{"benchmark_line":"gamebench2","economics_chart":{"eligible_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"enabled":true},"game_order":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"games":[{"alias":"GB2-01","name":"Go","slug":"go"},{"alias":"GB2-02","name":"Chess","slug":"chess"},{"alias":"GB2-03","name":"Shogi","slug":"shogi"},{"alias":"GB2-04","name":"Xiangqi","slug":"xiangqi"},{"alias":"GB2-05","name":"Hex","slug":"hex"},{"alias":"GB2-06","name":"International Draughts","slug":"international-draughts"},{"alias":"GB2-07","name":"Game of the Amazons","slug":"game-of-the-amazons"},{"alias":"GB2-08","name":"Tumbleweed","slug":"tumbleweed"}],"generated_at":"2026-08-24T10:33:49Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:7f49308e40ed3ed5","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-2026-08-08":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-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0371999999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6981,"mean":0.5046499999999999,"median":0.511355,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0372},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"evidence_basis":"Standard list-price estimate","max":1.91725,"mean":1.58262125,"median":1.5854,"min":1.05322,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":12.66097}},"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-2026-08-08":19},"run_count":16,"token_priced_attempt_count":19,"total":16.69817},"codegen_latency_ms":{"attempt_count":19,"max_ms":409229,"mean_ms":200864.125,"min_ms":48099,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":409229,"mean_ms":316399.125,"min_ms":206163,"run_count":8},"medium":{"attempt_count":8,"max_ms":135206,"mean_ms":85329.125,"min_ms":48099,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":35932,"output_mean":17962.875,"output_min":4319,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":35932,"output_mean":28345.125,"output_min":18778,"run_count":8},"medium":{"attempt_count":8,"output_max":11549,"output_mean":7580.625,"output_min":4319,"run_count":8}},"display_name":"Claude Fable 5","economics":{"highest":83.32037116335817,"medium":68.30128747589306},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":23,"output_token_observations":19,"total_output_tokens":287406},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-08-05T04:44:21Z","match_totals_all":{"draws":129,"losses":208,"wins":791},"match_totals_tracks":{"highest":{"draws":72,"losses":91,"wins":441},"medium":{"draws":57,"losses":117,"wins":350}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":74.68960256062708,"min":56.05592222052655},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":1,"overall_ranking_status":"partial","per_game":{"GB2-01":74.5791609476971,"GB2-02":72.77270456368558,"GB2-03":67.5967962093199,"GB2-04":100.0,"GB2-05":92.46710125142182,"GB2-06":86.36800772140613,"GB2-07":72.77919861333487,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":44,"wins":102},"GB2-02":{"draws":58,"losses":8,"wins":68},"GB2-03":{"draws":22,"losses":7,"wins":19},"GB2-04":{"draws":40,"losses":19,"wins":95},"GB2-05":{"draws":0,"losses":47,"wins":123},"GB2-06":{"draws":8,"losses":22,"wins":114},"GB2-07":{"draws":0,"losses":45,"wins":111},"GB2-08":{"draws":1,"losses":16,"wins":159}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":27,"wins":53},"GB2-02":{"draws":31,"losses":2,"wins":37},"GB2-03":{"draws":22,"losses":7,"wins":19},"GB2-04":{"draws":13,"losses":5,"wins":68},"GB2-05":{"draws":0,"losses":12,"wins":68},"GB2-06":{"draws":5,"losses":6,"wins":57},"GB2-07":{"draws":0,"losses":28,"wins":52},"GB2-08":{"draws":1,"losses":4,"wins":87}},"medium":{"GB2-01":{"draws":0,"losses":17,"wins":49},"GB2-02":{"draws":27,"losses":6,"wins":31},"GB2-04":{"draws":27,"losses":14,"wins":27},"GB2-05":{"draws":0,"losses":35,"wins":55},"GB2-06":{"draws":3,"losses":16,"wins":57},"GB2-07":{"draws":0,"losses":17,"wins":59},"GB2-08":{"draws":0,"losses":12,"wins":72}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1789.6986255095305,"GB2-02":1707.3717186637177,"GB2-03":1659.0010157114255,"GB2-04":1867.362240038843,"GB2-05":1984.5756471110153,"GB2-06":1929.4026084325167,"GB2-07":1741.7863118703656,"GB2-08":2039.7954541913955},"medium":{"GB2-01":1746.7718654981127,"GB2-02":1673.7931137310256,"GB2-04":1589.1701606113888,"GB2-05":1658.3798253586838,"GB2-06":1820.3562853548483,"GB2-07":1736.9661240517378,"GB2-08":1794.8063548988707}},"per_game_tracks":{"highest":{"GB2-01":74.5791609476971,"GB2-02":72.77270456368558,"GB2-03":67.5967962093199,"GB2-04":100.0,"GB2-05":92.46710125142182,"GB2-06":86.36800772140613,"GB2-07":72.77919861333487,"GB2-08":100.0},"medium":{"GB2-01":69.68374424625355,"GB2-02":64.79913198095714,"GB2-04":56.05592222052655,"GB2-05":63.81899142309433,"GB2-06":77.40648648738761,"GB2-07":72.16061484597145,"GB2-08":74.18412112706072}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.32037116335817,"medium":66.05883395789598},"reasoning_agg":{"highest":{"max":100.0,"mean":83.32037116335817,"min":67.5967962093199},"medium":{"max":77.40648648738761,"mean":66.05883395789598,"min":56.05592222052655}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":17.26153720546219},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":81.32660400680125,"reliability_score":85.86494262172171,"uncertainty_avg":14.135057378278294,"uncertainty_penalty":-1.9937671565569275},"medium":{"ceiling_score":77.40648648738761,"expected_score":77.10319408946961,"reliability_score":86.0496501762801,"uncertainty_avg":13.950349823719906,"uncertainty_penalty":11.044360131573626}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:e3a8c6d4d5f3bdeb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":74.7135625446535,"highest":80.00582303982326,"medium":75.96881544186866,"none":70.79162335985623},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["end_turn"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[128000],"total_output_tokens":1230744,"total_reasoning_output_tokens":878158,"total_visible_output_tokens":352586,"visible_token_observations":48},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-08-15T00:11:21Z","match_totals_all":{"draws":473,"losses":542,"wins":2180},"match_totals_tracks":{"highest":{"draws":52,"losses":140,"wins":586},"medium":{"draws":160,"losses":187,"wins":785},"none":{"draws":261,"losses":215,"wins":809}},"model_slug":"claude-opus-5","overall":{"max":100.0,"mean":72.63357209239122,"min":51.301004509305145},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.28936991672205,"GB2-02":67.36660657293471,"GB2-03":92.59586913113255,"GB2-04":82.0434973958146,"GB2-05":87.48023052744581,"GB2-07":100.0,"GB2-08":72.26518773471317},"per_game_all":{"GB2-01":64.44491396001625,"GB2-02":63.91182258587035,"GB2-03":80.5508933898234,"GB2-04":61.56058023557612,"GB2-05":88.23355653916845,"GB2-07":89.60341852050732,"GB2-08":74.6897525816126},"per_game_match_totals_all":{"GB2-01":{"draws":111,"losses":100,"wins":276},"GB2-02":{"draws":141,"losses":35,"wins":188},"GB2-03":{"draws":37,"losses":67,"wins":268},"GB2-04":{"draws":164,"losses":111,"wins":203},"GB2-05":{"draws":0,"losses":59,"wins":445},"GB2-06":{"draws":6,"losses":4,"wins":74},"GB2-07":{"draws":0,"losses":47,"wins":261},"GB2-08":{"draws":14,"losses":119,"wins":465}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":41,"wins":68},"GB2-02":{"draws":30,"losses":13,"wins":47},"GB2-03":{"draws":0,"losses":9,"wins":83},"GB2-04":{"draws":21,"losses":17,"wins":102},"GB2-05":{"draws":0,"losses":20,"wins":100},"GB2-07":{"draws":0,"losses":1,"wins":67},"GB2-08":{"draws":0,"losses":39,"wins":119}},"medium":{"GB2-01":{"draws":18,"losses":43,"wins":113},"GB2-02":{"draws":54,"losses":10,"wins":60},"GB2-03":{"draws":8,"losses":14,"wins":112},"GB2-04":{"draws":80,"losses":45,"wins":49},"GB2-05":{"draws":0,"losses":22,"wins":164},"GB2-07":{"draws":0,"losses":27,"wins":131},"GB2-08":{"draws":0,"losses":26,"wins":156}},"none":{"GB2-01":{"draws":92,"losses":16,"wins":95},"GB2-02":{"draws":57,"losses":12,"wins":81},"GB2-03":{"draws":29,"losses":44,"wins":73},"GB2-04":{"draws":63,"losses":49,"wins":52},"GB2-05":{"draws":0,"losses":17,"wins":181},"GB2-06":{"draws":6,"losses":4,"wins":74},"GB2-07":{"draws":0,"losses":19,"wins":63},"GB2-08":{"draws":14,"losses":54,"wins":190}}},"per_game_raw_elo_all":{"GB2-01":1692.5590076570188,"GB2-02":1671.9603243255551,"GB2-03":1744.7615990295783,"GB2-04":1621.2046555540285,"GB2-05":1936.463358716431,"GB2-07":1905.106244971849,"GB2-08":1796.9861683062536},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1641.152563313432,"GB2-02":1694.6686240486547,"GB2-03":1837.3301063724912,"GB2-04":1756.1344548669742,"GB2-05":1935.02209164043,"GB2-07":2007.7650814322424,"GB2-08":1777.792006324548},"medium":{"GB2-01":1733.9815154005573,"GB2-02":1668.274080690368,"GB2-03":1810.7920166159938,"GB2-04":1553.2200909613516,"GB2-05":1911.2358757943127,"GB2-07":1883.547354485846,"GB2-08":1888.389709769168},"none":{"GB2-01":1702.542944257067,"GB2-02":1652.9382682376422,"GB2-03":1586.1626741002503,"GB2-04":1554.25942083376,"GB2-05":1963.1321087145507,"GB2-06":1957.933835666878,"GB2-07":1824.0062989974588,"GB2-08":1724.7767888250444}},"per_game_tracks":{"highest":{"GB2-01":58.28936991672205,"GB2-02":67.36660657293471,"GB2-03":92.59586913113255,"GB2-04":82.0434973958146,"GB2-05":87.48023052744581,"GB2-07":100.0,"GB2-08":72.26518773471317},"medium":{"GB2-01":68.96857780411901,"GB2-02":63.392777513578906,"GB2-03":90.23843179247481,"GB2-04":51.33723880160861,"GB2-05":86.25800515426019,"GB2-07":87.44155540902236,"GB2-08":84.14512161801667},"none":{"GB2-01":66.07679415920771,"GB2-02":60.97608367109741,"GB2-03":58.81837924586282,"GB2-04":51.301004509305145,"GB2-05":90.96243393579934,"GB2-06":89.17064281296983,"GB2-07":81.36870015249958,"GB2-08":67.65894839210796}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":75.95868536285322,"medium":73.47462325689973,"none":68.46740765742071},"reasoning_agg":{"highest":{"max":100.0,"mean":75.95868536285322,"min":58.28936991672205},"medium":{"max":90.23843179247481,"mean":73.47462325689973,"min":51.33723880160861},"none":{"max":90.96243393579934,"mean":68.46740765742071,"min":51.301004509305145}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":85.46364840764097,"reasoning_variance":7.491277705432509,"reliability_score":85.89456696508026,"uncertainty_avg":14.10543303491974,"uncertainty_penalty":12.830076315249755},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":78.17000503520535,"reliability_score":79.0373193749807,"uncertainty_avg":20.9626806250193,"uncertainty_penalty":2.2113196723521327},"medium":{"ceiling_score":90.23843179247481,"expected_score":86.126060295048,"reliability_score":87.956748615296,"uncertainty_avg":12.043251384704012,"uncertainty_penalty":12.651437038148273},"none":{"ceiling_score":90.96243393579934,"expected_score":93.08301990608581,"reliability_score":90.54310198501058,"uncertainty_avg":9.456898014989422,"uncertainty_penalty":24.6156122486651}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:355993239c1ccc35","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":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.832505},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.0229249999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.832505},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983750000002},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":69.85630076191231,"highest":87.33240524426331,"medium":66.4740090857523,"none":55.76248795572134},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":266468,"total_reasoning_output_tokens":151113,"total_visible_output_tokens":115355,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-08-23T05:21:14Z","match_totals_all":{"draws":290,"losses":391,"wins":1393},"match_totals_tracks":{"highest":{"draws":31,"losses":70,"wins":585},"medium":{"draws":98,"losses":149,"wins":443},"none":{"draws":161,"losses":172,"wins":365}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":69.85630076191232,"min":27.127464596852075},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.89182828429095,"GB2-02":100.0,"GB2-03":100.0,"GB2-04":91.32241413921264,"GB2-05":63.917443301992066,"GB2-06":93.18006300131891,"GB2-07":98.38140095757626,"GB2-08":80.96609226971566},"per_game_all":{"GB2-01":70.20307680071818,"GB2-02":60.55154075522892,"GB2-03":73.4809427514948,"GB2-04":74.67649092897192,"GB2-05":64.51524154412141,"GB2-06":64.93354543334773,"GB2-07":78.66180326485171,"GB2-08":71.82776461656387},"per_game_match_totals_all":{"GB2-01":{"draws":20,"losses":64,"wins":182},"GB2-02":{"draws":112,"losses":6,"wins":88},"GB2-03":{"draws":45,"losses":47,"wins":176},"GB2-04":{"draws":73,"losses":20,"wins":145},"GB2-05":{"draws":0,"losses":76,"wins":196},"GB2-06":{"draws":10,"losses":82,"wins":183},"GB2-07":{"draws":0,"losses":49,"wins":226},"GB2-08":{"draws":30,"losses":47,"wins":197}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":21,"wins":66},"GB2-02":{"draws":13,"losses":0,"wins":55},"GB2-03":{"draws":1,"losses":5,"wins":84},"GB2-04":{"draws":8,"losses":2,"wins":68},"GB2-05":{"draws":0,"losses":23,"wins":65},"GB2-06":{"draws":6,"losses":1,"wins":83},"GB2-07":{"draws":0,"losses":1,"wins":89},"GB2-08":{"draws":0,"losses":17,"wins":75}},"medium":{"GB2-01":{"draws":17,"losses":23,"wins":48},"GB2-02":{"draws":40,"losses":1,"wins":27},"GB2-03":{"draws":9,"losses":24,"wins":55},"GB2-04":{"draws":11,"losses":3,"wins":64},"GB2-05":{"draws":0,"losses":17,"wins":77},"GB2-06":{"draws":1,"losses":53,"wins":38},"GB2-07":{"draws":0,"losses":11,"wins":81},"GB2-08":{"draws":20,"losses":17,"wins":53}},"none":{"GB2-01":{"draws":0,"losses":20,"wins":68},"GB2-02":{"draws":59,"losses":5,"wins":6},"GB2-03":{"draws":35,"losses":18,"wins":37},"GB2-04":{"draws":54,"losses":15,"wins":13},"GB2-05":{"draws":0,"losses":36,"wins":54},"GB2-06":{"draws":3,"losses":28,"wins":62},"GB2-07":{"draws":0,"losses":37,"wins":56},"GB2-08":{"draws":10,"losses":13,"wins":69}}},"per_game_raw_elo_all":{"GB2-01":1745.1709856860264,"GB2-02":1653.0768593593723,"GB2-03":1685.6366741110885,"GB2-04":1705.7656500626647,"GB2-05":1666.1052125495428,"GB2-06":1668.1303848002815,"GB2-07":1795.5754334047585,"GB2-08":1770.5137884199432},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.5204705553888,"GB2-02":1830.0318043667605,"GB2-03":1873.3759975611176,"GB2-04":1813.5063596110099,"GB2-05":1659.9607128670973,"GB2-06":2004.117017853337,"GB2-07":1985.9471428986744,"GB2-08":1857.759542012682},"medium":{"GB2-01":1656.0651074364548,"GB2-02":1626.3155963816746,"GB2-03":1641.1519271610578,"GB2-04":1805.933180290257,"GB2-05":1818.8752339259834,"GB2-06":1334.769380358261,"GB2-07":1852.419205680889,"GB2-08":1652.2299897743615},"none":{"GB2-01":1827.927379066235,"GB2-02":1502.8831773296815,"GB2-03":1542.3820976110903,"GB2-04":1497.857410286727,"GB2-05":1519.479690855548,"GB2-06":1665.5047561892463,"GB2-07":1548.3599516347117,"GB2-08":1801.5518334727867}},"per_game_tracks":{"highest":{"GB2-01":70.89182828429095,"GB2-02":100.0,"GB2-03":100.0,"GB2-04":91.32241413921264,"GB2-05":63.917443301992066,"GB2-06":93.18006300131891,"GB2-07":98.38140095757626,"GB2-08":80.96609226971566},"medium":{"GB2-01":60.974479549744906,"GB2-02":54.52715766883468,"GB2-03":67.15840316174446,"GB2-04":90.14837149543118,"GB2-05":78.10288928195592,"GB2-06":36.8828822319936,"GB2-07":84.56963011340204,"GB2-08":59.42825918291155},"none":{"GB2-01":78.74292256811869,"GB2-02":27.127464596852075,"GB2-03":53.28442509273992,"GB2-04":42.558687152271936,"GB2-05":51.525392048416236,"GB2-06":64.73769106673069,"GB2-07":53.034378723576836,"GB2-08":75.08894239706439}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":87.33240524426331,"medium":66.4740090857523,"none":55.76248795572135},"reasoning_agg":{"highest":{"max":100.0,"mean":87.33240524426331,"min":63.917443301992066},"medium":{"max":90.14837149543118,"mean":66.4740090857523,"min":36.8828822319936},"none":{"max":78.74292256811869,"mean":55.76248795572135,"min":27.127464596852075}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":75.4094475799581,"reasoning_variance":31.569917288541966,"reliability_score":90.0897289119552,"uncertainty_avg":9.910271088044789,"uncertainty_penalty":5.553146818045775},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":86.391088765996,"reliability_score":89.88102904119891,"uncertainty_avg":10.118970958801091,"uncertainty_penalty":-0.9413164782673107},"medium":{"ceiling_score":90.14837149543118,"expected_score":70.54971128744982,"reliability_score":90.01807018709775,"uncertainty_avg":9.981929812902244,"uncertainty_penalty":4.075702201697524},"none":{"ceiling_score":78.74292256811869,"expected_score":69.28754268642847,"reliability_score":90.37008750756897,"uncertainty_avg":9.629912492431034,"uncertainty_penalty":13.525054730707119}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:b646b36fcd253b5f","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":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.152239999999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.187937500000002},"codegen_output_tokens":{"attempt_count":27,"output_max":146534,"output_mean":40675.041666666664,"output_min":3180,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":146534,"output_mean":99672.5,"output_min":71368,"run_count":8},"medium":{"attempt_count":8,"output_max":26272,"output_mean":17600.375,"output_min":12941,"run_count":8},"none":{"attempt_count":10,"output_max":8643,"output_mean":4752.25,"output_min":3180,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":60.47233758029783,"highest":75.1839038927245,"medium":54.9575991334922,"none":43.47321666269807},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-08-23T08:23:52Z","match_totals_all":{"draws":511,"losses":484,"wins":1094},"match_totals_tracks":{"highest":{"draws":84,"losses":74,"wins":481},"medium":{"draws":211,"losses":170,"wins":349},"none":{"draws":216,"losses":240,"wins":264}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":57.04876585166363,"min":17.905822221963863},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.06137796160141,"GB2-03":38.881693886910185,"GB2-04":59.29009953663199,"GB2-05":94.27284751416232,"GB2-06":89.25646806706095,"GB2-07":90.48850476973648,"GB2-08":59.03633551296827},"per_game_all":{"GB2-01":89.41492349026284,"GB2-03":36.92356512678595,"GB2-04":39.05386520608471,"GB2-05":77.33647132265067,"GB2-06":82.82553515156162,"GB2-07":54.245588867092714,"GB2-08":43.506413897646325},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":24,"wins":250},"GB2-02":{"draws":129,"losses":14,"wins":6},"GB2-03":{"draws":123,"losses":88,"wins":66},"GB2-04":{"draws":126,"losses":66,"wins":55},"GB2-05":{"draws":0,"losses":50,"wins":230},"GB2-06":{"draws":10,"losses":32,"wins":242},"GB2-07":{"draws":0,"losses":129,"wins":161},"GB2-08":{"draws":119,"losses":81,"wins":84}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":3,"wins":89},"GB2-03":{"draws":27,"losses":30,"wins":36},"GB2-04":{"draws":43,"losses":4,"wins":35},"GB2-05":{"draws":0,"losses":1,"wins":93},"GB2-06":{"draws":3,"losses":6,"wins":87},"GB2-07":{"draws":0,"losses":7,"wins":89},"GB2-08":{"draws":11,"losses":23,"wins":52}},"medium":{"GB2-01":{"draws":0,"losses":1,"wins":91},"GB2-02":{"draws":68,"losses":4,"wins":5},"GB2-03":{"draws":46,"losses":24,"wins":20},"GB2-04":{"draws":41,"losses":33,"wins":8},"GB2-05":{"draws":0,"losses":17,"wins":79},"GB2-06":{"draws":3,"losses":8,"wins":81},"GB2-07":{"draws":0,"losses":60,"wins":38},"GB2-08":{"draws":53,"losses":23,"wins":27}},"none":{"GB2-01":{"draws":4,"losses":20,"wins":70},"GB2-02":{"draws":61,"losses":10,"wins":1},"GB2-03":{"draws":50,"losses":34,"wins":10},"GB2-04":{"draws":42,"losses":29,"wins":12},"GB2-05":{"draws":0,"losses":32,"wins":58},"GB2-06":{"draws":4,"losses":18,"wins":74},"GB2-07":{"draws":0,"losses":62,"wins":34},"GB2-08":{"draws":55,"losses":35,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1930.0823514178549,"GB2-03":1425.9382158471951,"GB2-04":1475.162129519729,"GB2-05":1810.3714616839707,"GB2-06":1880.0603400586833,"GB2-07":1559.249355560359,"GB2-08":1499.0032521511794},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1984.8430422639274,"GB2-03":1439.6598711541665,"GB2-04":1605.7836316615358,"GB2-05":2001.572693385237,"GB2-06":1956.1813224870132,"GB2-07":1908.5825702078523,"GB2-08":1649.4348299353023},"medium":{"GB2-01":2032.611031916279,"GB2-02":1495.2440690369426,"GB2-03":1467.8365938246095,"GB2-04":1398.7939198480567,"GB2-05":1852.929717172452,"GB2-06":1895.3746720098352,"GB2-07":1393.4711027318722,"GB2-08":1478.0480758610206},"none":{"GB2-01":1772.7929800733582,"GB2-02":1460.9158431127426,"GB2-03":1370.3181825628085,"GB2-04":1420.908837049594,"GB2-05":1576.611974494223,"GB2-06":1788.6250256792016,"GB2-07":1375.6943937413528,"GB2-08":1369.526850657215}},"per_game_tracks":{"highest":{"GB2-01":95.06137796160141,"GB2-03":38.881693886910185,"GB2-04":59.29009953663199,"GB2-05":94.27284751416232,"GB2-06":89.25646806706095,"GB2-07":90.48850476973648,"GB2-08":59.03633551296827},"medium":{"GB2-01":100.0,"GB2-02":25.90894221037543,"GB2-03":42.7632763142804,"GB2-04":27.2012319421299,"GB2-05":81.15458170352487,"GB2-06":84.06596764154368,"GB2-07":37.06804835684683,"GB2-08":41.49874489923657},"none":{"GB2-01":73.18339250918713,"GB2-02":17.905822221963863,"GB2-03":29.125725179167283,"GB2-04":30.67026413949224,"GB2-05":56.581984750264844,"GB2-06":75.15416974608023,"GB2-07":35.18021347469483,"GB2-08":29.98416128073413}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.71548175880062,"medium":54.95759913349221,"none":43.47321666269807},"reasoning_agg":{"highest":{"max":95.06137796160141,"mean":72.71548175880062,"min":38.881693886910185},"medium":{"max":100.0,"mean":54.95759913349221,"min":25.90894221037543},"none":{"max":75.15416974608023,"mean":43.47321666269807,"min":17.905822221963863}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":60.584246782340294,"reasoning_variance":29.24226509610255,"reliability_score":91.94467074109805,"uncertainty_avg":8.055329258901946,"uncertainty_penalty":3.5354809306766626},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":95.06137796160141,"expected_score":67.07132370933192,"reliability_score":91.64429458516922,"uncertainty_avg":8.355705414830778,"uncertainty_penalty":-5.6441580494687},"medium":{"ceiling_score":100.0,"expected_score":52.680680188677144,"reliability_score":91.54329677307489,"uncertainty_avg":8.45670322692512,"uncertainty_penalty":-2.2769189448150655},"none":{"ceiling_score":75.15416974608023,"expected_score":52.23341660282408,"reliability_score":91.16840299712256,"uncertainty_avg":8.831597002877439,"uncertainty_penalty":8.760199940126007}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:d65de196562f343c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087455999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087455999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998543999999998},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":55.237675475363496,"highest":62.11035404695588,"medium":57.18093497771301,"none":46.42173740142161},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"reasoning_token_observations":34,"total_output_tokens":187391,"total_reasoning_output_tokens":5791,"total_visible_output_tokens":181600,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-08-23T13:45:16Z","match_totals_all":{"draws":786,"losses":907,"wins":1496},"match_totals_tracks":{"highest":{"draws":233,"losses":327,"wins":660},"medium":{"draws":170,"losses":208,"wins":366},"none":{"draws":383,"losses":372,"wins":470}},"model_slug":"x-ai-grok-4-5","overall":{"max":91.324739517719,"mean":55.237675475363496,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.00202184525405,"GB2-02":52.06793491447559,"GB2-03":42.0930986190164,"GB2-04":32.41381726074275,"GB2-05":76.16684999097536,"GB2-06":56.128166821353254,"GB2-07":65.68620340611055,"GB2-08":91.324739517719},"per_game_all":{"GB2-01":67.46588283073301,"GB2-02":35.97246557609851,"GB2-03":30.016538676885943,"GB2-04":35.783800620505275,"GB2-05":63.41989456597664,"GB2-06":52.29093272893224,"GB2-07":68.92736759148677,"GB2-08":88.02452121228959},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":62,"wins":218},"GB2-02":{"draws":236,"losses":41,"wins":62},"GB2-03":{"draws":122,"losses":180,"wins":62},"GB2-04":{"draws":225,"losses":85,"wins":63},"GB2-05":{"draws":0,"losses":155,"wins":238},"GB2-06":{"draws":37,"losses":196,"wins":212},"GB2-07":{"draws":0,"losses":129,"wins":271},"GB2-08":{"draws":3,"losses":59,"wins":370}