"draws":4,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0}},"claude-opus-5":{"claude-fable-5":{"draws":3,"losses":2,"wins":5},"claude-opus-4-5":{"draws":2,"losses":1,"wins":1},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":4,"losses":12,"wins":12},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":6},"gpt-5.4":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":21}},"claude-sonnet-5":{"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":0},"o3":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0}},"cohere/north-mini-code":{"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0}},"google/gemini-3.1-flash-lite":{"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":3},"o3":{"draws":2,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":1}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":0,"losses":0,"wins":4},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":2,"wins":0}},"google/gemini-3.5-flash-lite":{"claude-opus-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.6-flash":{"draws":17,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":5,"losses":16,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":1}},"google/gemini-3.6-flash":{"claude-opus-5":{"draws":0,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":18},"google/gemini-3.6-flash":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":10}},"google/gemma-4-31b-it":{"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":0},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":1}},"gpt-5.4":{"claude-fable-5":{"draws":1,"losses":0,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":3},"gpt-5.5":{"draws":0,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0}},"gpt-5.4-mini":{"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":2,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":1},"gpt-5":{"draws":6,"losses":2,"wins":0},"gpt-5.4":{"draws":3,"losses":5,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":5},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":0}},"gpt-5.4-nano":{"claude-fable-5":{"draws":1,"losses":4,"wins":3},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":3,"losses":1,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":4},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":6},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":2},"o3":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"gpt-5.5":{"claude-fable-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":2}},"gpt-5.6-luna":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":1,"wins":1}},"gpt-5.6-sol":{"claude-fable-5":{"draws":1,"losses":1,"wins":0},"claude-opus-4-8":{"draws":1,"losses":0,"wins":3},"claude-opus-5":{"draws":1,"losses":5,"wins":2},"claude-sonnet-5":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":2},"gpt-5.5":{"draws":0,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":3,"wins":1}},"gpt-5.6-terra":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":1,"losses":0,"wins":1},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":0,"wins":1},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":2},"gpt-5.5":{"draws":4,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":0,"wins":2}},"minimax/minimax-m3":{"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0}},"moonshotai/kimi-k2.7-code":{"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":7,"losses":2,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":1}},"nex-agi/nex-n2-pro":{"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"nvidia/nemotron-3-ultra-550b-a55b":{"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":4},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":1},"o3":{"draws":1,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"o3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":4,"losses":1,"wins":1},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0}},"openai/gpt-oss-120b":{"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"o3":{"draws":3,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":0}},"qwen/qwen3.7-max":{"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0}},"thinkingmachines/inkling":{"claude-opus-5":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":16},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":9},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":1}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":4,"losses":4,"wins":4},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":4,"losses":21,"wins":13},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":6},"gpt-5.5":{"draws":1,"losses":2,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":5,"wins":5}},"x-ai/grok-build-0.1":{"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"xiaomi/mimo-v2.5-pro":{"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}}},"none":{"claude-opus-4-5":{"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":2},"gpt-5.5":{"draws":0,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"claude-opus-4-8":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1}},"claude-opus-5":{"claude-opus-4-5":{"draws":1,"losses":1,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":8,"losses":6,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":3},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":1,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4}},"cohere/north-mini-code":{"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"deepseek/deepseek-v4-flash":{"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":2,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":7},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":1}},"deepseek/deepseek-v4-pro":{"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":1,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"google/gemma-4-31b-it":{"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"gpt-5.4":{"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":3},"gpt-5.5":{"draws":0,"losses":0,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":3,"losses":1,"wins":0},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":2},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":9},"gpt-5.5":{"draws":6,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"losses":10,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":0}},"gpt-5.4-nano":{"claude-opus-4-5":{"draws":6,"losses":2,"wins":2},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"claude-opus-5":{"draws":1,"losses":3,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":10},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":8,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2}},"gpt-5.5":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":1,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":3},"gpt-5.5":{"draws":1,"losses":1,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":0}},"gpt-5.6-sol":{"claude-opus-4-8":{"draws":3,"losses":1,"wins":2},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":7},"gpt-5.5":{"draws":5,"losses":0,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1}},"gpt-5.6-terra":{"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":1},"gpt-5.5":{"draws":2,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":1}},"inclusionai/ling-3.0-flash":{"claude-opus-5":{"draws":1,"losses":3,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":13,"wins":8}},"meituan/longcat-2.0":{"claude-opus-5":{"draws":3,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":10},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":14}},"minimax/minimax-m3":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":1},"gpt-5.5":{"draws":2,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":5,"wins":3}},"moonshotai/kimi-k3":{"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"o3":{"draws":6,"losses":1,"wins":9},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":7,"wins":3}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":2},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":2}},"o3":{"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3}},"openai/gpt-oss-120b":{"gpt-5.4-nano":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":1},"o3":{"draws":4,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":11,"wins":0}},"poolside/laguna-s-2.1":{"claude-opus-5":{"draws":2,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":10}},"qwen/qwen3.7-max":{"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":1},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0}},"stepfun/step-3.7-flash":{"moonshotai/kimi-k3":{"draws":1,"losses":11,"wins":2},"o3":{"draws":3,"losses":8,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":1,"losses":12,"wins":1}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3}},"thinkingmachines/inkling":{"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":1}},"x-ai/grok-4.5":{"gpt-5.4":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":3,"wins":7},"o3":{"draws":5,"losses":3,"wins":8},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":11},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":12}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":4,"losses":3,"wins":5},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-5.4":{"draws":2,"losses":5,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":8},"gpt-5.5":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-8":{"draws":0,"losses":1,"wins":3},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":2}}}}}