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":30,"losses":14,"wins":116},"GB2-02":{"draws":68,"losses":19,"wins":47},"GB2-03":{"draws":62,"losses":53,"wins":29},"GB2-04":{"draws":59,"losses":52,"wins":35},"GB2-05":{"draws":0,"losses":37,"wins":97},"GB2-06":{"draws":12,"losses":75,"wins":87},"GB2-07":{"draws":0,"losses":57,"wins":101},"GB2-08":{"draws":2,"losses":20,"wins":148}},"medium":{"GB2-01":{"draws":7,"losses":14,"wins":65},"GB2-02":{"draws":61,"losses":13,"wins":10},"GB2-03":{"draws":19,"losses":23,"wins":24},"GB2-04":{"draws":75,"losses":13,"wins":12},"GB2-05":{"draws":0,"losses":37,"wins":65},"GB2-06":{"draws":7,"losses":55,"wins":50},"GB2-07":{"draws":0,"losses":40,"wins":60},"GB2-08":{"draws":1,"losses":13,"wins":80}},"none":{"GB2-01":{"draws":126,"losses":34,"wins":37},"GB2-02":{"draws":107,"losses":9,"wins":5},"GB2-03":{"draws":41,"losses":104,"wins":9},"GB2-04":{"draws":91,"losses":20,"wins":16},"GB2-05":{"draws":0,"losses":81,"wins":76},"GB2-06":{"draws":18,"losses":66,"wins":75},"GB2-07":{"draws":0,"losses":32,"wins":110},"GB2-08":{"draws":0,"losses":26,"wins":142}}},"per_game_raw_elo_all":{"GB2-01":1710.7307568003332,"GB2-02":1533.0460714613419,"GB2-03":1373.6623110081794,"GB2-04":1446.2996247330366,"GB2-05":1647.1598671438687,"GB2-06":1509.5248120359654,"GB2-07":1695.2210548129142,"GB2-08":1917.9190403295252},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1838.9026372811668,"GB2-02":1601.5705707988113,"GB2-03":1454.3749817413207,"GB2-04":1421.5035179780361,"GB2-05":1790.3881365012405,"GB2-06":1552.1910999620195,"GB2-07":1660.7238466980018,"GB2-08":1945.9379565959005},"medium":{"GB2-01":1798.3560336460778,"GB2-02":1503.3810335953954,"GB2-03":1511.5686533652022,"GB2-04":1485.6292037741962,"GB2-05":1664.3804338059472,"GB2-06":1460.828057804587,"GB2-07":1660.3057314183425,"GB2-08":1917.0549563802338},"none":{"GB2-01":1494.9335994737546,"GB2-02":1494.1866099898193,"GB2-03":1155.0432979180157,"GB2-04":1431.7661524468779,"GB2-05":1486.7110311244185,"GB2-06":1515.5552783412897,"GB2-07":1764.6335863223985,"GB2-08":1890.764208012442}},"per_game_tracks":{"highest":{"GB2-01":81.00202184525405,"GB2-02":52.06793491447559,"GB2-03":42.0930986190164,"GB2-04":32.41381726074275,"GB2-05":76.16684999097536,"GB2-06":56.128166821353254,"GB2-07":65.68620340611055,"GB2-08":91.324739517719},"medium":{"GB2-01":75.63550927040828,"GB2-02":28.15047326894219,"GB2-03":47.956517411641435,"GB2-04":41.29925429844576,"GB2-05":64.57296544365413,"GB2-06":47.816521510440936,"GB2-07":64.8042465369897,"GB2-08":87.21199208118166},"none":{"GB2-01":45.760117376536684,"GB2-02":27.69898854487774,"GB2-03":0.0,"GB2-04":33.63833030232732,"GB2-05":49.519868263300424,"GB2-06":52.928109855002525,"GB2-07":76.29165283136004,"GB2-08":85.5368320379681}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":62.11035404695588,"medium":57.180934977713015,"none":46.42173740142161},"reasoning_agg":{"highest":{"max":91.324739517719,"mean":62.11035404695588,"min":32.41381726074275},"medium":{"max":87.21199208118166,"mean":57.180934977713015,"min":28.15047326894219},"none":{"max":85.5368320379681,"mean":46.42173740142161,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":91.324739517719,"expected_score":51.97546340676748,"reasoning_variance":15.688616645534267,"reliability_score":97.16707690946767,"uncertainty_avg":2.8329230905323337,"uncertainty_penalty":-3.262212068596014},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":91.324739517719,"expected_score":48.344846755314144,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-13.765507291641732},"medium":{"ceiling_score":87.21199208118166,"expected_score":55.85616871789083,"reliability_score":91.7464865840803,"uncertainty_avg":8.253513415919693,"uncertainty_penalty":-1.3247662598221837},"none":{"ceiling_score":85.5368320379681,"expected_score":51.72537474709748,"reliability_score":99.75474414432269,"uncertainty_avg":0.2452558556773099,"uncertainty_penalty":5.303637345675874}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:66e9f46ea7415508","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-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":7.44989},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449889999999999}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":55.52178225991953,"highest":68.9074703488038,"medium":47.42768341066297,"none":49.15100352600053},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":31,"output_token_observations":25,"total_output_tokens":356249},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-08-05T03:49:27Z","match_totals_all":{"draws":484,"losses":473,"wins":839},"match_totals_tracks":{"highest":{"draws":71,"losses":146,"wins":355},"medium":{"draws":266,"losses":166,"wins":238},"none":{"draws":147,"losses":161,"wins":246}},"model_slug":"claude-opus-4-8","overall":{"max":80.14817108632784,"mean":53.87002875976319,"min":15.975113871358344},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.87170060837425,"GB2-02":79.43336636141659,"GB2-04":61.996358539488305,"GB2-05":53.60093706896381,"GB2-06":79.45887582150341,"GB2-07":77.77956211899175,"GB2-08":70.21149192288846},"per_game_all":{"GB2-01":53.06456893181803,"GB2-02":38.18527423229226,"GB2-04":47.69670314405272,"GB2-05":50.303100214998246,"GB2-06":72.6055057057419,"GB2-07":67.41401891798363,"GB2-08":59.38330467254994},"per_game_match_totals_all":{"GB2-01":{"draws":50,"losses":76,"wins":126},"GB2-02":{"draws":154,"losses":11,"wins":43},"GB2-03":{"draws":33,"losses":12,"wins":9},"GB2-04":{"draws":162,"losses":38,"wins":48},"GB2-05":{"draws":0,"losses":153,"wins":155},"GB2-06":{"draws":10,"losses":48,"wins":162},"GB2-07":{"draws":0,"losses":74,"wins":170},"GB2-08":{"draws":75,"losses":61,"wins":126}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":25,"wins":52},"GB2-02":{"draws":27,"losses":2,"wins":39},"GB2-04":{"draws":29,"losses":16,"wins":35},"GB2-05":{"draws":0,"losses":55,"wins":53},"GB2-06":{"draws":2,"losses":8,"wins":52},"GB2-07":{"draws":0,"losses":17,"wins":61},"GB2-08":{"draws":0,"losses":23,"wins":63}},"medium":{"GB2-01":{"draws":17,"losses":33,"wins":36},"GB2-02":{"draws":64,"losses":5,"wins":1},"GB2-03":{"draws":33,"losses":12,"wins":9},"GB2-04":{"draws":77,"losses":10,"wins":5},"GB2-05":{"draws":0,"losses":48,"wins":62},"GB2-06":{"draws":0,"losses":13,"wins":63},"GB2-07":{"draws":0,"losses":27,"wins":57},"GB2-08":{"draws":75,"losses":18,"wins":5}},"none":{"GB2-01":{"draws":20,"losses":18,"wins":38},"GB2-02":{"draws":63,"losses":4,"wins":3},"GB2-04":{"draws":56,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":50,"wins":40},"GB2-06":{"draws":8,"losses":27,"wins":47},"GB2-07":{"draws":0,"losses":30,"wins":52},"GB2-08":{"draws":0,"losses":20,"wins":58}}},"per_game_raw_elo_all":{"GB2-01":1580.6246228560794,"GB2-02":1552.6493392272384,"GB2-04":1530.9301348640095,"GB2-05":1503.1417316644847,"GB2-06":1764.3576555359796,"GB2-07":1689.747497681641,"GB2-08":1652.5651717299604},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1644.9301421808211,"GB2-02":1737.894247067,"GB2-04":1623.7791355637896,"GB2-05":1539.312046490709,"GB2-06":1849.5527583256137,"GB2-07":1790.5232339769955,"GB2-08":1756.3114534666295},"medium":{"GB2-01":1490.1750231054355,"GB2-02":1452.9211674035894,"GB2-03":1459.3652413928949,"GB2-04":1474.5093095901468,"GB2-05":1581.5207424969149,"GB2-06":1852.9315796761991,"GB2-07":1702.8026322218134,"GB2-08":1408.511822163267},"none":{"GB2-01":1606.7687032819815,"GB2-02":1467.1326032111256,"GB2-04":1494.501959438092,"GB2-05":1388.5924060058305,"GB2-06":1590.5886286061254,"GB2-07":1575.9166268461142,"GB2-08":1792.8722395599843}},"per_game_tracks":{"highest":{"GB2-01":59.87170060837425,"GB2-02":79.43336636141659,"GB2-04":61.996358539488305,"GB2-05":53.60093706896381,"GB2-06":79.45887582150341,"GB2-07":77.77956211899175,"GB2-08":70.21149192288846},"medium":{"GB2-01":43.773386925532954,"GB2-02":15.975113871358344,"GB2-03":39.87335695062395,"GB2-04":39.31546308499324,"GB2-05":57.367379627273316,"GB2-06":80.14817108632784,"GB2-07":68.84294122769712,"GB2-08":34.12565451149703},"none":{"GB2-01":55.548619261546875,"GB2-02":19.14734246410184,"GB2-04":41.77828780767661,"GB2-05":39.940983948757605,"GB2-06":58.20947020939446,"GB2-07":55.619553407262025,"GB2-08":73.81276758326433}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.64511476210285,"medium":47.42768341066297,"none":47.53728810652374},"reasoning_agg":{"highest":{"max":79.45887582150341,"mean":66.64511476210285,"min":53.60093706896381},"medium":{"max":80.14817108632784,"mean":47.42768341066297,"min":15.975113871358344},"none":{"max":73.81276758326433,"mean":47.53728810652374,"min":19.14734246410184}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":80.14817108632784,"expected_score":55.59039308775105,"reasoning_variance":19.217431351439878,"reliability_score":88.78068177698829,"uncertainty_avg":11.219318223011717,"uncertainty_penalty":1.7203643279878662},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.45887582150341,"expected_score":62.638974238485154,"reliability_score":88.19169445447774,"uncertainty_avg":11.808305545522256,"uncertainty_penalty":-4.006140523617695},"medium":{"ceiling_score":80.14817108632784,"expected_score":43.29840619697912,"reliability_score":88.60812826631295,"uncertainty_avg":11.391871733687054,"uncertainty_penalty":-4.129277213683849},"none":{"ceiling_score":73.81276758326433,"expected_score":56.61424279318782,"reliability_score":87.78820625122599,"uncertainty_avg":12.211793748774008,"uncertainty_penalty":9.076954686664081}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:6c8c03d567738842","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-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"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-2026-08-08":26},"run_count":24,"token_priced_attempt_count":26,"total":26.56635},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":55.832809143534746,"highest":69.79119288611703,"medium":53.08734861096748,"none":40.54520036195957},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"total_output_tokens":851788},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:23:57Z","match_totals_all":{"draws":649,"losses":459,"wins":724},"match_totals_tracks":{"highest":{"draws":107,"losses":115,"wins":322},"medium":{"draws":224,"losses":187,"wins":265},"none":{"draws":318,"losses":157,"wins":137}},"model_slug":"gpt-5-5","overall":{"max":93.82012264656494,"mean":53.267066860444224,"min":19.58339791797017},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.59314019339122,"GB2-03":49.69220134120665,"GB2-04":31.278757459984458,"GB2-05":86.85420097557086,"GB2-06":82.54672029424074,"GB2-07":93.82012264656494,"GB2-08":73.75320729186035},"per_game_all":{"GB2-01":59.40568400507138,"GB2-03":42.529550160535955,"GB2-04":37.25309863843188,"GB2-05":70.04802213472018,"GB2-07":70.60707728961167,"GB2-08":55.15342263283734},"per_game_match_totals_all":{"GB2-01":{"draws":165,"losses":33,"wins":76},"GB2-02":{"draws":100,"losses":15,"wins":17},"GB2-03":{"draws":91,"losses":68,"wins":49},"GB2-04":{"draws":159,"losses":59,"wins":36},"GB2-05":{"draws":0,"losses":71,"wins":167},"GB2-06":{"draws":4,"losses":75,"wins":101},"GB2-07":{"draws":0,"losses":78,"wins":182},"GB2-08":{"draws":130,"losses":60,"wins":96}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":12,"wins":41},"GB2-03":{"draws":24,"losses":24,"wins":20},"GB2-04":{"draws":43,"losses":27,"wins":6},"GB2-05":{"draws":0,"losses":13,"wins":67},"GB2-06":{"draws":3,"losses":11,"wins":54},"GB2-07":{"draws":0,"losses":6,"wins":76},"GB2-08":{"draws":12,"losses":22,"wins":58}},"medium":{"GB2-01":{"draws":56,"losses":6,"wins":24},"GB2-02":{"draws":35,"losses":8,"wins":17},"GB2-03":{"draws":32,"losses":21,"wins":13},"GB2-04":{"draws":58,"losses":16,"wins":20},"GB2-05":{"draws":0,"losses":26,"wins":54},"GB2-06":{"draws":1,"losses":64,"wins":47},"GB2-07":{"draws":0,"losses":25,"wins":55},"GB2-08":{"draws":42,"losses":21,"wins":35}},"none":{"GB2-01":{"draws":84,"losses":15,"wins":11},"GB2-02":{"draws":65,"losses":7,"wins":0},"GB2-03":{"draws":35,"losses":23,"wins":16},"GB2-04":{"draws":58,"losses":16,"wins":10},"GB2-05":{"draws":0,"losses":32,"wins":46},"GB2-07":{"draws":0,"losses":47,"wins":51},"GB2-08":{"draws":76,"losses":17,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1640.4427273802812,"GB2-03":1471.9858937571917,"GB2-04":1463.0644150519609,"GB2-05":1731.458394044459,"GB2-07":1719.2643153199162,"GB2-08":1610.1795192196996},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.7035828845744,"GB2-03":1523.1530595800598,"GB2-04":1426.7745846890361,"GB2-05":1921.1578815317785,"GB2-06":1884.0000254094712,"GB2-07":1943.974131521536,"GB2-08":1788.7771703951637},"medium":{"GB2-01":1638.442124593186,"GB2-02":1565.48401992745,"GB2-03":1437.8225277095194,"GB2-04":1475.1158867823526,"GB2-05":1723.253047437652,"GB2-06":1482.81989412051,"GB2-07":1752.1617029482936,"GB2-08":1612.390503669571},"none":{"GB2-01":1531.1824746630828,"GB2-02":1468.431303811449,"GB2-03":1454.9820939819956,"GB2-04":1487.3027736844938,"GB2-05":1549.9642531639468,"GB2-07":1461.6571114899198,"GB2-08":1429.3708835943642}},"per_game_tracks":{"highest":{"GB2-01":70.59314019339122,"GB2-03":49.69220134120665,"GB2-04":31.278757459984458,"GB2-05":86.85420097557086,"GB2-06":82.54672029424074,"GB2-07":93.82012264656494,"GB2-08":73.75320729186035},"medium":{"GB2-01":59.10237984120693,"GB2-02":40.26540457323291,"GB2-03":37.548190679008606,"GB2-04":39.477544864233046,"GB2-05":69.3382874498687,"GB2-06":49.66745425520703,"GB2-07":73.85605709393225,"GB2-08":55.44347013105038},"none":{"GB2-01":48.52153198061598,"GB2-02":19.58339791797017,"GB2-03":40.34825846139262,"GB2-04":41.00299359107813,"GB2-05":53.951577978721,"GB2-07":44.145052128337795,"GB2-08":36.263590475601305}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":67.49982310677103,"medium":53.08734861096748,"none":39.214028863594145},"reasoning_agg":{"highest":{"max":93.82012264656494,"mean":67.49982310677103,"min":31.278757459984458},"medium":{"max":73.85605709393225,"mean":53.08734861096748,"min":37.548190679008606},"none":{"max":53.951577978721,"mean":39.214028863594145,"min":19.58339791797017}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":93.82012264656494,"expected_score":55.61817350728371,"reasoning_variance":28.285794243176888,"reliability_score":89.31865090380595,"uncertainty_avg":10.681349096194047,"uncertainty_penalty":2.351106646839483},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":93.82012264656494,"expected_score":60.65291785610514,"reliability_score":87.19202762159838,"uncertainty_avg":12.80797237840162,"uncertainty_penalty":-6.846905250665891},"medium":{"ceiling_score":73.85605709393225,"expected_score":50.98490147086344,"reliability_score":88.94915602700004,"uncertainty_avg":11.050843972999953,"uncertainty_penalty":-2.10244714010404},"none":{"ceiling_score":53.951577978721,"expected_score":51.57575463782923,"reliability_score":90.14718445353434,"uncertainty_avg":9.852815546465658,"uncertainty_penalty":12.361725774235083}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:6aba70247d100ab2","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.6379623500000005},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.169687700000001},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000002},"historical-provider-setting-intensive":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.6379623500000005}},"codegen_cost_usd":{"admitted_cell_count":42,"cell_count":24,"cost_basis_counts":{"provider_reported":126},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.531673125,"mean":0.264606278125,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":126,"run_count":48,"total":12.701101350000002},"codegen_latency_ms":{"attempt_count":122,"max_ms":348942,"mean_ms":136127.20833333334,"min_ms":17298,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":49,"max_ms":348942,"mean_ms":238985.4375,"min_ms":149523,"run_count":16},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":126,"output_max":100087,"output_mean":32301.520833333332,"output_min":2060,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":100087,"output_mean":61701.5625,"output_min":36597,"run_count":16},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":57.42791059398194,"highest":67.94613426450412,"medium":57.72594535990393,"none":37.771112166458195},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":122,"finish_reasons":["length","stop"],"indexed_attempts":126,"output_token_observations":126,"reasoning_token_observations":82,"total_output_tokens":1550473,"total_reasoning_output_tokens":771353,"total_visible_output_tokens":207435,"visible_token_observations":82},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-07"],"first_pass_admitted":8,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-08-23T13:45:16Z","match_totals_all":{"draws":1589,"losses":1780,"wins":2615},"match_totals_tracks":{"highest":{"draws":285,"losses":436,"wins":1003},"medium":{"draws":443,"losses":428,"wins":942},"none":{"draws":861,"losses":916,"wins":670}},"model_slug":"google-gemini-3-6-flash","overall":{"max":91.56194509481253,"mean":52.27760470741041,"min":16.174375669656794},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.06934497191142,"GB2-03":86.9870467732465,"GB2-04":59.70973443654603,"GB2-05":88.3817448074802,"GB2-06":91.56194509481253,"GB2-07":48.9850812289486,"GB2-08":50.92804253858354},"per_game_all":{"GB2-01":46.51892429336166,"GB2-03":62.552499106489485,"GB2-04":45.61119540212897,"GB2-05":71.8467816393129,"GB2-06":71.39887324998553,"GB2-07":53.21592635675335,"GB2-08":50.8511741098417},"per_game_match_totals_all":{"GB2-01":{"draws":259,"losses":325,"wins":280},"GB2-02":{"draws":297,"losses":27,"wins":2},"GB2-03":{"draws":173,"losses":210,"wins":289},"GB2-04":{"draws":452,"losses":158,"wins":181},"GB2-05":{"draws":0,"losses":260,"wins":657},"GB2-06":{"draws":64,"losses":267,"wins":584},"GB2-07":{"draws":0,"losses":322,"wins":403},"GB2-08":{"draws":344,"losses":211,"wins":219}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":92,"losses":103,"wins":107},"GB2-03":{"draws":9,"losses":21,"wins":82},"GB2-04":{"draws":74,"losses":83,"wins":129},"GB2-05":{"draws":0,"losses":39,"wins":235},"GB2-06":{"draws":13,"losses":37,"wins":248},"GB2-07":{"draws":0,"losses":67,"wins":87},"GB2-08":{"draws":97,"losses":86,"wins":115}},"medium":{"GB2-01":{"draws":93,"losses":39,"wins":96},"GB2-02":{"draws":74,"losses":5,"wins":1},"GB2-03":{"draws":66,"losses":108,"wins":84},"GB2-04":{"draws":172,"losses":37,"wins":30},"GB2-05":{"draws":0,"losses":77,"wins":231},"GB2-06":{"draws":17,"losses":18,"wins":257},"GB2-07":{"draws":0,"losses":111,"wins":155},"GB2-08":{"draws":21,"losses":33,"wins":88}},"none":{"GB2-01":{"draws":74,"losses":183,"wins":77},"GB2-02":{"draws":223,"losses":22,"wins":1},"GB2-03":{"draws":98,"losses":81,"wins":123},"GB2-04":{"draws":206,"losses":38,"wins":22},"GB2-05":{"draws":0,"losses":144,"wins":191},"GB2-06":{"draws":34,"losses":212,"wins":79},"GB2-07":{"draws":0,"losses":144,"wins":161},"GB2-08":{"draws":226,"losses":92,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1507.8682078154495,"GB2-03":1601.1713498907732,"GB2-04":1508.465399736752,"GB2-05":1739.4975261190611,"GB2-06":1735.7146248112779,"GB2-07":1541.9000114298806,"GB2-08":1560.5930516719425},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1531.1126584018375,"GB2-03":1776.8727510068502,"GB2-04":1597.9332057560987,"GB2-05":1928.0234348943654,"GB2-06":1975.6465528059348,"GB2-07":1500.2174214587583,"GB2-08":1561.6648885423429},"medium":{"GB2-01":1716.4746501562718,"GB2-02":1450.7870290620301,"GB2-03":1503.6464217020275,"GB2-04":1453.8314186207444,"GB2-05":1774.4665174138186,"GB2-06":1964.5138371126773,"GB2-07":1567.0074698000692,"GB2-08":1755.9191643788624},"none":{"GB2-01":1276.0173148882393,"GB2-02":1447.93655147432,"GB2-03":1522.994876963442,"GB2-04":1473.6315748334123,"GB2-05":1516.0026260489992,"GB2-06":1266.9834845152213,"GB2-07":1558.4751430308143,"GB2-08":1364.1951020946215}},"per_game_tracks":{"highest":{"GB2-01":49.06934497191142,"GB2-03":86.9870467732465,"GB2-04":59.70973443654603,"GB2-05":88.3817448074802,"GB2-06":91.56194509481253,"GB2-07":48.9850812289486,"GB2-08":50.92804253858354},"medium":{"GB2-01":67.61223768430166,"GB2-02":16.174375669656794,"GB2-03":48.783597464425156,"GB2-04":36.87160934044171,"GB2-05":74.96104522556831,"GB2-06":90.59930630959718,"GB2-07":55.64840056444847,"GB2-08":71.15699062079223},"none":{"GB2-01":22.875190223871893,"GB2-02":17.43890191914832,"GB2-03":51.88685308179679,"GB2-04":40.25224242939918,"GB2-05":52.197554884890174,"GB2-06":32.035368345546885,"GB2-07":55.01429727686298,"GB2-08":30.468489170149333}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.23100270375121,"medium":55.83069925202183,"none":37.771112166458195},"reasoning_agg":{"highest":{"max":91.56194509481253,"mean":63.23100270375121,"min":48.9850812289486},"medium":{"max":90.59930630959718,"mean":55.83069925202183,"min":16.174375669656794},"none":{"max":55.01429727686298,"mean":37.771112166458195,"min":17.43890191914832}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":91.56194509481253,"expected_score":57.28516564856882,"reasoning_variance":25.459890537293013,"reliability_score":99.40361773022518,"uncertainty_avg":0.5963822697748243,"uncertainty_penalty":5.00756094115841},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":91.56194509481253,"expected_score":59.77055604272227,"reliability_score":99.53056522583145,"uncertainty_avg":0.46943477416855117,"uncertainty_penalty":-3.4604466610289393},"medium":{"ceiling_score":90.59930630959718,"expected_score":55.83185809768068,"reliability_score":97.36955752479412,"uncertainty_avg":2.630442475205876,"uncertainty_penalty":0.0011588456588498275},"none":{"ceiling_score":55.01429727686298,"expected_score":43.81668422923763,"reliability_score":99.85485181716555,"uncertainty_avg":0.14514818283444697,"uncertainty_penalty":6.045572062779435}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:c324fc4c43d7c8e1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.48907706250000005,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.9126165000000004},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","max":0.5145615,"mean":0.34875300000000004,"median":0.335163,"min":0.254883,"recorded_attempt_count":19,"run_count":8,"total":2.790024},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","max":0.5145615,"mean":0.34875300000000004,"median":0.335163,"min":0.254883,"recorded_attempt_count":19,"run_count":8,"total":2.790024},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.48907706250000005,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.9126165}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":24,"cost_basis_counts":{"provider_reported":51},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.6921525,"mean":0.30153312499999996,"median":0.335163,"min":0.025422,"recorded_attempt_count":51,"run_count":24,"total":7.236794999999999},"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":50.77386093048303,"medium":55.362830501043646},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":690711},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":8,"repaired_rate":1.0},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.75}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:04:52Z","match_totals_all":{"draws":328,"losses":324,"wins":450},"match_totals_tracks":{"highest":{"draws":133,"losses":168,"wins":165},"medium":{"draws":195,"losses":156,"wins":285}},"model_slug":"google-gemini-3-5-flash","overall":{"max":84.5317048418163,"mean":51.3066160991627,"min":24.174721344647317},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":9,"overall_ranking_status":"partial","per_game":{"GB2-03":46.64591903633767,"GB2-04":34.75060930600307,"GB2-05":53.89836516661261,"GB2-06":80.84833683146083,"GB2-07":64.32521389783669,"GB2-08":24.174721344647317},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":6,"wins":62},"GB2-02":{"draws":59,"losses":7,"wins":10},"GB2-03":{"draws":69,"losses":23,"wins":28},"GB2-04":{"draws":76,"losses":45,"wins":47},"GB2-05":{"draws":0,"losses":95,"wins":97},"GB2-06":{"draws":7,"losses":21,"wins":110},"GB2-07":{"draws":0,"losses":80,"wins":96},"GB2-08":{"draws":117,"losses":47,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":46,"losses":11,"wins":7},"GB2-04":{"draws":29,"losses":32,"wins":21},"GB2-05":{"draws":0,"losses":48,"wins":42},"GB2-06":{"draws":1,"losses":13,"wins":52},"GB2-07":{"draws":0,"losses":35,"wins":43},"GB2-08":{"draws":57,"losses":29,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":6,"wins":62},"GB2-02":{"draws":59,"losses":7,"wins":10},"GB2-03":{"draws":23,"losses":12,"wins":21},"GB2-04":{"draws":47,"losses":13,"wins":26},"GB2-05":{"draws":0,"losses":47,"wins":55},"GB2-06":{"draws":6,"losses":8,"wins":58},"GB2-07":{"draws":0,"losses":45,"wins":53},"GB2-08":{"draws":60,"losses":18,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1503.0287857501219,"GB2-04":1447.491289436351,"GB2-05":1546.2909017340082,"GB2-06":1864.5341381574124,"GB2-07":1660.8923428169323,"GB2-08":1316.0263767118158},"medium":{"GB2-01":1889.6728264013168,"GB2-02":1499.2755505440737,"GB2-03":1568.0355049211498,"GB2-04":1550.6279522740244,"GB2-05":1578.6612634811117,"GB2-06":1886.2628217788806,"GB2-07":1584.771978631998,"GB2-08":1360.7075347534644}},"per_game_tracks":{"highest":{"GB2-03":46.64591903633767,"GB2-04":34.75060930600307,"GB2-05":53.89836516661261,"GB2-06":80.84833683146083,"GB2-07":64.32521389783669,"GB2-08":24.174721344647317},"medium":{"GB2-01":84.5317048418163,"GB2-02":26.743400089025748,"GB2-03":55.34552410919058,"GB2-04":50.89782707711206,"GB2-05":56.98624033015518,"GB2-06":82.8497697558789,"GB2-07":56.923104326447486,"GB2-08":28.62507347872291}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.25040169728177,"medium":55.362830501043646},"reasoning_agg":{"highest":{"max":80.84833683146083,"mean":47.25040169728177,"min":24.174721344647317},"medium":{"max":84.5317048418163,"mean":55.362830501043646,"min":26.743400089025748}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":84.5317048418163,"reasoning_variance":8.11242880376188},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.84833683146083,"expected_score":34.05401329755414,"reliability_score":87.04025281801852,"uncertainty_avg":12.959747181981479,"uncertainty_penalty":-13.196388399727624},"medium":{"ceiling_score":84.5317048418163,"expected_score":54.95303303865899,"reliability_score":87.3376521645766,"uncertainty_avg":12.662347835423404,"uncertainty_penalty":-0.40979746238465964}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:601623cc06431dd6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.526117125,"median":0.5491332,"min":0.330054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":8,"total":4.208937},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.526117125,"median":0.5491332,"min":0.330054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":8,"total":4.208937}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.2975122,"median":0.2990655,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":40},"recorded_attempt_count":40,"run_count":24,"total":7.140292799999999},"codegen_latency_ms":{"attempt_count":40,"max_ms":1201344,"mean_ms":515468.5833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":1201344,"mean_ms":973286.5,"min_ms":605299,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":40000,"output_mean":17970.666666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":40000,"output_mean":33312.25,"output_min":20000,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":46.30445130030317,"highest":53.2059313724767,"medium":47.63127725653766,"none":53.4126423441468},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":40,"finish_reasons":["length","stop"],"indexed_attempts":41,"output_token_observations":40,"reasoning_token_observations":40,"total_output_tokens":431296,"total_reasoning_output_tokens":338477,"total_visible_output_tokens":92819,"visible_token_observations":40},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":5,"evaluated_cells":7,"failed_game_aliases":["GB2-05","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.2857142857142857,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":4,"repaired_rate":0.5714285714285714}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-08-22T17:46:55Z","match_totals_all":{"draws":991,"losses":919,"wins":1319},"match_totals_tracks":{"highest":{"draws":219,"losses":173,"wins":322},"medium":{"draws":376,"losses":385,"wins":416},"none":{"draws":396,"losses":361,"wins":581}},"model_slug":"moonshotai-kimi-k3","overall":{"max":98.88106339111127,"mean":49.98578029870014,"min":20.275423642118344},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":10,"overall_ranking_status":"partial","per_game":{"GB2-01":61.721626572263794,"GB2-02":23.78419992194771,"GB2-03":39.21229308756867,"GB2-04":80.95493130171027,"GB2-07":60.356605978893036},"per_game_all":{"GB2-01":58.25973450462445,"GB2-02":22.329499812134276,"GB2-03":55.11335601545562,"GB2-04":56.779574098521444,"GB2-07":39.04009207078003},"per_game_match_totals_all":{"GB2-01":{"draws":160,"losses":127,"wins":200},"GB2-02":{"draws":314,"losses":37,"wins":21},"GB2-03":{"draws":140,"losses":91,"wins":157},"GB2-04":{"draws":213,"losses":62,"wins":146},"GB2-05":{"draws":0,"losses":129,"wins":220},"GB2-06":{"draws":35,"losses":134,"wins":189},"GB2-07":{"draws":0,"losses":289,"wins":209},"GB2-08":{"draws":129,"losses":50,"wins":177}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":51,"wins":98},"GB2-02":{"draws":106,"losses":10,"wins":6},"GB2-03":{"draws":51,"losses":33,"wins":28},"GB2-04":{"draws":47,"losses":15,"wins":82},"GB2-07":{"draws":0,"losses":64,"wins":108}},"medium":{"GB2-01":{"draws":15,"losses":47,"wins":70},"GB2-02":{"draws":78,"losses":17,"wins":7},"GB2-03":{"draws":50,"losses":19,"wins":57},"GB2-04":{"draws":88,"losses":17,"wins":22},"GB2-05":{"draws":0,"losses":67,"wins":103},"GB2-06":{"draws":16,"losses":68,"wins":98},"GB2-07":{"draws":0,"losses":107,"wins":47},"GB2-08":{"draws":129,"losses":43,"wins":12}},"none":{"GB2-01":{"draws":130,"losses":29,"wins":32},"GB2-02":{"draws":130,"losses":10,"wins":8},"GB2-03":{"draws":39,"losses":39,"wins":72},"GB2-04":{"draws":78,"losses":30,"wins":42},"GB2-05":{"draws":0,"losses":62,"wins":117},"GB2-06":{"draws":19,"losses":66,"wins":91},"GB2-07":{"draws":0,"losses":118,"wins":54},"GB2-08":{"draws":0,"losses":7,"wins":165}}},"per_game_raw_elo_all":{"GB2-01":1618.9712348117603,"GB2-02":1470.000330828486,"GB2-03":1548.634107680773,"GB2-04":1579.3921028973082,"GB2-07":1403.2538565093776},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1652.03180370545,"GB2-02":1476.5010269282043,"GB2-03":1438.3742508178495,"GB2-04":1734.845435170706,"GB2-07":1608.0632436917545},"medium":{"GB2-01":1704.7601387652967,"GB2-02":1464.1282589545453,"GB2-03":1643.4933772800982,"GB2-04":1487.0663571860498,"GB2-05":1556.3039721739203,"GB2-06":1673.0845945046149,"GB2-07":1306.4568832534878,"GB2-08":1379.978890026653},"none":{"GB2-01":1500.1217619645342,"GB2-02":1469.3717066027084,"GB2-03":1564.0346949443713,"GB2-04":1516.264516335169,"GB2-05":1642.7293692690507,"GB2-06":1633.7663053252722,"GB2-07":1295.2414425828902,"GB2-08":2018.027571089958}},"per_game_tracks":{"highest":{"GB2-01":61.721626572263794,"GB2-02":23.78419992194771,"GB2-03":39.21229308756867,"GB2-04":80.95493130171027,"GB2-07":60.356605978893036},"medium":{"GB2-01":66.80663569310781,"GB2-02":20.275423642118344,"GB2-03":68.46351429427254,"GB2-04":42.21132135718317,"GB2-05":55.7884886977324,"GB2-06":66.35935969494538,"GB2-07":28.874737705095153,"GB2-08":32.270736967846446},"none":{"GB2-01":46.250941248501725,"GB2-02":22.928875872336782,"GB2-03":57.66426066452565,"GB2-04":47.172469636670904,"GB2-05":63.50627032058176,"GB2-06":63.0083250910945,"GB2-07":27.888932528351898,"GB2-08":98.88106339111127}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.91342129541595,"medium":47.63127725653765,"none":53.41264234414682},"reasoning_agg":{"highest":{"max":80.95493130171027,"mean":48.91342129541595,"min":23.78419992194771},"medium":{"max":68.46351429427254,"mean":47.63127725653765,"min":20.275423642118344},"none":{"max":98.88106339111127,"mean":53.41264234414682,"min":22.928875872336782}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":98.88106339111127,"expected_score":44.428964798615915,"reasoning_variance":5.781365087609167,"reliability_score":99.25346744295126,"uncertainty_avg":0.7465325570487357,"uncertainty_penalty":-5.556815500084227},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.95493130171027,"expected_score":38.24217716808049,"reliability_score":99.0760949694897,"uncertainty_avg":0.9239050305102943,"uncertainty_penalty":-10.671244127335463},"medium":{"ceiling_score":68.46351429427254,"expected_score":43.589861946595,"reliability_score":99.17769209960255,"uncertainty_avg":0.8223079003974454,"uncertainty_penalty":-4.04141530994265},"none":{"ceiling_score":98.88106339111127,"expected_score":63.08949503288847,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":9.676852688741654}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:3667fca8056828bb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":2,"cost_basis_counts":{"provider_reported":2},"evidence_basis":"Provider-reported","max":0.143734,"mean":0.123945875,"median":0.123945875,"min":0.10415775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":2},"recorded_attempt_count":2,"run_count":2,"total":0.24789175},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.376168},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.19141049999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616799999999995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105},"historical-provider-setting-intensive":{"admitted_cell_count":2,"cell_count":2,"cost_basis_counts":{"provider_reported":2},"evidence_basis":"Provider-reported","max":0.143734,"mean":0.123945875,"median":0.123945875,"min":0.10415775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":2},"recorded_attempt_count":2,"run_count":2,"total":0.24789175}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":18,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143734,"mean":0.04530390277777777,"median":0.035486000000000004,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20},"recorded_attempt_count":20,"run_count":18,"total":0.8154702500000001},"codegen_latency_ms":{"attempt_count":20,"max_ms":328036,"mean_ms":53436.555555555555,"min_ms":14709,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":2,"max_ms":328036,"mean_ms":222798.5,"min_ms":117561,"run_count":2},"medium":{"attempt_count":9,"max_ms":66794,"mean_ms":45688.625,"min_ms":28293,"run_count":8},"none":{"attempt_count":9,"max_ms":26924,"mean_ms":18844.0,"min_ms":14709,"run_count":8}},"codegen_output_tokens":{"attempt_count":20,"output_max":31468,"output_mean":8149.833333333333,"output_min":2554,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":2,"output_max":31468,"output_mean":26858.0,"output_min":22248,"run_count":2},"medium":{"attempt_count":9,"output_max":11293,"output_mean":8521.75,"output_min":5500,"run_count":8},"none":{"attempt_count":9,"output_max":3991,"output_mean":3100.875,"output_min":2554,"run_count":8}},"display_name":"Muse Spark 1.2","economics":{"all":53.940066899880996,"highest":51.99337133367074,"medium":54.56046464326638,"none":40.23993367386119},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":20,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":20,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":20,"reconciliation_get_attempt_observations":26,"reconciliation_get_attempts":125,"total_output_tokens":146697,"total_reasoning_output_tokens":76794,"total_visible_output_tokens":69903,"visible_token_observations":20},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"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":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":2,"evaluated_cells":2,"first_pass_admitted":2,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-08-23T02:44:09Z","match_totals_all":{"draws":317,"losses":525,"wins":621},"match_totals_tracks":{"highest":{"draws":19,"losses":70,"wins":89},"medium":{"draws":135,"losses":156,"wins":306},"none":{"draws":163,"losses":299,"wins":226}},"model_slug":"meta-muse-spark-1-2","overall":{"max":79.71591004614217,"mean":48.33415064687674,"min":16.944819699504418},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":11,"overall_ranking_status":"partial","per_game":{"GB2-01":53.346963426005594,"GB2-03":50.63977924133589},"per_game_all":{"GB2-01":55.05849256453458,"GB2-03":52.82164123522741},"per_game_match_totals_all":{"GB2-01":{"draws":42,"losses":93,"wins":129},"GB2-02":{"draws":107,"losses":14,"wins":14},"GB2-03":{"draws":54,"losses":98,"wins":120},"GB2-04":{"draws":94,"losses":36,"wins":22},"GB2-05":{"draws":0,"losses":83,"wins":103},"GB2-06":{"draws":0,"losses":69,"wins":25},"GB2-07":{"draws":0,"losses":80,"wins":100},"GB2-08":{"draws":20,"losses":52,"wins":108}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":37,"wins":46},"GB2-03":{"draws":14,"losses":33,"wins":43}},"medium":{"GB2-01":{"draws":0,"losses":12,"wins":74},"GB2-02":{"draws":50,"losses":6,"wins":11},"GB2-03":{"draws":29,"losses":29,"wins":34},"GB2-04":{"draws":40,"losses":27,"wins":9},"GB2-05":{"draws":0,"losses":41,"wins":53},"GB2-07":{"draws":0,"losses":22,"wins":70},"GB2-08":{"draws":16,"losses":19,"wins":55}},"none":{"GB2-01":{"draws":37,"losses":44,"wins":9},"GB2-02":{"draws":57,"losses":8,"wins":3},"GB2-03":{"draws":11,"losses":36,"wins":43},"GB2-04":{"draws":54,"losses":9,"wins":13},"GB2-05":{"draws":0,"losses":42,"wins":50},"GB2-06":{"draws":0,"losses":69,"wins":25},"GB2-07":{"draws":0,"losses":58,"wins":30},"GB2-08":{"draws":4,"losses":33,"wins":53}}},"per_game_raw_elo_all":{"GB2-01":1598.8490748142374,"GB2-03":1538.9520262184424},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1582.2892427440295,"GB2-03":1523.6439862621312},"medium":{"GB2-01":1837.8230227206066,"GB2-02":1512.022713465008,"GB2-03":1544.6194374124107,"GB2-04":1414.4147451259803,"GB2-05":1564.9118638803197,"GB2-07":1717.0113447747601,"GB2-08":1696.938698515543},"none":{"GB2-01":1376.434958978076,"GB2-02":1457.9484790906874,"GB2-03":1548.5926549807855,"GB2-04":1485.9572707576879,"GB2-05":1576.2966805223457,"GB2-06":1260.4296004941673,"GB2-07":1342.4372322496993,"GB2-08":1652.41020376169}},"per_game_tracks":{"highest":{"GB2-01":53.346963426005594,"GB2-03":50.63977924133589},"medium":{"GB2-01":79.71591004614217,"GB2-02":28.93634004616261,"GB2-03":53.664178268995066,"GB2-04":29.362656163193495,"GB2-05":55.62541697170394,"GB2-07":70.51569207279049,"GB2-08":64.10305893387694},"none":{"GB2-01":32.11260422145595,"GB2-02":16.944819699504418,"GB2-03":54.16096619535128,"GB2-04":40.45363557593279,"GB2-05":56.59420148801351,"GB2-06":30.66305165235034,"GB2-07":31.543087970431298,"GB2-08":59.44710258784996}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.99337133367074,"medium":52.769146933098305,"none":40.239933673861195},"reasoning_agg":{"highest":{"max":53.346963426005594,"mean":51.99337133367074,"min":50.63977924133589},"medium":{"max":79.71591004614217,"mean":52.769146933098305,"min":28.93634004616261},"none":{"max":59.44710258784996,"mean":40.239933673861195,"min":16.944819699504418}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.71591004614217,"expected_score":52.15471029681941,"reasoning_variance":12.52921325923711,"reliability_score":91.13402816883054,"uncertainty_avg":8.86597183116946,"uncertainty_penalty":3.820559649942666},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.346963426005594,"expected_score":35.682805011749,"reliability_score":91.04293208179304,"uncertainty_avg":8.957067918206963,"uncertainty_penalty":-16.31056632192174},"medium":{"ceiling_score":79.71591004614217,"expected_score":53.634150703378104,"reliability_score":89.66026426511598,"uncertainty_avg":10.339735734884012,"uncertainty_penalty":0.8650037702797988},"none":{"ceiling_score":59.44710258784996,"expected_score":48.3874001923387,"reliability_score":89.92970792223896,"uncertainty_avg":10.070292077761039,"uncertainty_penalty":8.147466518477508}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:7a31aface18eaea9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.43048093750000005,"median":0.4308725,"min":0.32672249999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-08-08":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887695000000001},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","max":0.266665,"mean":0.20888499999999996,"median":0.20905875000000002,"min":0.14104,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-08-08":8},"run_count":16,"token_priced_attempt_count":16,"total":3.34216},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.9739300000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.4245200000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709265},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":16,"token_priced_attempt_count":17,"total":4.096069999999999}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-08-08":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333333,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"all":48.11001608960556,"highest":43.01997012841454,"medium":52.33568653113013,"none":48.97439160927202},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":16,"requested_max_output_token_observations":16,"requested_max_output_tokens":[64000],"total_output_tokens":239955,"total_reasoning_output_tokens":171858,"total_visible_output_tokens":43839,"visible_token_observations":16},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-08-21T20:34:32Z","match_totals_all":{"draws":912,"losses":1023,"wins":1274},"match_totals_tracks":{"highest":{"draws":351,"losses":447,"wins":458},"medium":{"draws":324,"losses":389,"wins":562},"none":{"draws":237,"losses":187,"wins":254}},"model_slug":"claude-opus-4-5","overall":{"max":84.27791783076424,"mean":48.11001608960555,"min":13.078411737521655},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":12,"overall_ranking_status":"partial","per_game":{"GB2-01":65.20264997974215,"GB2-02":13.078411737521655,"GB2-03":39.11059502696876,"GB2-04":35.58935434104422,"GB2-05":52.28009274749246,"GB2-06":60.91814020044125,"GB2-07":49.63125807718102,"GB2-08":28.34925891692476},"per_game_all":{"GB2-01":54.18134989280361,"GB2-02":20.667770191274148,"GB2-03":45.79803657615406,"GB2-04":41.32417373144273,"GB2-05":56.956238362611884,"GB2-06":54.10748839578864,"GB2-07":50.93702227838056,"GB2-08":60.90804928838883},"per_game_match_totals_all":{"GB2-01":{"draws":139,"losses":91,"wins":187},"GB2-02":{"draws":287,"losses":38,"wins":7},"GB2-03":{"draws":165,"losses":112,"wins":89},"GB2-04":{"draws":186,"losses":84,"wins":38},"GB2-05":{"draws":0,"losses":197,"wins":279},"GB2-06":{"draws":37,"losses":177,"wins":228},"GB2-07":{"draws":0,"losses":212,"wins":232},"GB2-08":{"draws":98,"losses":112,"wins":214}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":23,"losses":30,"wins":90},"GB2-02":{"draws":101,"losses":20,"wins":1},"GB2-03":{"draws":39,"losses":56,"wins":43},"GB2-04":{"draws":79,"losses":55,"wins":17},"GB2-05":{"draws":0,"losses":82,"wins":110},"GB2-06":{"draws":16,"losses":64,"wins":90},"GB2-07":{"draws":0,"losses":72,"wins":90},"GB2-08":{"draws":93,"losses":68,"wins":17}},"medium":{"GB2-01":{"draws":45,"losses":39,"wins":82},"GB2-02":{"draws":118,"losses":10,"wins":2},"GB2-03":{"draws":75,"losses":43,"wins":34},"GB2-04":{"draws":68,"losses":15,"wins":10},"GB2-05":{"draws":0,"losses":84,"wins":108},"GB2-06":{"draws":16,"losses":76,"wins":96},"GB2-07":{"draws":0,"losses":96,"wins":90},"GB2-08":{"draws":2,"losses":26,"wins":140}},"none":{"GB2-01":{"draws":71,"losses":22,"wins":15},"GB2-02":{"draws":68,"losses":8,"wins":4},"GB2-03":{"draws":51,"losses":13,"wins":12},"GB2-04":{"draws":39,"losses":14,"wins":11},"GB2-05":{"draws":0,"losses":31,"wins":61},"GB2-06":{"draws":5,"losses":37,"wins":42},"GB2-07":{"draws":0,"losses":44,"wins":52},"GB2-08":{"draws":3,"losses":18,"wins":57}}},"per_game_raw_elo_all":{"GB2-01":1582.159561421895,"GB2-02":1464.9592460602164,"GB2-03":1484.6906800164154,"GB2-04":1487.09346863848,"GB2-05":1571.9302222060771,"GB2-06":1532.302132692482,"GB2-07":1520.6270663761327,"GB2-08":1659.6743517516159},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1687.8947917300393,"GB2-02":1428.5395963112296,"GB2-03":1433.9524119202586,"GB2-04":1441.440206836578,"GB2-05":1514.867968636721,"GB2-06":1609.4547207601838,"GB2-07":1505.6448959972681,"GB2-08":1342.9635954463263},"medium":{"GB2-01":1606.458566001231,"GB2-02":1469.0049313514542,"GB2-03":1504.1018206087042,"GB2-04":1475.5305327733142,"GB2-05":1570.330410553067,"GB2-06":1511.5889769331868,"GB2-07":1567.6069463139568,"GB2-08":1878.7242423201383},"none":{"GB2-01":1452.1253265344149,"GB2-02":1497.3332105179659,"GB2-03":1516.0178075202837,"GB2-04":1544.309666305548,"GB2-05":1630.5922874284433,"GB2-06":1475.8627003840757,"GB2-07":1488.6293568171732,"GB2-08":1757.3352174883826}},"per_game_tracks":{"highest":{"GB2-01":65.20264997974215,"GB2-02":13.078411737521655,"GB2-03":39.11059502696876,"GB2-04":35.58935434104422,"GB2-05":52.28009274749246,"GB2-06":60.91814020044125,"GB2-07":49.63125807718102,"GB2-08":28.34925891692476},"medium":{"GB2-01":57.02925130550037,"GB2-02":22.36064210907722,"GB2-03":49.23562494881364,"GB2-04":39.50807424575855,"GB2-05":57.18889318674271,"GB2-06":52.8069765902766,"GB2-07":56.278112032107714,"GB2-08":84.27791783076424},"none":{"GB2-01":40.3121483931683,"GB2-02":26.56425672722357,"GB2-03":49.047889752679794,"GB2-04":48.87509260752541,"GB2-05":61.399729153600475,"GB2-06":48.5973483966481,"GB2-07":46.901696725852915,"GB2-08":70.0969711174775}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.019970128414535,"medium":52.33568653113013,"none":48.974391609272004},"reasoning_agg":{"highest":{"max":65.20264997974215,"mean":43.019970128414535,"min":13.078411737521655},"medium":{"max":84.27791783076424,"mean":52.33568653113013,"min":22.36064210907722},"none":{"max":70.0969711174775,"mean":48.974391609272004,"min":26.56425672722357}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"reasoning_settings":{"balanced":"medium","intensive":"high"},"score_diagnostics":{"ceiling_score":84.27791783076424,"expected_score":44.50904348134377,"reasoning_variance":9.315716402715594,"reliability_score":96.05412617160354,"uncertainty_avg":3.9458738283964614,"uncertainty_penalty":-3.6009726082617846},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.20264997974215,"expected_score":24.61182157308238,"reliability_score":99.83331478332855,"uncertainty_avg":0.16668521667145164,"uncertainty_penalty":-18.408148555332154},"medium":{"ceiling_score":84.27791783076424,"expected_score":48.226446190876885,"reliability_score":99.02236721088254,"uncertainty_avg":0.9776327891174585,"uncertainty_penalty":-4.109240340253244},"none":{"ceiling_score":70.0969711174775,"expected_score":60.68886268007201,"reliability_score":89.30669652059953,"uncertainty_avg":10.693303479400472,"uncertainty_penalty":11.714471070800009}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:97de4d20c6c50836","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":12.137519999999999,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":0.15809499999999999,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":1.33952},"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-2026-08-08":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063375}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.24673750000000003,"mean":0.16744,"median":0.15809499999999999,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":1.33952},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063375},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":12.137519999999999,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":65.3280125}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":32},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":12.137519999999999,"mean":2.8005991666666663,"median":0.15809499999999999,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"run_count":25,"token_priced_attempt_count":32,"total":67.27386999999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":309143,"mean_ms":97936.92,"min_ms":13711,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":309143,"mean_ms":245541.25,"min_ms":194014,"run_count":8},"medium":{"attempt_count":11,"max_ms":70195,"mean_ms":41737.375,"min_ms":27719,"run_count":8},"none":{"attempt_count":10,"max_ms":27196,"mean_ms":16688.222222222223,"min_ms":13711,"run_count":9}},"codegen_output_tokens":{"attempt_count":32,"output_max":806490,"output_mean":177703.68,"output_min":2382,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":806490,"output_mean":542498.625,"output_min":312998,"run_count":8},"medium":{"attempt_count":11,"output_max":13756,"output_mean":9389.25,"output_min":6044,"run_count":8},"none":{"attempt_count":10,"output_max":5458,"output_mean":3054.3333333333335,"output_min":2382,"run_count":9}},"display_name":"GPT-5.6 Terra","economics":{"all":48.04402739757715,"highest":57.525108039292846,"medium":43.44652688282063,"none":43.16044727061799},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":32,"total_output_tokens":4442592},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.1111111111111111},"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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-08-05T05:18:32Z","match_totals_all":{"draws":661,"losses":603,"wins":698},"match_totals_tracks":{"highest":{"draws":137,"losses":185,"wins":280},"medium":{"draws":259,"losses":212,"wins":229},"none":{"draws":265,"losses":206,"wins":189}},"model_slug":"gpt-5-6-terra","overall":{"max":76.39149789263541,"mean":47.62657298276638,"min":21.8994809309449},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.41290592375142,"GB2-02":43.85138391276626,"GB2-03":58.693530462272456,"GB2-04":52.06108211106203,"GB2-05":62.12239074156852,"GB2-06":74.17041747029772,"GB2-07":76.39149789263541,"GB2-08":51.49765579998893},"per_game_all":{"GB2-01":46.93977556009244,"GB2-02":31.32899658305389,"GB2-03":50.045896901364046,"GB2-04":47.614263793696004,"GB2-05":59.32436522300191,"GB2-06":56.35429321299404,"GB2-07":51.27798996306899,"GB2-08":41.46663794334593},"per_game_match_totals_all":{"GB2-01":{"draws":93,"losses":81,"wins":82},"GB2-02":{"draws":185,"losses":29,"wins":18},"GB2-03":{"draws":78,"losses":52,"wins":50},"GB2-04":{"draws":166,"losses":27,"wins":47},"GB2-05":{"draws":0,"losses":105,"wins":145},"GB2-06":{"draws":14,"losses":105,"wins":139},"GB2-07":{"draws":0,"losses":122,"wins":154},"GB2-08":{"draws":125,"losses":82,"wins":63}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":31,"losses":34,"wins":27},"GB2-02":{"draws":41,"losses":17,"wins":14},"GB2-03":{"draws":12,"losses":11,"wins":19},"GB2-04":{"draws":40,"losses":13,"wins":27},"GB2-05":{"draws":0,"losses":35,"wins":41},"GB2-06":{"draws":0,"losses":24,"wins":50},"GB2-07":{"draws":0,"losses":21,"wins":59},"GB2-08":{"draws":13,"losses":30,"wins":43}},"medium":{"GB2-01":{"draws":32,"losses":23,"wins":29},"GB2-02":{"draws":67,"losses":7,"wins":0},"GB2-03":{"draws":34,"losses":21,"wins":13},"GB2-04":{"draws":66,"losses":9,"wins":13},"GB2-05":{"draws":0,"losses":40,"wins":58},"GB2-06":{"draws":12,"losses":32,"wins":46},"GB2-07":{"draws":0,"losses":50,"wins":52},"GB2-08":{"draws":48,"losses":30,"wins":18}},"none":{"GB2-01":{"draws":30,"losses":24,"wins":26},"GB2-02":{"draws":77,"losses":5,"wins":4},"GB2-03":{"draws":32,"losses":20,"wins":18},"GB2-04":{"draws":60,"losses":5,"wins":7},"GB2-05":{"draws":0,"losses":30,"wins":46},"GB2-06":{"draws":2,"losses":49,"wins":43},"GB2-07":{"draws":0,"losses":51,"wins":43},"GB2-08":{"draws":64,"losses":22,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1521.0197502678477,"GB2-02":1519.5309051657234,"GB2-03":1529.7131030104244,"GB2-04":1531.116383858686,"GB2-05":1609.4555592614697,"GB2-06":1567.6935099627128,"GB2-07":1531.8127749299872,"GB2-08":1480.4838730308793},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1465.937234683748,"GB2-02":1577.1507466448422,"GB2-03":1599.7752708410653,"GB2-04":1559.6914890100186,"GB2-05":1642.8634951956521,"GB2-06":1782.5107591539809,"GB2-07":1776.5903445158342,"GB2-08":1577.3366324646952},"medium":{"GB2-01":1507.8516420385984,"GB2-02":1478.1788100994386,"GB2-03":1481.3068886929552,"GB2-04":1511.0990916013604,"GB2-05":1620.8423835031147,"GB2-06":1527.379331282502,"GB2-07":1392.4789526855327,"GB2-08":1472.1846041302629},"none":{"GB2-01":1589.2703740811967,"GB2-02":1503.26315875289,"GB2-03":1508.0571494972528,"GB2-04":1522.5585709646791,"GB2-05":1564.6607990856423,"GB2-06":1393.1904394516557,"GB2-07":1426.3690275885945,"GB2-08":1391.9303824976794}},"per_game_tracks":{"highest":{"GB2-01":41.41290592375142,"GB2-02":43.85138391276626,"GB2-03":58.693530462272456,"GB2-04":52.06108211106203,"GB2-05":62.12239074156852,"GB2-06":74.17041747029772,"GB2-07":76.39149789263541,"GB2-08":51.49765579998893},"medium":{"GB2-01":45.549073450674925,"GB2-02":21.8994809309449,"GB2-03":43.78614708777877,"GB2-04":44.844934191198654,"GB2-05":60.64978060082346,"GB2-06":53.05565583214185,"GB2-07":37.04689513213039,"GB2-08":40.74024783687207},"none":{"GB2-01":53.857347305850986,"GB2-02":28.236124905450517,"GB2-03":47.6580131540409,"GB2-04":45.936775078827324,"GB2-05":55.20092432661375,"GB2-06":41.83680633654252,"GB2-07":40.395576864441175,"GB2-08":32.16201019317678}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.52510803929284,"medium":43.44652688282063,"none":41.90808402618568},"reasoning_agg":{"highest":{"max":76.39149789263541,"mean":57.52510803929284,"min":41.41290592375142},"medium":{"max":60.64978060082346,"mean":43.44652688282063,"min":21.8994809309449},"none":{"max":55.20092432661375,"mean":41.90808402618568,"min":28.236124905450517}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":76.39149789263541,"expected_score":46.64342517330108,"reasoning_variance":15.617024013107155,"reliability_score":88.18713669052882,"uncertainty_avg":11.812863309471178,"uncertainty_penalty":-0.9831478094653008},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.39149789263541,"expected_score":47.09136652437615,"reliability_score":85.4938129371661,"uncertainty_avg":14.506187062833908,"uncertainty_penalty":-10.43374151491669},"medium":{"ceiling_score":60.64978060082346,"expected_score":38.452880926371066,"reliability_score":90.26745416490233,"uncertainty_avg":9.73254583509767,"uncertainty_penalty":-4.993645956449562},"none":{"ceiling_score":55.20092432661375,"expected_score":54.38602806915604,"reliability_score":88.80014296951805,"uncertainty_avg":11.199857030481956,"uncertainty_penalty":12.477944042970357}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:b52271e32d7b710c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"provider_reported":7},"evidence_basis":"Provider-reported","max":0.09063263032999999,"mean":0.09063263032999999,"median":0.09063263032999999,"min":0.09063263032999999,"recorded_attempt_count":7,"run_count":2,"total":0.18126526065999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804},"historical-provider-setting-intensive":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"provider_reported":7},"evidence_basis":"Provider-reported","max":0.09063263032999999,"mean":0.09063263032999999,"median":0.09063263032999999,"min":0.09063263032999999,"recorded_attempt_count":7,"run_count":2,"total":0.18126526065999998}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":17,"cost_basis_counts":{"provider_reported":47},"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.04690495967823529,"median":0.030447832,"min":0.0106770175,"recorded_attempt_count":47,"run_count":26,"total":1.06760263506},"codegen_latency_ms":{"attempt_count":7,"max_ms":2481480,"mean_ms":1484485.0,"min_ms":487490,"run_count":2},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":7,"max_ms":2481480,"mean_ms":1484485.0,"min_ms":487490,"run_count":2}},"codegen_output_tokens":{"attempt_count":7,"output_max":153344,"output_mean":90656.0,"output_min":27968,"run_count":2},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":7,"output_max":153344,"output_mean":90656.0,"output_min":27968,"run_count":2}},"display_name":"GLM-5.2","economics":{"all":43.22025304198288,"highest":53.3313100517875,"medium":43.245062052265894,"none":42.77028062419599},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":7,"finish_reasons":["stop"],"indexed_attempts":7,"output_token_observations":7,"reasoning_token_observations":5,"total_output_tokens":181312,"total_reasoning_output_tokens":94090,"total_visible_output_tokens":10550,"visible_token_observations":5},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":8,"repaired_rate":1.0},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375},"intensive":{"admitted_plugins":2,"evaluated_cells":2,"first_pass_admitted":2,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-08-22T14:35:20Z","match_totals_all":{"draws":601,"losses":548,"wins":581},"match_totals_tracks":{"highest":{"draws":79,"losses":64,"wins":95},"medium":{"draws":195,"losses":138,"wins":161},"none":{"draws":327,"losses":346,"wins":325}},"model_slug":"z-ai-glm-5-2","overall":{"max":66.27613202821979,"mean":46.44888424274979,"min":18.537461190466654},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":14,"overall_ranking_status":"partial","per_game":{"GB2-03":53.3313100517875},"per_game_all":{"GB2-03":43.22025304198288},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":99,"wins":92},"GB2-02":{"draws":161,"losses":6,"wins":1},"GB2-03":{"draws":157,"losses":99,"wins":114},"GB2-04":{"draws":119,"losses":34,"wins":27},"GB2-05":{"draws":0,"losses":108,"wins":108},"GB2-06":{"draws":20,"losses":71,"wins":93},"GB2-07":{"draws":0,"losses":92,"wins":100},"GB2-08":{"draws":109,"losses":39,"wins":46}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":79,"losses":64,"wins":95}},"medium":{"GB2-01":{"draws":7,"losses":28,"wins":43},"GB2-02":{"draws":53,"losses":1,"wins":0},"GB2-03":{"draws":29,"losses":10,"wins":1},"GB2-04":{"draws":46,"losses":9,"wins":7},"GB2-05":{"draws":0,"losses":34,"wins":36},"GB2-06":{"draws":5,"losses":19,"wins":32},"GB2-07":{"draws":0,"losses":27,"wins":41},"GB2-08":{"draws":55,"losses":10,"wins":1}},"none":{"GB2-01":{"draws":28,"losses":71,"wins":49},"GB2-02":{"draws":108,"losses":5,"wins":1},"GB2-03":{"draws":49,"losses":25,"wins":18},"GB2-04":{"draws":73,"losses":25,"wins":20},"GB2-05":{"draws":0,"losses":74,"wins":72},"GB2-06":{"draws":15,"losses":52,"wins":61},"GB2-07":{"draws":0,"losses":65,"wins":59},"GB2-08":{"draws":54,"losses":29,"wins":45}}},"per_game_raw_elo_all":{"GB2-03":1481.6025420140638},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1537.306297413937},"medium":{"GB2-01":1466.6116867747367,"GB2-02":1473.9086495306929,"GB2-03":1427.6979199994657,"GB2-04":1497.431367332239,"GB2-05":1582.2082474431916,"GB2-06":1695.5081693751965,"GB2-07":1549.6193285283734,"GB2-08":1421.9737693629816},"none":{"GB2-01":1347.590696843264,"GB2-02":1469.457526624261,"GB2-03":1479.803408628788,"GB2-04":1493.6960155718434,"GB2-05":1519.7914352128794,"GB2-06":1612.7137751991481,"GB2-07":1539.9395388467756,"GB2-08":1571.7519312912373}},"per_game_tracks":{"highest":{"GB2-03":53.3313100517875},"medium":{"GB2-01":41.118148020938065,"GB2-02":19.216835075427902,"GB2-03":34.19952060625756,"GB2-04":41.48658634194338,"GB2-05":56.586976538895975,"GB2-06":66.27613202821979,"GB2-07":52.449200646157834,"GB2-08":34.627097160286695},"none":{"GB2-01":28.68527547982116,"GB2-02":18.537461190466654,"GB2-03":42.12992846790356,"GB2-04":40.6936216942447,"GB2-05":51.134814130021056,"GB2-06":59.57776973557898,"GB2-07":51.209975643465064,"GB2-08":50.193398652066804}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.3313100517875,"medium":43.245062052265894,"none":42.77028062419599},"reasoning_agg":{"highest":{"max":53.3313100517875,"mean":53.3313100517875,"min":53.3313100517875},"medium":{"max":66.27613202821979,"mean":43.245062052265894,"min":19.216835075427902},"none":{"max":59.57776973557898,"mean":42.77028062419599,"min":18.537461190466654}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.27613202821979,"expected_score":34.94678088150216,"reasoning_variance":10.561029427591507,"reliability_score":78.17559489122591,"uncertainty_avg":21.82440510877409,"uncertainty_penalty":-11.502103361247634},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.3313100517875,"expected_score":23.52033183265443,"reliability_score":98.09575095726298,"uncertainty_avg":1.9042490427370184,"uncertainty_penalty":-29.810978219133066},"medium":{"ceiling_score":66.27613202821979,"expected_score":39.154384508026276,"reliability_score":79.80016368052728,"uncertainty_avg":20.199836319472716,"uncertainty_penalty":-4.090677544239618},"none":{"ceiling_score":59.57776973557898,"expected_score":53.29101939382904,"reliability_score":80.38379766786747,"uncertainty_avg":19.616202332132524,"uncertainty_penalty":10.520738769633049}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:351ed472be23eda4","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":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.52499},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337000000000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":45.4885935610847,"highest":54.299112819219744,"medium":40.940759816475385,"none":41.22590804755896},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":322334,"total_reasoning_output_tokens":243107,"total_visible_output_tokens":79227,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-08-23T12:40:55Z","match_totals_all":{"draws":550,"losses":736,"wins":748},"match_totals_tracks":{"highest":{"draws":160,"losses":198,"wins":326},"medium":{"draws":200,"losses":266,"wins":209},"none":{"draws":190,"losses":272,"wins":213}},"model_slug":"claude-sonnet-5","overall":{"max":83.58905380078096,"mean":45.48859356108469,"min":18.648854275319852},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.83944130802511,"GB2-02":18.648854275319852,"GB2-03":58.06942397101405,"GB2-04":58.87607730332684,"GB2-05":52.77369810249913,"GB2-06":33.30669861449365,"GB2-07":72.2896551782984,"GB2-08":83.58905380078096},"per_game_all":{"GB2-01":46.970249190029655,"GB2-02":22.149286018144693,"GB2-03":51.90247525348834,"GB2-04":46.39534939219237,"GB2-05":46.67132838039038,"GB2-06":43.32160033991386,"GB2-07":54.337850641122174,"GB2-08":52.16060927339609},"per_game_match_totals_all":{"GB2-01":{"draws":43,"losses":112,"wins":105},"GB2-02":{"draws":178,"losses":16,"wins":6},"GB2-03":{"draws":101,"losses":72,"wins":85},"GB2-04":{"draws":130,"losses":41,"wins":53},"GB2-05":{"draws":0,"losses":146,"wins":132},"GB2-06":{"draws":12,"losses":167,"wins":101},"GB2-07":{"draws":0,"losses":113,"wins":157},"GB2-08":{"draws":86,"losses":69,"wins":109}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":28,"wins":48},"GB2-02":{"draws":62,"losses":5,"wins":1},"GB2-03":{"draws":41,"losses":19,"wins":26},"GB2-04":{"draws":40,"losses":8,"wins":26},"GB2-05":{"draws":0,"losses":39,"wins":55},"GB2-06":{"draws":5,"losses":64,"wins":23},"GB2-07":{"draws":0,"losses":22,"wins":70},"GB2-08":{"draws":0,"losses":13,"wins":77}},"medium":{"GB2-01":{"draws":15,"losses":41,"wins":29},"GB2-02":{"draws":55,"losses":3,"wins":4},"GB2-03":{"draws":29,"losses":36,"wins":23},"GB2-04":{"draws":46,"losses":16,"wins":14},"GB2-05":{"draws":0,"losses":44,"wins":48},"GB2-06":{"draws":3,"losses":58,"wins":33},"GB2-07":{"draws":0,"losses":39,"wins":51},"GB2-08":{"draws":52,"losses":29,"wins":7}},"none":{"GB2-01":{"draws":16,"losses":43,"wins":28},"GB2-02":{"draws":61,"losses":8,"wins":1},"GB2-03":{"draws":31,"losses":17,"wins":36},"GB2-04":{"draws":44,"losses":17,"wins":13},"GB2-05":{"draws":0,"losses":63,"wins":29},"GB2-06":{"draws":4,"losses":45,"wins":45},"GB2-07":{"draws":0,"losses":52,"wins":36},"GB2-08":{"draws":34,"losses":27,"wins":25}}},"per_game_raw_elo_all":{"GB2-01":1520.9360226379488,"GB2-02":1481.7835272209365,"GB2-03":1533.5493432356916,"GB2-04":1524.686910315915,"GB2-05":1464.0360594499296,"GB2-06":1410.9783137190464,"GB2-07":1561.5983426046969,"GB2-08":1583.1977355086121},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1616.069646677,"GB2-02":1465.5824743341007,"GB2-03":1577.2383618839162,"GB2-04":1605.3952927027833,"GB2-05":1532.691509009023,"GB2-06":1292.2789954568457,"GB2-07":1734.1032480369697,"GB2-08":1883.2982680044097},"medium":{"GB2-01":1462.5112502726618,"GB2-02":1513.7378064158515,"GB2-03":1452.2573394100423,"GB2-04":1475.013285163808,"GB2-05":1492.077411720965,"GB2-06":1438.1728462442638,"GB2-07":1542.6587539842521,"GB2-08":1384.1626713883547},"none":{"GB2-01":1484.2271709641848,"GB2-02":1466.030300912858,"GB2-03":1571.1523284131163,"GB2-04":1493.6521530811533,"GB2-05":1367.3392576198007,"GB2-06":1502.4830994560295,"GB2-07":1408.0330257928692,"GB2-08":1482.1322671330724}},"per_game_tracks":{"highest":{"GB2-01":56.83944130802511,"GB2-02":18.648854275319852,"GB2-03":58.06942397101405,"GB2-04":58.87607730332684,"GB2-05":52.77369810249913,"GB2-06":33.30669861449365,"GB2-07":72.2896551782984,"GB2-08":83.58905380078096},"medium":{"GB2-01":40.887590399986145,"GB2-02":28.897713502544164,"GB2-03":40.4983370246016,"GB2-04":38.75702900741598,"GB2-05":49.140227782544386,"GB2-06":45.62272982536658,"GB2-07":52.37264260162897,"GB2-08":31.349808387715242},"none":{"GB2-01":43.183715862077705,"GB2-02":18.901290276570073,"GB2-03":57.13966476484938,"GB2-04":41.552941865834306,"GB2-05":38.10005925612763,"GB2-06":51.03537257988135,"GB2-07":38.35125414343914,"GB2-08":41.54296563169207}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.29911281921975,"medium":40.94075981647538,"none":41.22590804755895},"reasoning_agg":{"highest":{"max":83.58905380078096,"mean":54.29911281921975,"min":18.648854275319852},"medium":{"max":52.37264260162897,"mean":40.94075981647538,"min":28.897713502544164},"none":{"max":57.13966476484938,"mean":41.22590804755895,"min":18.901290276570073}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":83.58905380078096,"expected_score":42.547621770808924,"reasoning_variance":13.358353002744373,"reliability_score":89.51033269097584,"uncertainty_avg":10.489667309024163,"uncertainty_penalty":-2.9409717902757677},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.58905380078096,"expected_score":41.303036375464444,"reliability_score":89.75727461031862,"uncertainty_avg":10.242725389681382,"uncertainty_penalty":-12.996076443755307},"medium":{"ceiling_score":52.37264260162897,"expected_score":35.30579124360774,"reliability_score":89.31858926950997,"uncertainty_avg":10.681410730490034,"uncertainty_penalty":-5.634968572867635},"none":{"ceiling_score":57.13966476484938,"expected_score":51.03403769335459,"reliability_score":89.45513419309893,"uncertainty_avg":10.544865806901074,"uncertainty_penalty":9.808129645795638}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:509525aafb482b3d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561124999999995},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793050000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793049999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-08-08":19},"run_count":24,"token_priced_attempt_count":31,"total":4.4559187499999995},"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":46.247748968419636,"medium":44.25870820023652},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:06Z","match_totals_all":{"draws":349,"losses":434,"wins":417},"match_totals_tracks":{"highest":{"draws":193,"losses":230,"wins":217},"medium":{"draws":156,"losses":204,"wins":200}},"model_slug":"gpt-5","overall":{"max":67.70578978678658,"mean":44.52668228063902,"min":19.976294071045},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":16,"overall_ranking_status":"partial","per_game":{"GB2-01":48.32288377460864,"GB2-02":19.976294071045,"GB2-03":36.28813655813136,"GB2-04":38.653128654939394,"GB2-05":63.893829202898324,"GB2-06":67.70578978678658,"GB2-07":59.19331770120144,"GB2-08":35.948611997746326},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":93,"wins":68},"GB2-02":{"draws":52,"losses":12,"wins":2},"GB2-03":{"draws":47,"losses":42,"wins":19},"GB2-04":{"draws":106,"losses":31,"wins":23},"GB2-05":{"draws":0,"losses":77,"wins":87},"GB2-06":{"draws":13,"losses":59,"wins":96},"GB2-07":{"draws":0,"losses":72,"wins":100},"GB2-08":{"draws":110,"losses":48,"wins":22}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":46,"wins":48},"GB2-02":{"draws":52,"losses":12,"wins":2},"GB2-03":{"draws":18,"losses":25,"wins":11},"GB2-04":{"draws":52,"losses":17,"wins":7},"GB2-05":{"draws":0,"losses":38,"wins":42},"GB2-06":{"draws":6,"losses":26,"wins":44},"GB2-07":{"draws":0,"losses":38,"wins":48},"GB2-08":{"draws":59,"losses":28,"wins":15}},"medium":{"GB2-01":{"draws":15,"losses":47,"wins":20},"GB2-03":{"draws":29,"losses":17,"wins":8},"GB2-04":{"draws":54,"losses":14,"wins":16},"GB2-05":{"draws":0,"losses":39,"wins":45},"GB2-06":{"draws":7,"losses":33,"wins":52},"GB2-07":{"draws":0,"losses":34,"wins":52},"GB2-08":{"draws":51,"losses":20,"wins":7}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1531.0962511352168,"GB2-02":1472.2427790750996,"GB2-03":1433.9628765018,"GB2-04":1474.3430744138302,"GB2-05":1661.7384364801353,"GB2-06":1705.0975680441916,"GB2-07":1609.3281773288047,"GB2-08":1425.1578264572643},"medium":{"GB2-01":1275.7786038469053,"GB2-03":1403.2862829940107,"GB2-04":1505.6460224672696,"GB2-05":1631.1656521686612,"GB2-06":1604.3099870611559,"GB2-07":1644.6647109838646,"GB2-08":1362.3112742107332}},"per_game_tracks":{"highest":{"GB2-01":48.32288377460864,"GB2-02":19.976294071045,"GB2-03":36.28813655813136,"GB2-04":38.653128654939394,"GB2-05":63.893829202898324,"GB2-06":67.70578978678658,"GB2-07":59.19331770120144,"GB2-08":35.948611997746326},"medium":{"GB2-01":21.501856921354634,"GB2-03":31.9585259455821,"GB2-04":43.846681213455774,"GB2-05":61.28160282112335,"GB2-06":59.56864288533566,"GB2-07":62.86088508787239,"GB2-08":28.79276252693172}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.24774896841963,"medium":42.80561559285842},"reasoning_agg":{"highest":{"max":67.70578978678658,"mean":46.24774896841963,"min":19.976294071045},"medium":{"max":62.86088508787239,"mean":42.80561559285842,"min":21.501856921354634}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":67.70578978678658,"reasoning_variance":3.4421333755612054},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.70578978678658,"expected_score":31.369487109246336,"reliability_score":87.41940117496573,"uncertainty_avg":12.58059882503427,"uncertainty_penalty":-14.878261859173293},"medium":{"ceiling_score":62.86088508787239,"expected_score":37.40622987169026,"reliability_score":87.68214976068434,"uncertainty_avg":12.317850239315666,"uncertainty_penalty":-5.399385721168166}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:d46bf919cbe90971","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.10909930499999998,"mean":0.082847753875,"median":0.084146916,"min":0.03951746,"recorded_attempt_count":16,"run_count":8,"total":0.662782031},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.029078938,"mean":0.015562441375000001,"median":0.013116718500000001,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.12449953100000001}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.029078938,"mean":0.015562441375000001,"median":0.013116718500000001,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.124499531},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.10909930499999998,"mean":0.082847753875,"median":0.084146916,"min":0.03951746,"recorded_attempt_count":16,"run_count":8,"total":0.662782031}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.10909930499999998,"mean":0.049205097625000006,"median":0.034298199,"min":0.005612805,"recorded_attempt_count":28,"run_count":16,"total":0.7872815620000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214284,"mean_ms":465438.125,"min_ms":42870,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":1214284,"mean_ms":845698.625,"min_ms":162422,"run_count":8},"none":{"attempt_count":12,"max_ms":162843,"mean_ms":85177.625,"min_ms":42870,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":80681,"output_mean":29459.75,"output_min":2689,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":80681,"output_mean":54027.75,"output_min":8210,"run_count":8},"none":{"attempt_count":12,"output_max":7681,"output_mean":4891.75,"output_min":2689,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"highest":49.79095279932275,"none":42.13826236852083},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":471356},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:41Z","match_totals_all":{"draws":332,"losses":388,"wins":388},"match_totals_tracks":{"highest":{"draws":125,"losses":201,"wins":188},"none":{"draws":207,"losses":187,"wins":200}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":77.21666620850746,"mean":43.545245203742624,"min":22.057846645260756},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":17,"overall_ranking_status":"partial","per_game":{"GB2-01":44.19117788523471,"GB2-04":39.474444158374034,"GB2-05":77.21666620850746,"GB2-06":43.617353114418286,"GB2-07":61.26423443502467,"GB2-08":32.98184099437737},"per_game_match_totals_all":{"GB2-01":{"draws":63,"losses":76,"wins":67},"GB2-02":{"draws":70,"losses":6,"wins":2},"GB2-03":{"draws":15,"losses":23,"wins":12},"GB2-04":{"draws":49,"losses":18,"wins":9},"GB2-05":{"draws":0,"losses":75,"wins":97},"GB2-06":{"draws":7,"losses":72,"wins":97},"GB2-07":{"draws":0,"losses":84,"wins":94},"GB2-08":{"draws":128,"losses":34,"wins":10}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":38,"wins":33},"GB2-04":{"draws":49,"losses":18,"wins":9},"GB2-05":{"draws":0,"losses":29,"wins":53},"GB2-06":{"draws":2,"losses":54,"wins":48},"GB2-07":{"draws":0,"losses":43,"wins":43},"GB2-08":{"draws":55,"losses":19,"wins":2}},"none":{"GB2-01":{"draws":44,"losses":38,"wins":34},"GB2-02":{"draws":70,"losses":6,"wins":2},"GB2-03":{"draws":15,"losses":23,"wins":12},"GB2-05":{"draws":0,"losses":46,"wins":44},"GB2-06":{"draws":5,"losses":18,"wins":49},"GB2-07":{"draws":0,"losses":41,"wins":51},"GB2-08":{"draws":73,"losses":15,"wins":8}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1493.2629278529,"GB2-04":1479.6409821341078,"GB2-05":1811.7287474218497,"GB2-06":1412.3428545385407,"GB2-07":1629.281190088032,"GB2-08":1402.9553709497593},"none":{"GB2-01":1482.983885430028,"GB2-02":1477.703775598533,"GB2-03":1410.904948282172,"GB2-05":1411.1338655756442,"GB2-06":1692.7406046026997,"GB2-07":1450.05224599759,"GB2-08":1515.051856910287}},"per_game_tracks":{"highest":{"GB2-01":44.19117788523471,"GB2-04":39.474444158374034,"GB2-05":77.21666620850746,"GB2-06":43.617353114418286,"GB2-07":61.26423443502467,"GB2-08":32.98184099437737},"none":{"GB2-01":43.640363221816266,"GB2-02":22.057846645260756,"GB2-03":32.740913466707504,"GB2-05":41.936055258537635,"GB2-06":66.56206174162008,"GB2-07":42.8080936476681,"GB2-08":45.222502598035426}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.33570261437304,"none":40.75478779311221},"reasoning_agg":{"highest":{"max":77.21666620850746,"mean":46.33570261437304,"min":32.98184099437737},"none":{"max":66.56206174162008,"mean":40.75478779311221,"min":22.057846645260756}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":77.21666620850746,"reasoning_variance":5.5809148212608335},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.21666620850746,"expected_score":35.77544749488418,"reliability_score":89.80707022001744,"uncertainty_avg":10.19292977998257,"uncertainty_penalty":-10.560255119488858},"none":{"ceiling_score":66.56206174162008,"expected_score":48.00206935537634,"reliability_score":88.60098228183321,"uncertainty_avg":11.399017718166789,"uncertainty_penalty":7.247281562264135}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:3b6469f485258e46","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_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002},"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":45.58338513665576},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":18,"finish_reasons":["length","stop"],"indexed_attempts":18,"output_token_observations":18,"total_output_tokens":308283},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-06"],"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.75}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:26:41Z","match_totals_all":{"draws":163,"losses":193,"wins":216},"match_totals_tracks":{"medium":{"draws":163,"losses":193,"wins":216}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":63.086489595554106,"mean":42.42011970249428,"min":23.435946683398193},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":18,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":44,"wins":48},"GB2-02":{"draws":83,"losses":18,"wins":3},"GB2-04":{"draws":68,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":46,"wins":52},"GB2-07":{"draws":0,"losses":46,"wins":56},"GB2-08":{"draws":8,"losses":27,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":44,"wins":48},"GB2-02":{"draws":83,"losses":18,"wins":3},"GB2-04":{"draws":68,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":46,"wins":52},"GB2-07":{"draws":0,"losses":46,"wins":56},"GB2-08":{"draws":8,"losses":27,"wins":49}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1489.2955239513867,"GB2-02":1477.9100862300777,"GB2-04":1445.2230735526018,"GB2-05":1604.103283115645,"GB2-07":1510.1505201787807,"GB2-08":1688.6711614594897}},"per_game_tracks":{"medium":{"GB2-01":43.91721529100322,"GB2-02":23.435946683398193,"GB2-04":34.63241298761103,"GB2-05":59.168257240229266,"GB2-07":49.25998902213876,"GB2-08":63.086489595554106}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":42.42011970249428},"reasoning_agg":{"medium":{"max":63.086489595554106,"mean":42.42011970249428,"min":23.435946683398193}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.086489595554106},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.086489595554106,"expected_score":44.89280028040134,"reliability_score":92.69780416162251,"uncertainty_avg":7.3021958383774885,"uncertainty_penalty":2.472680577907056}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:2295a106326bfd7d","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"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":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239874999999997}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":44.10198903600353,"none":43.48832517883201},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"total_output_tokens":178317},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:11Z","match_totals_all":{"draws":430,"losses":397,"wins":393},"match_totals_tracks":{"medium":{"draws":240,"losses":203,"wins":209},"none":{"draws":190,"losses":194,"wins":184}},"model_slug":"qwen-qwen3-7-max","overall":{"max":79.13676897206143,"mean":42.357283712111325,"min":15.302941621960535},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":19,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":51,"losses":64,"wins":51},"GB2-02":{"draws":127,"losses":14,"wins":11},"GB2-03":{"draws":44,"losses":7,"wins":5},"GB2-04":{"draws":58,"losses":20,"wins":16},"GB2-05":{"draws":0,"losses":102,"wins":106},"GB2-06":{"draws":13,"losses":91,"wins":84},"GB2-07":{"draws":0,"losses":41,"wins":109},"GB2-08":{"draws":137,"losses":58,"wins":11}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":28,"losses":48,"wins":10},"GB2-02":{"draws":72,"losses":9,"wins":3},"GB2-04":{"draws":58,"losses":20,"wins":16},"GB2-05":{"draws":0,"losses":53,"wins":59},"GB2-06":{"draws":11,"losses":31,"wins":54},"GB2-07":{"draws":0,"losses":14,"wins":58},"GB2-08":{"draws":71,"losses":28,"wins":9}},"none":{"GB2-01":{"draws":23,"losses":16,"wins":41},"GB2-02":{"draws":55,"losses":5,"wins":8},"GB2-03":{"draws":44,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":49,"wins":47},"GB2-06":{"draws":2,"losses":60,"wins":30},"GB2-07":{"draws":0,"losses":27,"wins":51},"GB2-08":{"draws":66,"losses":30,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1214.7994373479398,"GB2-02":1465.43993039221,"GB2-04":1491.404650141681,"GB2-05":1562.335337787397,"GB2-06":1615.8418485040806,"GB2-07":1805.412687918018,"GB2-08":1427.2167537575},"none":{"GB2-01":1652.4221322011101,"GB2-02":1493.9557794402522,"GB2-03":1445.7895878905797,"GB2-05":1525.507550969813,"GB2-06":1238.9945909503178,"GB2-07":1704.7019054474856,"GB2-08":1379.4580243708433}},"per_game_tracks":{"medium":{"GB2-01":15.302941621960535,"GB2-02":19.68138864924798,"GB2-04":42.00273303004231,"GB2-05":55.69921153212445,"GB2-06":60.61195345345551,"GB2-07":79.13676897206143,"GB2-08":36.278925993132454},"none":{"GB2-01":60.386461607802104,"GB2-02":24.982247392476896,"GB2-03":38.09206930228779,"GB2-05":52.175510141908525,"GB2-06":28.822041323047518,"GB2-07":68.87219421844685,"GB2-08":31.087752265854334}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":42.654041799293545,"none":42.060525624929106},"reasoning_agg":{"medium":{"max":79.13676897206143,"mean":42.654041799293545,"min":15.302941621960535},"none":{"max":68.87219421844685,"mean":42.060525624929106,"min":24.982247392476896}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":79.13676897206143,"reasoning_variance":0.5935161743644386},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":79.13676897206143,"expected_score":41.59520904513601,"reliability_score":91.84251452345784,"uncertainty_avg":8.157485476542167,"uncertainty_penalty":-1.0588327541575353},"none":{"ceiling_score":68.87219421844685,"expected_score":50.377016824656785,"reliability_score":87.87910303512052,"uncertainty_avg":12.120896964879478,"uncertainty_penalty":8.316491199727679}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:d5dcb828dbee1dd0","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001},"codegen_latency_ms":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8}},"codegen_output_tokens":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8}},"display_name":"GPT 4.1","economics":{"none":41.47586576190677},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":11,"finish_reasons":["stop"],"indexed_attempts":11,"output_token_observations":11,"total_output_tokens":35469},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:31Z","match_totals_all":{"draws":228,"losses":224,"wins":199},"match_totals_tracks":{"none":{"draws":228,"losses":224,"wins":199}},"model_slug":"gpt-4-1","overall":{"max":63.331047607164344,"mean":41.47586576190677,"min":18.508036486618778},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":20,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":31,"wins":55},"GB2-02":{"draws":60,"losses":11,"wins":1},"GB2-03":{"draws":25,"losses":23,"wins":22},"GB2-04":{"draws":56,"losses":14,"wins":4},"GB2-05":{"draws":0,"losses":64,"wins":26},"GB2-06":{"draws":10,"losses":31,"wins":43},"GB2-07":{"draws":0,"losses":35,"wins":37},"GB2-08":{"draws":72,"losses":15,"wins":11}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":5,"losses":31,"wins":55},"GB2-02":{"draws":60,"losses":11,"wins":1},"GB2-03":{"draws":25,"losses":23,"wins":22},"GB2-04":{"draws":56,"losses":14,"wins":4},"GB2-05":{"draws":0,"losses":64,"wins":26},"GB2-06":{"draws":10,"losses":31,"wins":43},"GB2-07":{"draws":0,"losses":35,"wins":37},"GB2-08":{"draws":72,"losses":15,"wins":11}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1678.161582569883,"GB2-02":1469.498417326438,"GB2-03":1538.6746024305037,"GB2-04":1443.1168128216952,"GB2-05":1146.4306765922527,"GB2-06":1572.6488159742216,"GB2-07":1559.8690234891826,"GB2-08":1407.8185070181821}},"per_game_tracks":{"none":{"GB2-01":63.331047607164344,"GB2-02":19.821595384418693,"GB2-03":51.97927682744617,"GB2-04":33.71863054561698,"GB2-05":18.508036486618778,"GB2-06":56.74330710655394,"GB2-07":53.65187154398772,"GB2-08":34.05316059344751}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":41.47586576190677},"reasoning_agg":{"none":{"max":63.331047607164344,"mean":41.47586576190677,"min":18.508036486618778}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.331047607164344},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":63.331047607164344,"expected_score":51.27150094955935,"reliability_score":88.35717405090311,"uncertainty_avg":11.642825949096883,"uncertainty_penalty":9.795635187652586}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:1f2ff8329154ac84","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":15,"cost_basis_counts":{"provider_reported":27},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.2996388,"mean":0.08564151856,"median":0.0495450162,"min":0.0057139812,"recorded_attempt_count":27,"run_count":15,"total":1.2846227784},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":46.17892461527247,"none":40.66399209647053},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["error","length","stop"],"indexed_attempts":27,"output_token_observations":27,"total_output_tokens":643548},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.2857142857142857}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:01Z","match_totals_all":{"draws":232,"losses":369,"wins":367},"match_totals_tracks":{"medium":{"draws":110,"losses":186,"wins":168},"none":{"draws":122,"losses":183,"wins":199}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":68.98589007065465,"mean":41.0505200712072,"min":25.444968645038077},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete","fixed_coverage_incomplete"],"overall_official_rank":21,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":47,"wins":32},"GB2-02":{"draws":58,"losses":7,"wins":5},"GB2-03":{"draws":34,"losses":14,"wins":14},"GB2-04":{"draws":43,"losses":17,"wins":16},"GB2-05":{"draws":0,"losses":105,"wins":83},"GB2-06":{"draws":2,"losses":73,"wins":109},"GB2-07":{"draws":0,"losses":86,"wins":106},"GB2-08":{"draws":66,"losses":20,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":43,"losses":17,"wins":16},"GB2-05":{"draws":0,"losses":65,"wins":35},"GB2-06":{"draws":1,"losses":33,"wins":60},"GB2-07":{"draws":0,"losses":51,"wins":55},"GB2-08":{"draws":66,"losses":20,"wins":2}},"none":{"GB2-01":{"draws":29,"losses":47,"wins":32},"GB2-02":{"draws":58,"losses":7,"wins":5},"GB2-03":{"draws":34,"losses":14,"wins":14},"GB2-05":{"draws":0,"losses":40,"wins":48},"GB2-06":{"draws":1,"losses":40,"wins":49},"GB2-07":{"draws":0,"losses":35,"wins":51}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1553.5411300031487,"GB2-05":1302.4616251701777,"GB2-06":1715.7619684800297,"GB2-07":1487.9631011121937,"GB2-08":1384.997724777921},"none":{"GB2-01":1418.7059748335482,"GB2-02":1495.3456741149573,"GB2-03":1459.8196949799096,"GB2-05":1432.2526700075625,"GB2-06":1425.7039967938965,"GB2-07":1549.490807576366}},"per_game_tracks":{"medium":{"GB2-04":50.930917233328884,"GB2-05":32.506339570901225,"GB2-06":68.98589007065465,"GB2-07":47.03435356364199,"GB2-08":31.43712263783562},"none":{"GB2-01":36.856998866883636,"GB2-02":25.444968645038077,"GB2-03":40.43722567444062,"GB2-05":43.763744651369436,"GB2-06":44.498198272140634,"GB2-07":52.982816468950794}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":42.974331635082116,"none":39.12670850733229},"reasoning_agg":{"medium":{"max":68.98589007065465,"mean":42.974331635082116,"min":31.43712263783562},"none":{"max":52.982816468950794,"mean":39.12670850733229,"min":25.444968645038077}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":68.98589007065465,"reasoning_variance":3.847623127749827},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":68.98589007065465,"expected_score":45.854686726803315,"reliability_score":91.87644324056454,"uncertainty_avg":8.123556759435465,"uncertainty_penalty":2.8803550917211993},"none":{"ceiling_score":52.982816468950794,"expected_score":47.52243523066809,"reliability_score":88.87596023601249,"uncertainty_avg":11.124039763987517,"uncertainty_penalty":8.395726723335798}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:bf2b00ecdde1f74d","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-08-08":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-08-08":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-08-08":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425},"codegen_latency_ms":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1}},"codegen_output_tokens":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1}},"display_name":"GPT 4.1 Nano","economics":{"none":39.72974279439747},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":1,"finish_reasons":["stop"],"indexed_attempts":2,"output_token_observations":2,"reasoning_token_observations":1,"total_output_tokens":2006,"total_visible_output_tokens":64,"visible_token_observations":1},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-08-14T15:31:41Z","match_totals_all":{"draws":35,"losses":67,"wins":60},"match_totals_tracks":{"none":{"draws":35,"losses":67,"wins":60}},"model_slug":"gpt-4-1-nano","overall":{"max":39.72974279439747,"mean":39.72974279439747,"min":39.72974279439747},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":67,"wins":60}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":35,"losses":67,"wins":60}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1439.5094730893666}},"per_game_tracks":{"none":{"GB2-01":39.72974279439747}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":39.72974279439747},"reasoning_agg":{"none":{"max":39.72974279439747,"mean":39.72974279439747,"min":39.72974279439747}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":39.72974279439747},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":39.72974279439747,"expected_score":47.86414347565057,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.134400681253105}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:657efc023ad7cc85","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.4852846}},"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":0.48528460000000007},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":39.4814143462601},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":17,"output_token_observations":17,"total_output_tokens":179458},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":8,"repaired_rate":1.0}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:34:43Z","match_totals_all":{"draws":276,"losses":241,"wins":209},"match_totals_tracks":{"medium":{"draws":276,"losses":241,"wins":209}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":67.9767252117913,"mean":39.4814143462601,"min":21.895370370120215},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":23,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":33,"wins":42},"GB2-02":{"draws":73,"losses":2,"wins":3},"GB2-03":{"draws":26,"losses":18,"wins":16},"GB2-04":{"draws":73,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":46,"wins":58},"GB2-06":{"draws":0,"losses":61,"wins":49},"GB2-07":{"draws":0,"losses":62,"wins":30},"GB2-08":{"draws":81,"losses":13,"wins":6}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":23,"losses":33,"wins":42},"GB2-02":{"draws":73,"losses":2,"wins":3},"GB2-03":{"draws":26,"losses":18,"wins":16},"GB2-04":{"draws":73,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":46,"wins":58},"GB2-06":{"draws":0,"losses":61,"wins":49},"GB2-07":{"draws":0,"losses":62,"wins":30},"GB2-08":{"draws":81,"losses":13,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1508.6558361046946,"GB2-02":1476.9758894809659,"GB2-03":1420.1877638819335,"GB2-04":1485.9213014671434,"GB2-05":1702.4608950678553,"GB2-06":1443.244562486499,"GB2-07":1264.6371016053838,"GB2-08":1412.9235515651562}},"per_game_tracks":{"medium":{"GB2-01":45.96146347343779,"GB2-02":21.895370370120215,"GB2-03":34.72802275090764,"GB2-04":40.788828941639004,"GB2-05":67.9767252117913,"GB2-06":46.30821047229321,"GB2-07":23.563915845571497,"GB2-08":34.62877770432017}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.4814143462601},"reasoning_agg":{"medium":{"max":67.9767252117913,"mean":39.4814143462601,"min":21.895370370120215}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":67.9767252117913},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":67.9767252117913,"expected_score":32.63176531430405,"reliability_score":90.92378901094423,"uncertainty_avg":9.076210989055772,"uncertainty_penalty":-6.849649031956055}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:3bcc7f6323eff7b9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.957684},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586000000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.452750000000002},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":40.33645773867913,"highest":44.78487833740139,"medium":40.08960539503473,"none":34.74902962197964},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":1,"effective_max_output_tokens":[131072],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"reconciliation_get_attempts":142,"requested_max_output_token_observations":1,"requested_max_output_tokens":[131072],"total_output_tokens":994500,"total_reasoning_output_tokens":878493,"total_visible_output_tokens":116007,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.8,"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.2,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-08-23T01:51:58Z","match_totals_all":{"draws":132,"losses":115,"wins":162},"match_totals_tracks":{"highest":{"draws":36,"losses":29,"wins":64},"medium":{"draws":44,"losses":41,"wins":59},"none":{"draws":52,"losses":45,"wins":39}},"model_slug":"qwen-qwen3-8-max","overall":{"max":68.66906686669674,"mean":39.06451930494661,"min":7.529917385447114},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":24,"overall_ranking_status":"partial","per_game":{"GB2-02":20.752949450340513,"GB2-03":42.74500116475145,"GB2-04":50.942602650877994,"GB2-05":49.02675226585254,"GB2-06":47.93379015513136,"GB2-07":68.66906686669674,"GB2-08":33.42398580815915},"per_game_all":{"GB2-02":13.371443087330277,"GB2-03":36.548036782264575,"GB2-04":37.512571451164185,"GB2-05":55.7694216891426,"GB2-06":44.849706244516675,"GB2-07":51.946572171298065,"GB2-08":42.3574527450375},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":17,"wins":9},"GB2-02":{"draws":45,"losses":6,"wins":3},"GB2-03":{"draws":12,"losses":19,"wins":15},"GB2-04":{"draws":36,"losses":9,"wins":13},"GB2-05":{"draws":0,"losses":17,"wins":42},"GB2-06":{"draws":3,"losses":24,"wins":24},"GB2-07":{"draws":0,"losses":17,"wins":40},"GB2-08":{"draws":30,"losses":6,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":13,"losses":1,"wins":3},"GB2-03":{"draws":1,"losses":7,"wins":9},"GB2-04":{"draws":10,"losses":1,"wins":9},"GB2-05":{"draws":0,"losses":9,"wins":13},"GB2-06":{"draws":0,"losses":7,"wins":8},"GB2-07":{"draws":0,"losses":0,"wins":20},"GB2-08":{"draws":12,"losses":4,"wins":2}},"medium":{"GB2-01":{"draws":5,"losses":4,"wins":7},"GB2-02":{"draws":18,"losses":2,"wins":0},"GB2-03":{"draws":6,"losses":5,"wins":5},"GB2-04":{"draws":9,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":8,"wins":12},"GB2-06":{"draws":1,"losses":6,"wins":13},"GB2-07":{"draws":0,"losses":10,"wins":8},"GB2-08":{"draws":5,"losses":2,"wins":11}},"none":{"GB2-01":{"draws":1,"losses":13,"wins":2},"GB2-02":{"draws":14,"losses":3,"wins":0},"GB2-03":{"draws":5,"losses":7,"wins":1},"GB2-04":{"draws":17,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":0,"wins":17},"GB2-06":{"draws":2,"losses":11,"wins":3},"GB2-07":{"draws":0,"losses":7,"wins":12},"GB2-08":{"draws":13,"losses":0,"wins":3}}},"per_game_raw_elo_all":{"GB2-02":1485.735232477331,"GB2-03":1481.2682424148745,"GB2-04":1510.6373867424802,"GB2-05":1613.8243862875117,"GB2-06":1482.716176663085,"GB2-07":1586.1209503772106,"GB2-08":1540.5529453777665},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1521.1352852847508,"GB2-03":1520.056619582484,"GB2-04":1595.3194324712535,"GB2-05":1532.722998103657,"GB2-06":1524.5925491348792,"GB2-07":1745.028439951044,"GB2-08":1453.3660051372515},"medium":{"GB2-01":1504.6122502478056,"GB2-02":1474.173692393705,"GB2-03":1500.9877282935317,"GB2-04":1476.9628271566362,"GB2-05":1580.8596132907571,"GB2-06":1599.7715708378887,"GB2-07":1454.0796217693523,"GB2-08":1632.7448564416845},"none":{"GB2-01":1367.2484890428086,"GB2-02":1461.8967197535371,"GB2-03":1422.7603793686078,"GB2-04":1459.6299005995513,"GB2-05":1727.8905474681214,"GB2-06":1323.7844100164866,"GB2-07":1559.254789411236,"GB2-08":1535.547974554364}},"per_game_tracks":{"highest":{"GB2-02":20.752949450340513,"GB2-03":42.74500116475145,"GB2-04":50.942602650877994,"GB2-05":49.02675226585254,"GB2-06":47.93379015513136,"GB2-07":68.66906686669674,"GB2-08":33.42398580815915},"medium":{"GB2-01":39.66966887583633,"GB2-02":11.831462426203206,"GB2-03":39.667892968316686,"GB2-04":31.086249261383635,"GB2-05":52.94363834256713,"GB2-06":55.331168423892514,"GB2-07":38.00669500599334,"GB2-08":52.180067856085},"none":{"GB2-01":25.4679471098268,"GB2-02":7.529917385447114,"GB2-03":27.231216213725585,"GB2-04":30.50886244123093,"GB2-05":65.33787445900813,"GB2-06":31.28416015452614,"GB2-07":49.16395464120409,"GB2-08":41.46830457086832}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.35492289782546,"medium":40.089605395034724,"none":34.749029621979645},"reasoning_agg":{"highest":{"max":68.66906686669674,"mean":42.35492289782546,"min":20.752949450340513},"medium":{"max":55.331168423892514,"mean":40.089605395034724,"min":11.831462426203206},"none":{"max":65.33787445900813,"mean":34.749029621979645,"min":7.529917385447114}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":68.66906686669674,"expected_score":42.9643970361098,"reasoning_variance":7.6058932758458155,"reliability_score":28.269403278676293,"uncertainty_avg":71.7305967213237,"uncertainty_penalty":3.899877731163194},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.66906686669674,"expected_score":35.29465133940456,"reliability_score":29.766396486381936,"uncertainty_avg":70.23360351361806,"uncertainty_penalty":-7.060271558420901},"medium":{"ceiling_score":55.331168423892514,"expected_score":42.285364160656854,"reliability_score":28.681749152618764,"uncertainty_avg":71.31825084738124,"uncertainty_penalty":2.1957587656221307},"none":{"ceiling_score":65.33787445900813,"expected_score":48.81874222878122,"reliability_score":25.100384398780704,"uncertainty_avg":74.8996156012193,"uncertainty_penalty":14.069712606801573}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:55f0d0ca5e9d66ef","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.14705250000000003},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.168810400000001},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":46.812644270765105,"none":30.595878931104806},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":21,"finish_reasons":["incomplete","stop"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":2,"total_output_tokens":1096010,"total_reasoning_output_tokens":255888,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:18Z","match_totals_all":{"draws":517,"losses":457,"wins":407},"match_totals_tracks":{"medium":{"draws":219,"losses":217,"wins":287},"none":{"draws":298,"losses":240,"wins":120}},"model_slug":"gpt-5-4-mini","overall":{"max":58.26867546532442,"mean":38.704261600934956,"min":7.108412173273799},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":25,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":42,"losses":69,"wins":67},"GB2-02":{"draws":148,"losses":3,"wins":3},"GB2-03":{"draws":105,"losses":22,"wins":16},"GB2-04":{"draws":101,"losses":20,"wins":35},"GB2-05":{"draws":0,"losses":105,"wins":93},"GB2-06":{"draws":18,"losses":80,"wins":92},"GB2-07":{"draws":0,"losses":112,"wins":68},"GB2-08":{"draws":103,"losses":46,"wins":33}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":29,"wins":47},"GB2-02":{"draws":77,"losses":2,"wins":3},"GB2-03":{"draws":40,"losses":18,"wins":15},"GB2-04":{"draws":49,"losses":8,"wins":19},"GB2-05":{"draws":0,"losses":46,"wins":66},"GB2-06":{"draws":12,"losses":37,"wins":49},"GB2-07":{"draws":0,"losses":43,"wins":55},"GB2-08":{"draws":37,"losses":34,"wins":33}},"none":{"GB2-01":{"draws":38,"losses":40,"wins":20},"GB2-02":{"draws":71,"losses":1,"wins":0},"GB2-03":{"draws":65,"losses":4,"wins":1},"GB2-04":{"draws":52,"losses":12,"wins":16},"GB2-05":{"draws":0,"losses":59,"wins":27},"GB2-06":{"draws":6,"losses":43,"wins":43},"GB2-07":{"draws":0,"losses":69,"wins":13},"GB2-08":{"draws":66,"losses":12,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1631.9382025233147,"GB2-02":1475.896463396586,"GB2-03":1479.5678575239842,"GB2-04":1552.3585485416486,"GB2-05":1570.4972105951804,"GB2-06":1577.603307582626,"GB2-07":1513.4758066512193,"GB2-08":1429.4598339312142},"none":{"GB2-01":1377.9183970053725,"GB2-02":1472.7375666323005,"GB2-03":1480.862249672601,"GB2-04":1469.0718049538236,"GB2-05":1289.417656335887,"GB2-06":1350.5359335828546,"GB2-07":1108.5181051201985,"GB2-08":1407.788041459873}},"per_game_tracks":{"medium":{"GB2-01":58.26867546532442,"GB2-02":21.89947442115403,"GB2-03":43.7743274862355,"GB2-04":50.747585899586106,"GB2-05":56.42159236209911,"GB2-06":57.42832822067658,"GB2-07":49.52329772108889,"GB2-08":36.437872589956235},"none":{"GB2-01":32.44482183373839,"GB2-02":20.5446273273821,"GB2-03":43.819799277453555,"GB2-04":38.01263971429604,"GB2-05":31.078992764114222,"GB2-06":38.20986690104408,"GB2-07":7.108412173273799,"GB2-08":33.54787145753626}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.81264427076511,"none":30.595878931104806},"reasoning_agg":{"medium":{"max":58.26867546532442,"mean":46.81264427076511,"min":21.89947442115403},"none":{"max":43.819799277453555,"mean":30.595878931104806,"min":7.108412173273799}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":58.26867546532442,"reasoning_variance":16.216765339660306},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":58.26867546532442,"expected_score":42.464343577270824,"reliability_score":91.01542228191786,"uncertainty_avg":8.984577718082132,"uncertainty_penalty":-4.348300693494288},"none":{"ceiling_score":43.819799277453555,"expected_score":37.13245016351214,"reliability_score":88.71789508177106,"uncertainty_avg":11.282104918228933,"uncertainty_penalty":6.536571232407333}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:21e1db315087268e","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999},"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821378999999998},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":42.61298325940131,"none":38.74874374094833},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["incomplete","stop"],"indexed_attempts":57,"output_token_observations":57,"reasoning_token_observations":2,"total_output_tokens":752982,"total_reasoning_output_tokens":128000,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-03","GB2-04","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:07Z","match_totals_all":{"draws":507,"losses":802,"wins":731},"match_totals_tracks":{"medium":{"draws":200,"losses":416,"wins":410},"none":{"draws":307,"losses":386,"wins":321}},"model_slug":"gpt-5-4-nano","overall":{"max":63.14422335372282,"mean":37.857809245731936,"min":15.136633992883711},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":26,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":77,"losses":158,"wins":109},"GB2-02":{"draws":207,"losses":14,"wins":3},"GB2-03":{"draws":30,"losses":25,"wins":25},"GB2-04":{"draws":54,"losses":6,"wins":24},"GB2-05":{"draws":0,"losses":211,"wins":135},"GB2-06":{"draws":7,"losses":139,"wins":214},"GB2-07":{"draws":0,"losses":153,"wins":111},"GB2-08":{"draws":132,"losses":96,"wins":110}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":26,"losses":109,"wins":33},"GB2-02":{"draws":68,"losses":2,"wins":0},"GB2-04":{"draws":54,"losses":6,"wins":24},"GB2-05":{"draws":0,"losses":83,"wins":97},"GB2-06":{"draws":6,"losses":67,"wins":115},"GB2-07":{"draws":0,"losses":96,"wins":74},"GB2-08":{"draws":46,"losses":53,"wins":67}},"none":{"GB2-01":{"draws":51,"losses":49,"wins":76},"GB2-02":{"draws":139,"losses":12,"wins":3},"GB2-03":{"draws":30,"losses":25,"wins":25},"GB2-05":{"draws":0,"losses":128,"wins":38},"GB2-06":{"draws":1,"losses":72,"wins":99},"GB2-07":{"draws":0,"losses":57,"wins":37},"GB2-08":{"draws":86,"losses":43,"wins":43}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1214.2842678515308,"GB2-02":1477.8595823514117,"GB2-04":1577.9623544152807,"GB2-05":1540.5178969518408,"GB2-06":1646.3542719474497,"GB2-07":1414.3017135371133,"GB2-08":1574.610446657007},"none":{"GB2-01":1609.1217179945165,"GB2-02":1467.1081705185377,"GB2-03":1510.9851115234762,"GB2-05":1177.5020483483413,"GB2-06":1529.0020375469994,"GB2-07":1323.4878955652127,"GB2-08":1497.1120170443423}},"per_game_tracks":{"medium":{"GB2-01":15.136633992883711,"GB2-02":21.54178243508168,"GB2-04":55.05762102524152,"GB2-05":53.353895713407034,"GB2-06":63.14422335372282,"GB2-07":38.923736548942394,"GB2-08":51.13298974653004},"none":{"GB2-01":56.113615016738166,"GB2-02":19.627918979635304,"GB2-03":48.4984550891471,"GB2-05":21.10631739223014,"GB2-06":53.100496566401134,"GB2-07":29.717577482950762,"GB2-08":43.07682565953572}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.655849282035284,"none":36.05976920942859},"reasoning_agg":{"medium":{"max":63.14422335372282,"mean":39.655849282035284,"min":15.136633992883711},"none":{"max":56.113615016738166,"mean":36.05976920942859,"min":19.627918979635304}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.14422335372282,"reasoning_variance":3.5960800726066964},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.14422335372282,"expected_score":41.51341396719902,"reliability_score":89.28870883481922,"uncertainty_avg":10.71129116518078,"uncertainty_penalty":1.8575646851637373},"none":{"ceiling_score":56.113615016738166,"expected_score":44.06245180081017,"reliability_score":89.62288200165422,"uncertainty_avg":10.377117998345776,"uncertainty_penalty":8.002682591381586}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:0ccf02fcc67f023e","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":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.24666659999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054444999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.050544450000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399885},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":37.80451197917877,"highest":52.76207198216007,"medium":40.16990167973068,"none":20.481562275645565},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":238178,"total_reasoning_output_tokens":167062,"total_visible_output_tokens":71116,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-08-23T12:40:55Z","match_totals_all":{"draws":604,"losses":857,"wins":597},"match_totals_tracks":{"highest":{"draws":200,"losses":175,"wins":306},"medium":{"draws":217,"losses":268,"wins":203},"none":{"draws":187,"losses":414,"wins":88}},"model_slug":"gpt-5-6-luna","overall":{"max":83.09168848413222,"mean":37.80451197917878,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.39863746617029,"GB2-02":26.812606919993172,"GB2-03":43.671930557268624,"GB2-04":30.587564175213476,"GB2-05":58.37713182359818,"GB2-06":83.09168848413222,"GB2-07":74.93025959728134,"GB2-08":24.22675683362329},"per_game_all":{"GB2-01":49.860170721692555,"GB2-02":23.867038999653193,"GB2-03":36.28091043016276,"GB2-04":34.15892590290696,"GB2-05":45.8094886186309,"GB2-06":56.717140802146076,"GB2-07":39.3095450060017,"GB2-08":16.43287535223604},"per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":127,"wins":116},"GB2-02":{"draws":179,"losses":11,"wins":6},"GB2-03":{"draws":116,"losses":111,"wins":44},"GB2-04":{"draws":154,"losses":49,"wins":31},"GB2-05":{"draws":0,"losses":143,"wins":136},"GB2-06":{"draws":14,"losses":115,"wins":143},"GB2-07":{"draws":0,"losses":160,"wins":112},"GB2-08":{"draws":118,"losses":141,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":20,"wins":68},"GB2-02":{"draws":58,"losses":3,"wins":5},"GB2-03":{"draws":39,"losses":30,"wins":19},"GB2-04":{"draws":44,"losses":23,"wins":11},"GB2-05":{"draws":0,"losses":35,"wins":59},"GB2-06":{"draws":8,"losses":9,"wins":72},"GB2-07":{"draws":0,"losses":20,"wins":70},"GB2-08":{"draws":51,"losses":35,"wins":2}},"medium":{"GB2-01":{"draws":11,"losses":39,"wins":39},"GB2-02":{"draws":63,"losses":2,"wins":1},"GB2-03":{"draws":27,"losses":42,"wins":22},"GB2-04":{"draws":58,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":49,"wins":44},"GB2-06":{"draws":3,"losses":32,"wins":56},"GB2-07":{"draws":0,"losses":61,"wins":29},"GB2-08":{"draws":55,"losses":32,"wins":3}},"none":{"GB2-01":{"draws":12,"losses":68,"wins":9},"GB2-02":{"draws":58,"losses":6,"wins":0},"GB2-03":{"draws":50,"losses":39,"wins":3},"GB2-04":{"draws":52,"losses":15,"wins":11},"GB2-05":{"draws":0,"losses":59,"wins":33},"GB2-06":{"draws":3,"losses":74,"wins":15},"GB2-07":{"draws":0,"losses":79,"wins":13},"GB2-08":{"draws":12,"losses":74,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1548.4063523581872,"GB2-02":1489.9218398441683,"GB2-03":1421.8359768148075,"GB2-04":1444.7724389938367,"GB2-05":1454.2247603564665,"GB2-06":1570.7333806748984,"GB2-07":1416.6464030366117,"GB2-08":1241.1882096967354},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1843.9420024778738,"GB2-02":1502.869141070355,"GB2-03":1474.74320418467,"GB2-04":1421.735317704969,"GB2-05":1596.0023160248443,"GB2-06":1884.4844196491322,"GB2-07":1759.9984530561082,"GB2-08":1316.0394459572435},"medium":{"GB2-01":1561.7387010272973,"GB2-02":1517.6444248483235,"GB2-03":1443.518054717542,"GB2-04":1449.127962983689,"GB2-05":1481.579607297685,"GB2-06":1625.7147784478864,"GB2-07":1338.1870209205915,"GB2-08":1323.6533845849854},"none":{"GB2-01":1239.5383535693904,"GB2-02":1449.2519536138268,"GB2-03":1347.246671542211,"GB2-04":1463.4540362928522,"GB2-05":1285.0923577468707,"GB2-06":1202.0009439276766,"GB2-07":1151.7537351331357,"GB2-08":1083.8717985479768}},"per_game_tracks":{"highest":{"GB2-01":80.39863746617029,"GB2-02":26.812606919993172,"GB2-03":43.671930557268624,"GB2-04":30.587564175213476,"GB2-05":58.37713182359818,"GB2-06":83.09168848413222,"GB2-07":74.93025959728134,"GB2-08":24.22675683362329},"medium":{"GB2-01":51.24671194156034,"GB2-02":30.110695747971825,"GB2-03":39.36327550240593,"GB2-04":34.834147059507195,"GB2-05":48.23068051946542,"GB2-06":61.35124581231818,"GB2-07":31.15058763153171,"GB2-08":25.07186922308482},"none":{"GB2-01":17.93516275734703,"GB2-02":14.67781433099459,"GB2-03":25.807525230813738,"GB2-04":37.05506647400019,"GB2-05":30.820653512829104,"GB2-06":25.70848810998782,"GB2-07":11.847787789192054,"GB2-08":0.0}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.76207198216008,"medium":40.169901679730685,"none":20.481562275645565},"reasoning_agg":{"highest":{"max":83.09168848413222,"mean":52.76207198216008,"min":24.22675683362329},"medium":{"max":61.35124581231818,"mean":40.169901679730685,"min":25.07186922308482},"none":{"max":37.05506647400019,"mean":20.481562275645565,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":83.09168848413222,"expected_score":32.50570678923648,"reasoning_variance":32.280509706514515,"reliability_score":89.82341437352544,"uncertainty_avg":10.176585626474562,"uncertainty_penalty":-5.2988051899423},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.09168848413222,"expected_score":39.34680386558436,"reliability_score":89.65542670809569,"uncertainty_avg":10.344573291904306,"uncertainty_penalty":-13.415268116575717},"medium":{"ceiling_score":61.35124581231818,"expected_score":34.691909263071615,"reliability_score":89.91243776155054,"uncertainty_avg":10.087562238449461,"uncertainty_penalty":-5.47799241665907},"none":{"ceiling_score":37.05506647400019,"expected_score":23.478407239053457,"reliability_score":89.90237865093007,"uncertainty_avg":10.097621349069922,"uncertainty_penalty":2.9968449634078915}}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:54cad6d3f7756427","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999},"historical-provider-setting-intensive":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":29,"cell_count":24,"cost_basis_counts":{"estimated":40,"local_standard_estimate":29},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":19,"max":0.17217,"mean":0.08358424999999998,"median":0.08653749999999999,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-08-08":56},"recorded_attempt_count":40,"run_count":48,"token_priced_attempt_count":29,"total":4.2016860000000005},"codegen_latency_ms":{"attempt_count":29,"max_ms":130647,"mean_ms":59683.958333333336,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":13,"max_ms":130647,"mean_ms":108464.0,"min_ms":46796,"run_count":8}},"codegen_output_tokens":{"attempt_count":69,"output_max":15813,"output_mean":8194.3125,"output_min":2653,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":21,"output_max":14517,"output_mean":8935.125,"output_min":5431,"run_count":8}},"display_name":"O3","economics":{"all":43.02874094408157,"highest":48.78091738661657,"medium":50.20675055685003,"none":27.169386199575268},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":93,"output_token_observations":69,"reasoning_token_observations":13,"total_output_tokens":393327,"total_reasoning_output_tokens":26752,"total_visible_output_tokens":24077,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.59375,"model_code_failure_rate":0.40625,"model_code_failures":13,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-08-23T12:51:52Z","match_totals_all":{"draws":597,"losses":1760,"wins":1649},"match_totals_tracks":{"highest":{"draws":282,"losses":1224,"wins":1295},"medium":{"draws":143,"losses":185,"wins":238},"none":{"draws":172,"losses":351,"wins":116}},"model_slug":"o3","overall":{"max":62.569827155594346,"mean":37.46323340271141,"min":2.8219078055756306},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":28,"overall_ranking_status":"partial","per_game":{"GB2-01":56.03900598894137,"GB2-03":39.158820258821116,"GB2-05":53.94753611433414,"GB2-06":51.19784527381407,"GB2-07":47.0302536987219,"GB2-08":45.3120429850668},"per_game_all":{"GB2-01":34.41887462396962,"GB2-06":44.889302096746725,"GB2-07":54.53155750763196,"GB2-08":38.275229547977965},"per_game_match_totals_all":{"GB2-01":{"draws":91,"losses":301,"wins":274},"GB2-03":{"draws":46,"losses":55,"wins":27},"GB2-04":{"draws":60,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":318,"wins":396},"GB2-06":{"draws":51,"losses":428,"wins":360},"GB2-07":{"draws":0,"losses":436,"wins":420},"GB2-08":{"draws":349,"losses":211,"wins":163}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":151,"wins":235},"GB2-03":{"draws":46,"losses":55,"wins":27},"GB2-05":{"draws":0,"losses":275,"wins":335},"GB2-06":{"draws":17,"losses":280,"wins":286},"GB2-07":{"draws":0,"losses":326,"wins":282},"GB2-08":{"draws":187,"losses":137,"wins":130}},"medium":{"GB2-01":{"draws":17,"losses":39,"wins":34},"GB2-04":{"draws":60,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":43,"wins":61},"GB2-06":{"draws":9,"losses":33,"wins":50},"GB2-07":{"draws":0,"losses":32,"wins":56},"GB2-08":{"draws":57,"losses":27,"wins":28}},"none":{"GB2-01":{"draws":42,"losses":111,"wins":5},"GB2-06":{"draws":25,"losses":115,"wins":24},"GB2-07":{"draws":0,"losses":78,"wins":82},"GB2-08":{"draws":105,"losses":47,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1392.6390051959243,"GB2-06":1423.6335918457225,"GB2-07":1556.9513715044147,"GB2-08":1441.956726118867},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1599.7594820788852,"GB2-03":1435.5845812595855,"GB2-05":1537.2233988941953,"GB2-06":1496.398635934153,"GB2-07":1481.5992503742432,"GB2-08":1507.7257361361333},"medium":{"GB2-01":1495.2412310238194,"GB2-04":1458.678974566677,"GB2-05":1575.6242718976087,"GB2-06":1610.9544501736414,"GB2-07":1641.3758195563273,"GB2-08":1471.633977758998},"none":{"GB2-01":1082.9163024850677,"GB2-06":1163.5476894293736,"GB2-07":1547.8790445826737,"GB2-08":1346.5104644614696}},"per_game_tracks":{"highest":{"GB2-01":56.03900598894137,"GB2-03":39.158820258821116,"GB2-05":53.94753611433414,"GB2-06":51.19784527381407,"GB2-07":47.0302536987219,"GB2-08":45.3120429850668},"medium":{"GB2-01":44.395710077391875,"GB2-04":36.401476747289344,"GB2-05":56.75082800967719,"GB2-06":60.12787105389861,"GB2-07":62.569827155594346,"GB2-08":40.99479029724878},"none":{"GB2-01":2.8219078055756306,"GB2-06":23.342189962527502,"GB2-07":53.99459166857962,"GB2-08":28.51885536161832}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.82041472033598,"medium":46.72264602793167,"none":22.846639459866584},"reasoning_agg":{"highest":{"max":56.03900598894137,"mean":42.82041472033598,"min":39.158820258821116},"medium":{"max":62.569827155594346,"mean":46.72264602793167,"min":36.401476747289344},"none":{"max":53.99459166857962,"mean":22.846639459866584,"min":2.8219078055756306}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":62.569827155594346,"expected_score":36.8579883840775,"reasoning_variance":23.876006568065083,"reliability_score":97.54135784869025,"uncertainty_avg":2.458642151309745,"uncertainty_penalty":-0.6052450186339087},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.03900598894137,"expected_score":31.536034228587834,"reliability_score":99.92025214335281,"uncertainty_avg":0.07974785664718197,"uncertainty_penalty":-11.284380491748149},"medium":{"ceiling_score":62.569827155594346,"expected_score":48.153323243620264,"reliability_score":92.30861280081712,"uncertainty_avg":7.691387199182877,"uncertainty_penalty":1.430677215688597},"none":{"ceiling_score":53.99459166857962,"expected_score":25.135038553070206,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2883990932036227}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:2017c74462701082","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0},"medium":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"none":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":79,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":112,"run_count":88,"total":0.0},"codegen_latency_ms":{"attempt_count":112,"max_ms":1487583,"mean_ms":467860.5227272727,"min_ms":38538,"run_count":88},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":31,"max_ms":1487583,"mean_ms":1029047.25,"min_ms":343277,"run_count":28},"medium":{"attempt_count":39,"max_ms":676327,"mean_ms":324151.5,"min_ms":151453,"run_count":30},"none":{"attempt_count":42,"max_ms":287181,"mean_ms":87795.26666666666,"min_ms":38538,"run_count":30}},"codegen_output_tokens":{"attempt_count":112,"output_max":85105,"output_mean":23027.329545454544,"output_min":1660,"run_count":88},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":31,"output_max":85105,"output_mean":50628.67857142857,"output_min":15800,"run_count":28},"medium":{"attempt_count":39,"output_max":33467,"output_mean":16156.733333333334,"output_min":6647,"run_count":30},"none":{"attempt_count":42,"output_max":9871,"output_mean":4136.666666666667,"output_min":1660,"run_count":30}},"display_name":"Ox Alpha","economics":{"all":36.859310208673485,"highest":44.31643372112509,"medium":35.15050484430993,"none":31.11099206058544},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":101,"effective_max_output_tokens":[131072],"finish_reason_observations":110,"finish_reasons":["stop"],"indexed_attempts":114,"output_token_observations":112,"provider_post_attempt_observations":113,"provider_post_attempts":113,"reasoning_token_observations":112,"reconciliation_get_attempt_observations":113,"reconciliation_get_attempts":534,"requested_max_output_token_observations":102,"requested_max_output_tokens":[131072],"total_output_tokens":2026405,"total_visible_output_tokens":2026405,"visible_token_observations":112},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/ox-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":26,"evaluated_cells":30,"failed_game_aliases":["GB2-01","GB2-03","GB2-06"],"first_pass_admitted":21,"first_pass_rate":0.7,"model_code_failure_rate":0.13333333333333333,"model_code_failures":4,"official_qualification":{"coverage_attestation":{"completed_directed_seatings":481,"evidence_sha256":"92cc408e51465c940fc6de770119146d19b9c20359d691863cdff02f59c8079f","focused_entrant_count":66,"full_double_round_robin_complete":true,"policy_id":"focused_full_double_round_robin_attestation_v1","residual_blocked_count":0,"residual_unblocked_count":0,"schema_version":1,"settled_model_fault_directed_seatings":1},"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.16666666666666666},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"model_code_failure_rate":0.06666666666666667,"model_code_failures":2,"official_qualification":{"coverage_attestation":{"completed_directed_seatings":481,"evidence_sha256":"92cc408e51465c940fc6de770119146d19b9c20359d691863cdff02f59c8079f","focused_entrant_count":66,"full_double_round_robin_complete":true,"policy_id":"focused_full_double_round_robin_attestation_v1","residual_blocked_count":0,"residual_unblocked_count":0,"schema_version":1,"settled_model_fault_directed_seatings":1},"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":9,"repaired_rate":0.3},"intensive":{"admitted_plugins":25,"evaluated_cells":25,"first_pass_admitted":22,"first_pass_rate":0.88,"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"coverage_attestation":{"completed_directed_seatings":481,"evidence_sha256":"92cc408e51465c940fc6de770119146d19b9c20359d691863cdff02f59c8079f","focused_entrant_count":66,"full_double_round_robin_complete":true,"policy_id":"focused_full_double_round_robin_attestation_v1","residual_blocked_count":0,"residual_unblocked_count":0,"schema_version":1,"settled_model_fault_directed_seatings":1},"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.12}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-08-23T14:12:18Z","match_totals_all":{"draws":224,"losses":369,"wins":369},"match_totals_tracks":{"highest":{"draws":61,"losses":81,"wins":191},"medium":{"draws":80,"losses":133,"wins":95},"none":{"draws":83,"losses":155,"wins":83}},"model_slug":"stealth-ox-alpha","overall":{"max":52.06957808560736,"mean":36.27021137287471,"min":3.8514807674763087},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.77290160209612,"GB2-02":35.26149604339514,"GB2-03":38.512996050435966,"GB2-04":41.953702406627194,"GB2-05":51.24945473815348,"GB2-06":52.06957808560736,"GB2-07":48.24161735863407,"GB2-08":44.46972348405135},"per_game_all":{"GB2-01":38.89451571414592,"GB2-02":16.385992037013843,"GB2-03":37.19159584566137,"GB2-04":34.65761898138449,"GB2-05":44.92610336244913,"GB2-06":44.67836450046163,"GB2-07":42.2280724918537,"GB2-08":35.9122187364178},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":53,"wins":53},"GB2-02":{"draws":62,"losses":25,"wins":25},"GB2-03":{"draws":34,"losses":24,"wins":24},"GB2-04":{"draws":76,"losses":34,"wins":34},"GB2-05":{"draws":0,"losses":72,"wins":72},"GB2-06":{"draws":8,"losses":52,"wins":52},"GB2-07":{"draws":0,"losses":72,"wins":72},"GB2-08":{"draws":38,"losses":37,"wins":37}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":16,"wins":26},"GB2-02":{"draws":10,"losses":1,"wins":17},"GB2-03":{"draws":18,"losses":8,"wins":9},"GB2-04":{"draws":17,"losses":9,"wins":22},"GB2-05":{"draws":0,"losses":15,"wins":33},"GB2-06":{"draws":6,"losses":8,"wins":28},"GB2-07":{"draws":0,"losses":17,"wins":31},"GB2-08":{"draws":10,"losses":7,"wins":25}},"medium":{"GB2-01":{"draws":3,"losses":10,"wins":15},"GB2-02":{"draws":24,"losses":11,"wins":7},"GB2-03":{"draws":5,"losses":6,"wins":13},"GB2-04":{"draws":30,"losses":9,"wins":9},"GB2-05":{"draws":0,"losses":34,"wins":14},"GB2-06":{"draws":1,"losses":22,"wins":5},"GB2-07":{"draws":0,"losses":28,"wins":20},"GB2-08":{"draws":17,"losses":13,"wins":12}},"none":{"GB2-01":{"draws":3,"losses":27,"wins":12},"GB2-02":{"draws":28,"losses":13,"wins":1},"GB2-03":{"draws":11,"losses":10,"wins":2},"GB2-04":{"draws":29,"losses":16,"wins":3},"GB2-05":{"draws":0,"losses":23,"wins":25},"GB2-06":{"draws":1,"losses":22,"wins":19},"GB2-07":{"draws":0,"losses":27,"wins":21},"GB2-08":{"draws":11,"losses":17,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1503.3800177664307,"GB2-02":1510.5701719500605,"GB2-03":1498.626544943351,"GB2-04":1500.0,"GB2-05":1500.0,"GB2-06":1489.1928022127213,"GB2-07":1500.0,"GB2-08":1488.6761544554581},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1540.8930518724999,"GB2-02":1595.1315475505453,"GB2-03":1508.2407303398938,"GB2-04":1547.063493316194,"GB2-05":1571.444849455973,"GB2-06":1577.0114222032025,"GB2-07":1557.9397208469782,"GB2-08":1570.5181600374551},"medium":{"GB2-01":1530.420159897876,"GB2-02":1482.162820902962,"GB2-03":1537.4080832752197,"GB2-04":1503.2014764650874,"GB2-05":1426.7474591280127,"GB2-06":1402.7352199144916,"GB2-07":1466.9786554793234,"GB2-08":1497.424913229797},"none":{"GB2-01":1438.826841528916,"GB2-02":1454.4161473966744,"GB2-03":1450.2308212149396,"GB2-04":1449.7350302187187,"GB2-05":1501.807691416014,"GB2-06":1487.8317645204697,"GB2-07":1475.0816236736982,"GB2-08":1398.0853900991224}},"per_game_tracks":{"highest":{"GB2-01":42.77290160209612,"GB2-02":35.26149604339514,"GB2-03":38.512996050435966,"GB2-04":41.953702406627194,"GB2-05":51.24945473815348,"GB2-06":52.06957808560736,"GB2-07":48.24161735863407,"GB2-08":44.46972348405135},"medium":{"GB2-01":41.69013350806352,"GB2-02":10.044999300170076,"GB2-03":42.84271453304636,"GB2-04":35.153932317419596,"GB2-05":38.44275909587383,"GB2-06":37.40170202397549,"GB2-07":38.80079783582027,"GB2-08":36.82700014011026},"none":{"GB2-01":32.220512032278116,"GB2-02":3.8514807674763087,"GB2-03":30.219076953501776,"GB2-04":26.86522222010667,"GB2-05":45.08609625332008,"GB2-06":44.56381339180203,"GB2-07":39.64180228110675,"GB2-08":26.439932585091782}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.31643372112509,"medium":33.91521622287523,"none":30.578984174623823},"reasoning_agg":{"highest":{"max":52.06957808560736,"mean":44.31643372112509,"min":35.26149604339514},"medium":{"max":42.84271453304636,"mean":33.91521622287523,"min":10.044999300170076},"none":{"max":45.08609625332008,"mean":30.578984174623823,"min":3.8514807674763087}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":52.06957808560736,"expected_score":40.494506222349656,"reasoning_variance":13.737449546501264,"reliability_score":16.214253162425095,"uncertainty_avg":83.7857468375749,"uncertainty_penalty":4.224294849474944},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.06957808560736,"expected_score":37.69890392990169,"reliability_score":16.179010447538346,"uncertainty_avg":83.82098955246165,"uncertainty_penalty":-6.617529791223397},"medium":{"ceiling_score":42.84271453304636,"expected_score":37.648330148986034,"reliability_score":16.390466736858897,"uncertainty_avg":83.6095332631411,"uncertainty_penalty":3.7331139261108035},"none":{"ceiling_score":45.08609625332008,"expected_score":46.13628458816124,"reliability_score":16.073282302878084,"uncertainty_avg":83.92671769712192,"uncertainty_penalty":15.557300413537416}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:f8fa673b07fb084d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139173999999999}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.03158643900000001}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":37.220730361632086,"none":39.95580492735129},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":130744},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:51Z","match_totals_all":{"draws":346,"losses":369,"wins":309},"match_totals_tracks":{"highest":{"draws":134,"losses":244,"wins":174},"none":{"draws":212,"losses":125,"wins":135}},"model_slug":"tencent-hy3-preview","overall":{"max":72.88756496655336,"mean":36.068609227458595,"min":13.368124963630589},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":30,"overall_ranking_status":"partial","per_game":{"GB2-01":57.3619117116447,"GB2-02":13.456150792860978,"GB2-04":31.883837501980675,"GB2-05":59.334280478082064,"GB2-06":30.12382384874148,"GB2-07":27.27162069011934,"GB2-08":41.11348750799539},"per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":35,"wins":94},"GB2-02":{"draws":98,"losses":15,"wins":1},"GB2-03":{"draws":25,"losses":25,"wins":26},"GB2-04":{"draws":85,"losses":28,"wins":19},"GB2-05":{"draws":0,"losses":96,"wins":78},"GB2-06":{"draws":0,"losses":55,"wins":23},"GB2-07":{"draws":0,"losses":58,"wins":34},"GB2-08":{"draws":109,"losses":57,"wins":34}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":26,"wins":39},"GB2-02":{"draws":44,"losses":9,"wins":1},"GB2-04":{"draws":49,"losses":18,"wins":7},"GB2-05":{"draws":0,"losses":41,"wins":39},"GB2-06":{"draws":0,"losses":55,"wins":23},"GB2-07":{"draws":0,"losses":58,"wins":34},"GB2-08":{"draws":26,"losses":37,"wins":31}},"none":{"GB2-01":{"draws":14,"losses":9,"wins":55},"GB2-02":{"draws":54,"losses":6,"wins":0},"GB2-03":{"draws":25,"losses":25,"wins":26},"GB2-04":{"draws":36,"losses":10,"wins":12},"GB2-05":{"draws":0,"losses":55,"wins":39},"GB2-08":{"draws":83,"losses":20,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1623.1676828791458,"GB2-02":1448.1010532318462,"GB2-04":1431.281453340056,"GB2-05":1610.2220406835493,"GB2-06":1257.9871534436184,"GB2-07":1300.3603544346433,"GB2-08":1476.1794699081136},"none":{"GB2-01":1773.8960199591977,"GB2-02":1444.9854646078195,"GB2-03":1452.812696623928,"GB2-04":1503.3498876524732,"GB2-05":1334.1173082540881,"GB2-08":1424.9981872068206}},"per_game_tracks":{"highest":{"GB2-01":57.3619117116447,"GB2-02":13.456150792860978,"GB2-04":31.883837501980675,"GB2-05":59.334280478082064,"GB2-06":30.12382384874148,"GB2-07":27.27162069011934,"GB2-08":41.11348750799539},"none":{"GB2-01":72.88756496655336,"GB2-02":13.368124963630589,"GB2-03":40.12729304970078,"GB2-04":42.14362212889749,"GB2-05":35.19854110959529,"GB2-08":36.009683345730224}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.95415224018846,"none":37.18306621472872},"reasoning_agg":{"highest":{"max":59.334280478082064,"mean":34.95415224018846,"min":13.456150792860978},"none":{"max":72.88756496655336,"mean":37.18306621472872,"min":13.368124963630589}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.88756496655336,"reasoning_variance":2.228913974540255},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.334280478082064,"expected_score":21.106493189444624,"reliability_score":87.22613976236028,"uncertainty_avg":12.773860237639722,"uncertainty_penalty":-13.84765905074384},"none":{"ceiling_score":72.88756496655336,"expected_score":51.44793797082042,"reliability_score":86.75277986841317,"uncertainty_avg":13.24722013158683,"uncertainty_penalty":14.2648717560917}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:54dd73921471ddad","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.0165325}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.0165325}},"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":222264.07142857142,"min_ms":41984,"run_count":14},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":550842,"mean_ms":354649.85714285716,"min_ms":219950,"run_count":7},"none":{"attempt_count":8,"max_ms":161392,"mean_ms":89878.28571428571,"min_ms":41984,"run_count":7}},"codegen_output_tokens":{"attempt_count":23,"output_max":12552,"output_mean":5500.928571428572,"output_min":1283,"run_count":14},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":12552,"output_mean":8851.57142857143,"output_min":6019,"run_count":7},"none":{"attempt_count":8,"output_max":4235,"output_mean":2150.285714285714,"output_min":1283,"run_count":7}},"display_name":"Gemma 4 31B","economics":{"medium":43.751461488092524,"none":32.366653836465424},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":23,"total_output_tokens":77013},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.14285714285714285}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-08-05T03:57:18Z","match_totals_all":{"draws":234,"losses":406,"wins":310},"match_totals_tracks":{"medium":{"draws":66,"losses":171,"wins":155},"none":{"draws":168,"losses":235,"wins":155}},"model_slug":"google-gemma-4-31b-it","overall":{"max":59.53630433773744,"mean":34.591197146192016,"min":18.568992620174647},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":31,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":34,"wins":53},"GB2-04":{"draws":126,"losses":14,"wins":18},"GB2-05":{"draws":0,"losses":115,"wins":87},"GB2-06":{"draws":3,"losses":120,"wins":77},"GB2-07":{"draws":0,"losses":102,"wins":72},"GB2-08":{"draws":82,"losses":21,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":65,"losses":5,"wins":8},"GB2-05":{"draws":0,"losses":52,"wins":62},"GB2-06":{"draws":1,"losses":68,"wins":37},"GB2-07":{"draws":0,"losses":46,"wins":48}},"none":{"GB2-01":{"draws":23,"losses":34,"wins":53},"GB2-04":{"draws":61,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":63,"wins":25},"GB2-06":{"draws":2,"losses":52,"wins":40},"GB2-07":{"draws":0,"losses":56,"wins":24},"GB2-08":{"draws":82,"losses":21,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1468.117049186159,"GB2-05":1605.3603699693099,"GB2-06":1336.2633420492373,"GB2-07":1426.8604269782086},"none":{"GB2-01":1487.7710394884484,"GB2-04":1482.3450286460047,"GB2-05":1147.5879156708982,"GB2-06":1335.778953761991,"GB2-07":1224.0896973580377,"GB2-08":1419.8830391614035}},"per_game_tracks":{"medium":{"GB2-04":37.777956524978244,"GB2-05":59.53630433773744,"GB2-06":37.24500604167221,"GB2-07":40.44657904798219},"none":{"GB2-01":44.033324039853156,"GB2-04":40.070339654447714,"GB2-05":18.568992620174647,"GB2-06":37.00479516375429,"GB2-07":19.047634614739106,"GB2-08":35.474836925823645}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.039346973942585,"none":31.14304731844145},"reasoning_agg":{"medium":{"max":59.53630433773744,"mean":38.039346973942585,"min":37.24500604167221},"none":{"max":44.033324039853156,"mean":31.14304731844145,"min":18.568992620174647}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":59.53630433773744,"reasoning_variance":6.896299655501135},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.53630433773744,"expected_score":40.91860051025365,"reliability_score":93.12115562128555,"uncertainty_avg":6.878844378714444,"uncertainty_penalty":2.8792535363110616},"none":{"ceiling_score":44.033324039853156,"expected_score":37.575841163967766,"reliability_score":91.88255884073418,"uncertainty_avg":8.117441159265825,"uncertainty_penalty":6.432793845526316}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:a67ab29b6f7f0b5a","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":46.74957304825288,"none":27.939354001518367},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"total_output_tokens":343242},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":6,"evaluated_cells":9,"failed_game_aliases":["GB2-01","GB2-03","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"model_code_failure_rate":0.3333333333333333,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-08-05T03:48:47Z","match_totals_all":{"draws":336,"losses":423,"wins":312},"match_totals_tracks":{"medium":{"draws":176,"losses":188,"wins":202},"none":{"draws":160,"losses":235,"wins":110}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":72.53293912084276,"mean":34.37571804749471,"min":3.600933227553536},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":32,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":43,"losses":87,"wins":52},"GB2-02":{"draws":153,"losses":4,"wins":1},"GB2-04":{"draws":49,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":106,"wins":104},"GB2-06":{"draws":3,"losses":88,"wins":82},"GB2-07":{"draws":0,"losses":112,"wins":68},"GB2-08":{"draws":88,"losses":18,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":18,"losses":36,"wins":34},"GB2-02":{"draws":69,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":57,"wins":59},"GB2-06":{"draws":1,"losses":22,"wins":57},"GB2-07":{"draws":0,"losses":51,"wins":51},"GB2-08":{"draws":88,"losses":18,"wins":0}},"none":{"GB2-01":{"draws":25,"losses":51,"wins":18},"GB2-02":{"draws":84,"losses":0,"wins":0},"GB2-04":{"draws":49,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":49,"wins":45},"GB2-06":{"draws":2,"losses":66,"wins":25},"GB2-07":{"draws":0,"losses":61,"wins":17}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1508.8769477318842,"GB2-02":1481.2479095839017,"GB2-05":1624.9915664363414,"GB2-06":1761.3115017129503,"GB2-07":1450.504688670992,"GB2-08":1417.7461884339903},"none":{"GB2-01":1330.725824672585,"GB2-02":1470.566214509699,"GB2-04":1467.7918733909657,"GB2-05":1484.0462009965422,"GB2-06":1257.1713265502815,"GB2-07":1075.8218147652353}},"per_game_tracks":{"medium":{"GB2-01":45.75703593114919,"GB2-02":22.584554928424122,"GB2-05":61.302135745250496,"GB2-06":72.53293912084276,"GB2-07":43.06936748228342,"GB2-08":35.251405081567306},"none":{"GB2-01":27.47909111397539,"GB2-02":20.8256604365787,"GB2-04":36.89168262273526,"GB2-05":48.468260024253375,"GB2-06":30.370496584013946,"GB2-07":3.600933227553536}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":43.50537983965268,"none":25.246056255336736},"reasoning_agg":{"medium":{"max":72.53293912084276,"mean":43.50537983965268,"min":22.584554928424122},"none":{"max":48.468260024253375,"mean":25.246056255336736,"min":3.600933227553536}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.53293912084276,"reasoning_variance":18.259323584315947},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":72.53293912084276,"expected_score":46.961214007463724,"reliability_score":92.0635364687606,"uncertainty_avg":7.9364635312394,"uncertainty_penalty":3.455834167811041},"none":{"ceiling_score":48.468260024253375,"expected_score":30.88011870902113,"reliability_score":89.14166902378474,"uncertainty_avg":10.858330976215257,"uncertainty_penalty":5.634062453684393}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:1e1b77d01aa6fd1f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519748999999999},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":35.28334006893099,"highest":36.646037321732905,"medium":27.967008360684993,"none":41.23697452437507},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":132,"finish_reasons":["stop"],"indexed_attempts":132,"output_token_observations":132,"reasoning_token_observations":89,"total_output_tokens":604751,"total_reasoning_output_tokens":229572,"total_visible_output_tokens":177334,"visible_token_observations":89},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.0625,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375},"intensive":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.0625}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-08-23T12:51:52Z","match_totals_all":{"draws":1845,"losses":2652,"wins":1581},"match_totals_tracks":{"highest":{"draws":435,"losses":812,"wins":542},"medium":{"draws":680,"losses":995,"wins":377},"none":{"draws":730,"losses":845,"wins":662}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":73.02102977984342,"mean":34.35621790435424,"min":10.571254109747576},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":28.004907598248348,"GB2-02":27.25129104934696,"GB2-03":54.3795837338173,"GB2-04":36.70643364563969,"GB2-05":26.141806979414127,"GB2-06":46.980742920105875,"GB2-07":46.86769680909644,"GB2-08":26.835835838194487},"per_game_all":{"GB2-01":35.01137086350506,"GB2-02":23.22779141431253,"GB2-03":48.66544243555423,"GB2-04":40.56015656640402,"GB2-05":18.207224046202438,"GB2-06":44.076280685407646,"GB2-07":44.83041959713646,"GB2-08":27.6880349429255},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":384,"wins":283},"GB2-02":{"draws":408,"losses":30,"wins":13},"GB2-03":{"draws":220,"losses":246,"wins":219},"GB2-04":{"draws":500,"losses":130,"wins":100},"GB2-05":{"draws":0,"losses":748,"wins":192},"GB2-06":{"draws":20,"losses":515,"wins":357},"GB2-07":{"draws":0,"losses":361,"wins":384},"GB2-08":{"draws":534,"losses":238,"wins":33}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":24,"losses":78,"wins":34},"GB2-02":{"draws":79,"losses":8,"wins":11},"GB2-03":{"draws":57,"losses":92,"wins":101},"GB2-04":{"draws":163,"losses":59,"wins":34},"GB2-05":{"draws":0,"losses":218,"wins":78},"GB2-06":{"draws":12,"losses":147,"wins":129},"GB2-07":{"draws":0,"losses":154,"wins":149},"GB2-08":{"draws":100,"losses":56,"wins":6}},"medium":{"GB2-01":{"draws":65,"losses":149,"wins":138},"GB2-02":{"draws":103,"losses":2,"wins":0},"GB2-03":{"draws":116,"losses":105,"wins":50},"GB2-04":{"draws":183,"losses":27,"wins":18},"GB2-05":{"draws":0,"losses":253,"wins":67},"GB2-06":{"draws":4,"losses":256,"wins":52},"GB2-07":{"draws":0,"losses":113,"wins":39},"GB2-08":{"draws":209,"losses":90,"wins":13}},"none":{"GB2-01":{"draws":74,"losses":157,"wins":111},"GB2-02":{"draws":226,"losses":20,"wins":2},"GB2-03":{"draws":47,"losses":49,"wins":68},"GB2-04":{"draws":154,"losses":44,"wins":48},"GB2-05":{"draws":0,"losses":277,"wins":47},"GB2-06":{"draws":4,"losses":112,"wins":176},"GB2-07":{"draws":0,"losses":94,"wins":196},"GB2-08":{"draws":225,"losses":92,"wins":14}}},"per_game_raw_elo_all":{"GB2-01":1394.3007549549886,"GB2-02":1476.219380765767,"GB2-03":1501.4082022456998,"GB2-04":1477.2871997718637,"GB2-05":1132.9764332093412,"GB2-06":1411.4721849715272,"GB2-07":1460.6719403384093,"GB2-08":1338.1627788399965},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1328.9468682572074,"GB2-02":1496.1681603311224,"GB2-03":1543.8864018616787,"GB2-04":1451.4196953279754,"GB2-05":1223.5192759386232,"GB2-06":1446.4894914486981,"GB2-07":1480.0791092283798,"GB2-08":1329.9225797807596},"medium":{"GB2-01":1445.289152623251,"GB2-02":1474.5153667728528,"GB2-03":1432.6859481766683,"GB2-04":1470.048880995099,"GB2-05":1129.252871556389,"GB2-06":1157.4214480942765,"GB2-07":1169.155353986958,"GB2-08":1334.1974425120047},"none":{"GB2-01":1408.6662439845072,"GB2-02":1457.9746151933264,"GB2-03":1527.6522566987526,"GB2-04":1510.3930229925163,"GB2-05":1046.1571521330118,"GB2-06":1630.5056153716068,"GB2-07":1732.781357799889,"GB2-08":1350.3683142272248}},"per_game_tracks":{"highest":{"GB2-01":28.004907598248348,"GB2-02":27.25129104934696,"GB2-03":54.3795837338173,"GB2-04":36.70643364563969,"GB2-05":26.141806979414127,"GB2-06":46.980742920105875,"GB2-07":46.86769680909644,"GB2-08":26.835835838194487},"medium":{"GB2-01":40.402427775346794,"GB2-02":22.719387636610737,"GB2-03":38.88817423342006,"GB2-04":39.2343034850068,"GB2-05":17.90861104944561,"GB2-06":22.76063329257293,"GB2-07":14.602532202469558,"GB2-08":27.219997210607445},"none":{"GB2-01":36.62677721692003,"GB2-02":19.712695556979902,"GB2-03":52.72856933942535,"GB2-04":45.73973256856557,"GB2-05":10.571254109747576,"GB2-06":62.48746584354412,"GB2-07":73.02102977984342,"GB2-08":29.008271779974574}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.44288232495812,"medium":27.048801419001688,"none":40.576969969102905},"reasoning_agg":{"highest":{"max":54.3795837338173,"mean":35.44288232495812,"min":26.141806979414127},"medium":{"max":40.402427775346794,"mean":27.048801419001688,"min":14.602532202469558},"none":{"max":73.02102977984342,"mean":40.576969969102905,"min":10.571254109747576}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":73.02102977984342,"expected_score":27.797493368800886,"reasoning_variance":13.528168550101217,"reliability_score":99.25267848544756,"uncertainty_avg":0.7473215145524323,"uncertainty_penalty":-6.5587245355533526},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.3795837338173,"expected_score":16.983404137938674,"reliability_score":99.02288768688162,"uncertainty_avg":0.977112313118385,"uncertainty_penalty":-18.459478187019446},"medium":{"ceiling_score":40.402427775346794,"expected_score":16.894222263487386,"reliability_score":99.00115704993263,"uncertainty_avg":0.9988429500673673,"uncertainty_penalty":-10.154579155514302},"none":{"ceiling_score":73.02102977984342,"expected_score":49.514853704976595,"reliability_score":99.73399071952845,"uncertainty_avg":0.2660092804715447,"uncertainty_penalty":8.93788373587369}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:fb6f94455ec4d370","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0221782524,"mean":0.00999808046,"median":0.009941171,"min":0.00212373,"recorded_attempt_count":14,"run_count":8,"total":0.07998464368},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.050973330659999996},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00408087,"mean":0.0022664345375,"median":0.0017928150000000001,"min":0.0013289177,"recorded_attempt_count":11,"run_count":8,"total":0.0181314763}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.050973330659999996},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00408087,"mean":0.0022664345375,"median":0.0017928150000000001,"min":0.0013289177,"recorded_attempt_count":11,"run_count":8,"total":0.018131476299999998},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0221782524,"mean":0.00999808046,"median":0.009941171,"min":0.00212373,"recorded_attempt_count":14,"run_count":8,"total":0.07998464368000001}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":49},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0221782524,"mean":0.005150116054583333,"median":0.00311373,"min":0.0013289177,"recorded_attempt_count":49,"run_count":32,"total":0.14908945063999998},"codegen_latency_ms":{"attempt_count":25,"max_ms":1394682,"mean_ms":281124.875,"min_ms":22331,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1394682,"mean_ms":494109.375,"min_ms":61403,"run_count":8},"none":{"attempt_count":11,"max_ms":129944,"mean_ms":68140.375,"min_ms":22331,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":82048,"output_mean":17675.4375,"output_min":1698,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":82048,"output_mean":31903.25,"output_min":4091,"run_count":8},"none":{"attempt_count":11,"output_max":6315,"output_mean":3447.625,"output_min":1698,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":34.594127650102884,"highest":41.58875401302814,"medium":33.18602349106142,"none":30.23445187997459},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":282807},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":10,"first_pass_rate":0.625,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:23:15Z","match_totals_all":{"draws":689,"losses":791,"wins":494},"match_totals_tracks":{"highest":{"draws":135,"losses":186,"wins":153},"medium":{"draws":328,"losses":381,"wins":219},"none":{"draws":226,"losses":224,"wins":122}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":72.31048780319064,"mean":33.346988072989255,"min":16.951008971108347},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":34,"overall_ranking_status":"partial","per_game":{"GB2-01":32.14530790884301,"GB2-02":24.79810278001538,"GB2-05":55.0033758790599,"GB2-06":31.46308983512399,"GB2-07":72.31048780319064,"GB2-08":33.8121598719359},"per_game_all":{"GB2-02":20.510404604623528,"GB2-05":43.41865271710751,"GB2-06":27.312914586490976,"GB2-07":47.59842662449685,"GB2-08":34.13023971779555},"per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":108,"wins":55},"GB2-02":{"draws":215,"losses":25,"wins":6},"GB2-03":{"draws":51,"losses":38,"wins":27},"GB2-04":{"draws":90,"losses":29,"wins":7},"GB2-05":{"draws":0,"losses":184,"wins":154},"GB2-06":{"draws":3,"losses":208,"wins":91},"GB2-07":{"draws":0,"losses":149,"wins":145},"GB2-08":{"draws":277,"losses":50,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":43,"wins":25},"GB2-02":{"draws":47,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":39,"wins":47},"GB2-06":{"draws":1,"losses":50,"wins":21},"GB2-07":{"draws":0,"losses":25,"wins":55},"GB2-08":{"draws":69,"losses":22,"wins":1}},"medium":{"GB2-01":{"draws":35,"losses":65,"wins":30},"GB2-02":{"draws":100,"losses":15,"wins":1},"GB2-03":{"draws":15,"losses":16,"wins":11},"GB2-04":{"draws":49,"losses":9,"wins":4},"GB2-05":{"draws":0,"losses":89,"wins":61},"GB2-06":{"draws":1,"losses":95,"wins":52},"GB2-07":{"draws":0,"losses":80,"wins":56},"GB2-08":{"draws":128,"losses":12,"wins":4}},"none":{"GB2-02":{"draws":68,"losses":3,"wins":1},"GB2-03":{"draws":36,"losses":22,"wins":16},"GB2-04":{"draws":41,"losses":20,"wins":3},"GB2-05":{"draws":0,"losses":56,"wins":46},"GB2-06":{"draws":1,"losses":63,"wins":18},"GB2-07":{"draws":0,"losses":44,"wins":34},"GB2-08":{"draws":80,"losses":16,"wins":4}}},"per_game_raw_elo_all":{"GB2-02":1476.0978070218746,"GB2-05":1428.6816411288862,"GB2-06":1225.2225791734065,"GB2-07":1500.5958458626458,"GB2-08":1411.0528328358398},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1377.7043878093432,"GB2-02":1497.0520433424101,"GB2-05":1559.729054266692,"GB2-06":1275.7125698415605,"GB2-07":1737.270344317228,"GB2-08":1406.790186771671},"medium":{"GB2-01":1397.2125499308513,"GB2-02":1461.919888631724,"GB2-03":1504.2149280033655,"GB2-04":1470.707966398987,"GB2-05":1292.428283867453,"GB2-06":1260.2930330590852,"GB2-07":1407.295129846862,"GB2-08":1409.5458902114271},"none":{"GB2-02":1469.3214890914899,"GB2-03":1431.8471904592118,"GB2-04":1374.1892220782775,"GB2-05":1433.8875852525139,"GB2-06":1139.6621346195743,"GB2-07":1357.2220634238477,"GB2-08":1416.8224215244215}},"per_game_tracks":{"highest":{"GB2-01":32.14530790884301,"GB2-02":24.79810278001538,"GB2-05":55.0033758790599,"GB2-06":31.46308983512399,"GB2-07":72.31048780319064,"GB2-08":33.8121598719359},"medium":{"GB2-01":33.46949800381537,"GB2-02":16.951008971108347,"GB2-03":45.206404703543946,"GB2-04":37.34375399192475,"GB2-05":31.079789578479307,"GB2-06":30.21820378332707,"GB2-07":37.67741814723562,"GB2-08":33.54211074905695},"none":{"GB2-02":19.782102062746848,"GB2-03":37.08306137270303,"GB2-04":22.501934434108996,"GB2-05":44.17279269378332,"GB2-06":20.257450141021867,"GB2-07":32.80737392306428,"GB2-08":35.0364485323938}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.70269656852593,"medium":32.09646694130927,"none":29.24180070913258},"reasoning_agg":{"highest":{"max":72.31048780319064,"mean":38.70269656852593,"min":24.79810278001538},"medium":{"max":45.206404703543946,"mean":32.09646694130927,"min":16.951008971108347},"none":{"max":44.17279269378332,"mean":29.24180070913258,"min":19.782102062746848}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.31048780319064,"expected_score":27.685545757054076,"reasoning_variance":9.46089585939335,"reliability_score":86.93480455169848,"uncertainty_avg":13.065195448301527,"uncertainty_penalty":-5.661442315935179},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.31048780319064,"expected_score":28.48620296145455,"reliability_score":87.37842952261109,"uncertainty_avg":12.62157047738892,"uncertainty_penalty":-10.216493607071381},"medium":{"ceiling_score":45.206404703543946,"expected_score":26.326895697233468,"reliability_score":81.23088750857072,"uncertainty_avg":18.76911249142928,"uncertainty_penalty":-5.769571244075799},"none":{"ceiling_score":44.17279269378332,"expected_score":34.661766613789716,"reliability_score":88.26031196121535,"uncertainty_avg":11.739688038784653,"uncertainty_penalty":5.419965904657136}}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:aa9d42ace8f050f0","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917795999999999},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386000000001}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":30.092779704224654,"none":39.52658657172093},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.21428571428571427,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.2857142857142857},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.35714285714285715}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-08-23T00:33:40Z","match_totals_all":{"draws":1114,"losses":1117,"wins":687},"match_totals_tracks":{"medium":{"draws":691,"losses":709,"wins":309},"none":{"draws":423,"losses":408,"wins":378}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":57.87934682152756,"mean":33.18219132607179,"min":19.31198981966688},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":35,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":72,"losses":154,"wins":136},"GB2-02":{"draws":313,"losses":12,"wins":3},"GB2-03":{"draws":225,"losses":197,"wins":115},"GB2-04":{"draws":90,"losses":46,"wins":12},"GB2-05":{"draws":0,"losses":306,"wins":235},"GB2-06":{"draws":11,"losses":180,"wins":87},"GB2-07":{"draws":0,"losses":99,"wins":79},"GB2-08":{"draws":403,"losses":123,"wins":20}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":72,"wins":58},"GB2-02":{"draws":223,"losses":9,"wins":0},"GB2-03":{"draws":125,"losses":121,"wins":60},"GB2-04":{"draws":90,"losses":46,"wins":12},"GB2-05":{"draws":0,"losses":243,"wins":122},"GB2-06":{"draws":7,"losses":124,"wins":43},"GB2-08":{"draws":224,"losses":94,"wins":14}},"none":{"GB2-01":{"draws":50,"losses":82,"wins":78},"GB2-02":{"draws":90,"losses":3,"wins":3},"GB2-03":{"draws":100,"losses":76,"wins":55},"GB2-05":{"draws":0,"losses":63,"wins":113},"GB2-06":{"draws":4,"losses":56,"wins":44},"GB2-07":{"draws":0,"losses":99,"wins":79},"GB2-08":{"draws":179,"losses":29,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1437.1200705128342,"GB2-02":1466.6231620188373,"GB2-03":1405.4802666018688,"GB2-04":1383.2834532411562,"GB2-05":1315.0698482131118,"GB2-06":1169.8992765543176,"GB2-08":1355.6049159769764},"none":{"GB2-01":1512.667219495499,"GB2-02":1461.0127959450965,"GB2-03":1443.945798874046,"GB2-05":1591.7468690047804,"GB2-06":1233.8513345112337,"GB2-07":1543.060781937911,"GB2-08":1387.5631121202853}},"per_game_tracks":{"medium":{"GB2-01":39.37852779468735,"GB2-02":21.375448760554548,"GB2-03":35.33064329629842,"GB2-04":26.523140403424865,"GB2-05":34.528261127510206,"GB2-06":23.952752097603227,"GB2-08":29.56068444949395},"none":{"GB2-01":46.51241566794083,"GB2-02":19.31198981966688,"GB2-03":39.88354454110426,"GB2-05":57.87934682152756,"GB2-06":28.594696782513516,"GB2-07":52.39005509336917,"GB2-08":32.11405727592425}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":28.332080574852135,"none":38.03230207729145},"reasoning_agg":{"medium":{"max":39.37852779468735,"mean":28.332080574852135,"min":21.375448760554548},"none":{"max":57.87934682152756,"mean":38.03230207729145,"min":19.31198981966688}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":57.87934682152756,"reasoning_variance":9.700221502439312},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":39.37852779468735,"expected_score":16.36898868441458,"reliability_score":99.64642623541394,"uncertainty_avg":0.35357376458606055,"uncertainty_penalty":-11.963091890437553},"none":{"ceiling_score":57.87934682152756,"expected_score":43.4821821752156,"reliability_score":93.51413701502604,"uncertainty_avg":6.4858629849739655,"uncertainty_penalty":5.449880097924151}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:e5c2210ece87e3e8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761485},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.07206399999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761484999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373186},"codegen_latency_ms":{"attempt_count":43,"max_ms":599272,"mean_ms":125847.07142857143,"min_ms":18961,"run_count":28},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":599272,"mean_ms":283663.1,"min_ms":69866,"run_count":10},"medium":{"attempt_count":15,"max_ms":68712,"mean_ms":42566.11111111111,"min_ms":22862,"run_count":9},"none":{"attempt_count":14,"max_ms":63236,"mean_ms":33776.88888888889,"min_ms":18961,"run_count":9}},"codegen_output_tokens":{"attempt_count":43,"output_max":49133,"output_mean":11683.67857142857,"output_min":894,"run_count":28},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":49133,"output_mean":28182.1,"output_min":11882,"run_count":10},"medium":{"attempt_count":15,"output_max":4066,"output_mean":2679.6666666666665,"output_min":1736,"run_count":9},"none":{"attempt_count":14,"output_max":5147,"output_mean":2356.1111111111113,"output_min":894,"run_count":9}},"display_name":"Inkling Small","economics":{"all":34.365074620632456,"highest":37.264078008031774,"medium":32.80838268685741,"none":32.851444464888665},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":43,"finish_reasons":["stop"],"indexed_attempts":43,"output_token_observations":43,"provider_post_attempt_observations":43,"provider_post_attempts":43,"reasoning_token_observations":43,"reconciliation_get_attempt_observations":43,"reconciliation_get_attempts":203,"total_output_tokens":327143,"total_reasoning_output_tokens":261125,"total_visible_output_tokens":66018,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"thinkingmachines/inkling-small","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":4,"repaired_rate":0.4444444444444444},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":6,"first_pass_rate":0.6,"model_code_failure_rate":0.2,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.2}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-08-23T05:50:12Z","match_totals_all":{"draws":148,"losses":156,"wins":100},"match_totals_tracks":{"highest":{"draws":44,"losses":33,"wins":40},"medium":{"draws":54,"losses":62,"wins":30},"none":{"draws":50,"losses":61,"wins":30}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":55.386274611099374,"mean":32.998933573710495,"min":11.59827459432436},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":36,"overall_ranking_status":"partial","per_game":{"GB2-02":11.59827459432436,"GB2-03":46.57541663713608,"GB2-04":44.88860616405384,"GB2-05":45.65403638689062,"GB2-06":55.386274611099374,"GB2-07":21.997140822640443,"GB2-08":34.74879684007773},"per_game_all":{"GB2-02":13.620220128036204,"GB2-03":43.37952633564078,"GB2-04":38.245398504923465,"GB2-05":34.79779081502142,"GB2-06":42.78133330850096,"GB2-07":34.34235771942026,"GB2-08":33.38889553288411},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":22,"wins":11},"GB2-02":{"draws":53,"losses":1,"wins":0},"GB2-03":{"draws":16,"losses":14,"wins":21},"GB2-04":{"draws":35,"losses":6,"wins":11},"GB2-05":{"draws":0,"losses":37,"wins":14},"GB2-06":{"draws":0,"losses":31,"wins":25},"GB2-07":{"draws":0,"losses":37,"wins":18},"GB2-08":{"draws":38,"losses":8,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":15,"losses":1,"wins":0},"GB2-03":{"draws":4,"losses":5,"wins":9},"GB2-04":{"draws":9,"losses":1,"wins":7},"GB2-05":{"draws":0,"losses":8,"wins":9},"GB2-06":{"draws":0,"losses":2,"wins":14},"GB2-07":{"draws":0,"losses":15,"wins":1},"GB2-08":{"draws":16,"losses":1,"wins":0}},"medium":{"GB2-01":{"draws":3,"losses":15,"wins":2},"GB2-02":{"draws":20,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":5,"wins":6},"GB2-04":{"draws":13,"losses":5,"wins":2},"GB2-05":{"draws":0,"losses":12,"wins":4},"GB2-06":{"draws":0,"losses":14,"wins":5},"GB2-07":{"draws":0,"losses":8,"wins":11},"GB2-08":{"draws":12,"losses":3,"wins":0}},"none":{"GB2-01":{"draws":3,"losses":7,"wins":9},"GB2-02":{"draws":18,"losses":0,"wins":0},"GB2-03":{"draws":6,"losses":4,"wins":6},"GB2-04":{"draws":13,"losses":0,"wins":2},"GB2-05":{"draws":0,"losses":17,"wins":1},"GB2-06":{"draws":0,"losses":15,"wins":6},"GB2-07":{"draws":0,"losses":14,"wins":6},"GB2-08":{"draws":10,"losses":4,"wins":0}}},"per_game_raw_elo_all":{"GB2-02":1486.9226537392253,"GB2-03":1524.625333027939,"GB2-04":1519.9847945918198,"GB2-05":1382.9040834718035,"GB2-06":1453.9527770417972,"GB2-07":1418.2559578957323,"GB2-08":1460.4509362926372},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1482.8561157275458,"GB2-03":1544.6816547576702,"GB2-04":1563.2617872617693,"GB2-05":1505.4912588279985,"GB2-06":1610.153408293399,"GB2-07":1305.0776107344343,"GB2-08":1468.5508035025312},"medium":{"GB2-01":1350.83081881614,"GB2-02":1484.9154364994188,"GB2-03":1510.3734345802525,"GB2-04":1470.799314323205,"GB2-05":1365.410320453481,"GB2-06":1380.0794653970897,"GB2-07":1543.2649898641687,"GB2-08":1460.0959389047707},"none":{"GB2-01":1497.182936178097,"GB2-02":1492.996408990712,"GB2-03":1518.820909745894,"GB2-04":1525.8932821904841,"GB2-05":1277.8106711339308,"GB2-06":1371.625457434903,"GB2-07":1406.4252730885935,"GB2-08":1452.7060664706091}},"per_game_tracks":{"highest":{"GB2-02":11.59827459432436,"GB2-03":46.57541663713608,"GB2-04":44.88860616405384,"GB2-05":45.65403638689062,"GB2-06":55.386274611099374,"GB2-07":21.997140822640443,"GB2-08":34.74879684007773},"medium":{"GB2-01":24.776223890208286,"GB2-02":14.229198182783765,"GB2-03":41.37834288379551,"GB2-04":31.638698369369212,"GB2-05":33.01400834375168,"GB2-06":36.659461887948076,"GB2-07":47.504378523447755,"GB2-08":33.26674941355504},"none":{"GB2-01":39.68437234670113,"GB2-02":15.033187607000485,"GB2-03":42.18481948599077,"GB2-04":38.20889098134736,"GB2-05":25.725327714421983,"GB2-06":36.298263426455435,"GB2-07":33.525553812172575,"GB2-08":32.15114034501958}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.24218909333583,"medium":31.856399674988566,"none":31.898211952807085},"reasoning_agg":{"highest":{"max":55.386274611099374,"mean":35.24218909333583,"min":11.59827459432436},"medium":{"max":47.504378523447755,"mean":31.856399674988566,"min":14.229198182783765},"none":{"max":42.18481948599077,"mean":31.898211952807085,"min":15.033187607000485}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":55.386274611099374,"expected_score":36.672126267878625,"reasoning_variance":3.385789418347265,"reliability_score":26.678541888425713,"uncertainty_avg":73.32145811157429,"uncertainty_penalty":3.6731926941681294},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.386274611099374,"expected_score":27.0903656773907,"reliability_score":24.883614988135136,"uncertainty_avg":75.11638501186486,"uncertainty_penalty":-8.151823415945131},"medium":{"ceiling_score":47.504378523447755,"expected_score":32.6761767390185,"reliability_score":29.3684280225135,"uncertainty_avg":70.6315719774865,"uncertainty_penalty":0.8197770640299353},"none":{"ceiling_score":42.18481948599077,"expected_score":48.92052220618526,"reliability_score":27.213038320862537,"uncertainty_avg":72.78696167913746,"uncertainty_penalty":17.022310253378176}}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:bb38eb0c97be722d","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":28.93797267122631,"none":40.388823983582036},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"total_output_tokens":596080},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.875},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-08-05T04:33:21Z","match_totals_all":{"draws":330,"losses":505,"wins":347},"match_totals_tracks":{"medium":{"draws":211,"losses":307,"wins":140},"none":{"draws":119,"losses":198,"wins":207}},"model_slug":"minimax-minimax-m3","overall":{"max":52.04366523994301,"mean":32.78696154293632,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":37,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":91,"wins":85},"GB2-02":{"draws":120,"losses":17,"wins":1},"GB2-03":{"draws":32,"losses":20,"wins":28},"GB2-04":{"draws":64,"losses":5,"wins":7},"GB2-05":{"draws":0,"losses":146,"wins":54},"GB2-06":{"draws":0,"losses":69,"wins":39},"GB2-07":{"draws":0,"losses":98,"wins":90},"GB2-08":{"draws":86,"losses":59,"wins":43}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":59,"wins":26},"GB2-02":{"draws":59,"losses":14,"wins":1},"GB2-04":{"draws":64,"losses":5,"wins":7},"GB2-05":{"draws":0,"losses":94,"wins":2},"GB2-06":{"draws":0,"losses":69,"wins":39},"GB2-07":{"draws":0,"losses":50,"wins":58},"GB2-08":{"draws":81,"losses":16,"wins":7}},"none":{"GB2-01":{"draws":21,"losses":32,"wins":59},"GB2-02":{"draws":61,"losses":3,"wins":0},"GB2-03":{"draws":32,"losses":20,"wins":28},"GB2-05":{"draws":0,"losses":52,"wins":52},"GB2-07":{"draws":0,"losses":48,"wins":32},"GB2-08":{"draws":5,"losses":43,"wins":36}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1318.6106318223515,"GB2-02":1422.731839146371,"GB2-04":1504.092051220334,"GB2-05":935.9987215696694,"GB2-06":1375.1489778493396,"GB2-07":1495.3408603140847,"GB2-08":1417.7357176254268},"none":{"GB2-01":1564.9122301422362,"GB2-02":1457.2399661529485,"GB2-03":1501.233407603528,"GB2-05":1470.0736718738399,"GB2-07":1380.3193424919139,"GB2-08":1506.4645617409897}},"per_game_tracks":{"medium":{"GB2-01":26.18114898717137,"GB2-02":9.522795772569406,"GB2-04":43.265005107407845,"GB2-05":0.0,"GB2-06":40.547794543772895,"GB2-07":47.83708028920805,"GB2-08":35.21198399845459},"none":{"GB2-01":52.04366523994301,"GB2-02":16.460871449147128,"GB2-03":47.12212623530856,"GB2-05":47.40888752062887,"GB2-07":35.262658898597685,"GB2-08":44.03473455786694}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.987887233331772,"none":37.58603585254086},"reasoning_agg":{"medium":{"max":47.83708028920805,"mean":27.987887233331772,"min":0.0},"none":{"max":52.04366523994301,"mean":37.58603585254086,"min":16.460871449147128}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":52.04366523994301,"reasoning_variance":9.598148619209088},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.83708028920805,"expected_score":22.452805043825084,"reliability_score":92.04887995549635,"uncertainty_avg":7.951120044503652,"uncertainty_penalty":-5.535082189506689},"none":{"ceiling_score":52.04366523994301,"expected_score":47.57579055787934,"reliability_score":89.88464334550235,"uncertainty_avg":10.115356654497653,"uncertainty_penalty":9.989754705338477}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:ba2faefd47e3050c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.486187507},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.0016912200000000002,"recorded_attempt_count":37,"run_count":24,"total":0.0689052158}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.27207317540000003},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.0306854728},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":16,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.0016912200000000002,"recorded_attempt_count":108,"run_count":56,"total":0.7524538071999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":34.52096762318904,"highest":34.8179320327108,"medium":35.76399551847051,"none":38.3767355961338},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["length","stop"],"indexed_attempts":32,"output_token_observations":32,"total_output_tokens":734523},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":12,"failed_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.08333333333333333,"infra_excluded_game_aliases":["GB2-03","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.3333333333333333,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.5833333333333334},"baseline":{"admitted_plugins":11,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.3125,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05","GB2-07"],"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:45Z","match_totals_all":{"draws":1059,"losses":1095,"wins":832},"match_totals_tracks":{"highest":{"draws":203,"losses":74,"wins":45},"medium":{"draws":486,"losses":509,"wins":343},"none":{"draws":370,"losses":512,"wins":444}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":58.591838652401584,"mean":32.73983907587124,"min":17.329198413600206},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":38,"overall_ranking_status":"partial","per_game":{"GB2-01":17.329198413600206,"GB2-02":24.338864125825364,"GB2-04":40.772376702118756,"GB2-06":58.591838652401584,"GB2-08":33.05738226960813},"per_game_all":{"GB2-01":31.667089535455716,"GB2-02":22.263441258569415,"GB2-04":40.205791974454584,"GB2-06":47.56998277767943,"GB2-08":30.898532569786056},"per_game_match_totals_all":{"GB2-01":{"draws":119,"losses":238,"wins":181},"GB2-02":{"draws":299,"losses":29,"wins":8},"GB2-03":{"draws":34,"losses":22,"wins":18},"GB2-04":{"draws":326,"losses":65,"wins":41},"GB2-05":{"draws":0,"losses":236,"wins":214},"GB2-06":{"draws":12,"losses":215,"wins":189},"GB2-07":{"draws":0,"losses":177,"wins":155},"GB2-08":{"draws":269,"losses":113,"wins":26}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":41,"losses":27,"wins":2},"GB2-02":{"draws":49,"losses":9,"wins":2},"GB2-04":{"draws":43,"losses":9,"wins":6},"GB2-06":{"draws":5,"losses":26,"wins":33},"GB2-08":{"draws":65,"losses":3,"wins":2}},"medium":{"GB2-01":{"draws":18,"losses":97,"wins":75},"GB2-02":{"draws":195,"losses":19,"wins":6},"GB2-04":{"draws":185,"losses":49,"wins":16},"GB2-05":{"draws":0,"losses":122,"wins":98},"GB2-06":{"draws":4,"losses":69,"wins":39},"GB2-07":{"draws":0,"losses":87,"wins":87},"GB2-08":{"draws":84,"losses":66,"wins":22}},"none":{"GB2-01":{"draws":60,"losses":114,"wins":104},"GB2-02":{"draws":55,"losses":1,"wins":0},"GB2-03":{"draws":34,"losses":22,"wins":18},"GB2-04":{"draws":98,"losses":7,"wins":19},"GB2-05":{"draws":0,"losses":114,"wins":116},"GB2-06":{"draws":3,"losses":120,"wins":117},"GB2-07":{"draws":0,"losses":90,"wins":68},"GB2-08":{"draws":120,"losses":44,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1373.2326092742453,"GB2-02":1483.7622486525327,"GB2-04":1487.421235265302,"GB2-06":1463.9639542022685,"GB2-08":1382.131620802851},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1238.9848297340284,"GB2-02":1494.1338632198867,"GB2-04":1494.504648883028,"GB2-06":1600.8399247445086,"GB2-08":1405.564866061363},"medium":{"GB2-01":1366.4931344086308,"GB2-02":1481.799645643289,"GB2-04":1466.5662869913588,"GB2-05":1433.0571045642391,"GB2-06":1359.647741311623,"GB2-07":1458.2767735661741,"GB2-08":1387.024127139457},"none":{"GB2-01":1514.2198636800767,"GB2-02":1475.3532370944224,"GB2-03":1481.899175382564,"GB2-04":1501.192769921518,"GB2-05":1514.8763793004314,"GB2-06":1431.4041965506742,"GB2-07":1338.8129674710015,"GB2-08":1353.8058692077334}},"per_game_tracks":{"highest":{"GB2-01":17.329198413600206,"GB2-02":24.338864125825364,"GB2-04":40.772376702118756,"GB2-06":58.591838652401584,"GB2-08":33.05738226960813},"medium":{"GB2-01":31.194844980833093,"GB2-02":22.699064906311374,"GB2-04":37.80204674868615,"GB2-05":44.220775294483815,"GB2-06":39.30072691137755,"GB2-07":43.53573291311461,"GB2-08":31.594776874486953},"none":{"GB2-01":46.477225211933856,"GB2-02":19.75239474357151,"GB2-03":44.14726180448418,"GB2-04":42.04295247255884,"GB2-05":50.80751645753057,"GB2-06":44.817382769259154,"GB2-07":30.92571274446921,"GB2-08":28.04343856526308}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.95800581695214,"medium":32.31641800758346,"none":34.945093403078104},"reasoning_agg":{"highest":{"max":58.591838652401584,"mean":30.95800581695214,"min":17.329198413600206},"medium":{"max":44.220775294483815,"mean":32.31641800758346,"min":22.699064906311374},"none":{"max":50.80751645753057,"mean":34.945093403078104,"min":19.75239474357151}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":58.591838652401584,"expected_score":29.154638450779295,"reasoning_variance":3.9870875861259627,"reliability_score":86.19880020908049,"uncertainty_avg":13.801199790919506,"uncertainty_penalty":-3.585200625091943},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.591838652401584,"expected_score":20.032057385665148,"reliability_score":81.7883142858301,"uncertainty_avg":18.211685714169896,"uncertainty_penalty":-10.925948431286994},"medium":{"ceiling_score":44.220775294483815,"expected_score":31.245319747320444,"reliability_score":91.66600300901005,"uncertainty_avg":8.333996990989943,"uncertainty_penalty":-1.071098260263014},"none":{"ceiling_score":50.80751645753057,"expected_score":47.92141875733714,"reliability_score":86.22175521808252,"uncertainty_avg":13.778244781917476,"uncertainty_penalty":12.976325354259039}}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:75c0c8b0e77d80fa","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.214047204}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.60040646},"codegen_latency_ms":{"attempt_count":87,"max_ms":1635062,"mean_ms":598630.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":49,"max_ms":1635062,"mean_ms":1021590.9375,"min_ms":525940,"run_count":16},"none":{"attempt_count":38,"max_ms":457140,"mean_ms":175670.5625,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":110598,"output_mean":38325.9375,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":59,"output_max":110598,"output_mean":68392.8125,"output_min":16796,"run_count":16},"none":{"attempt_count":38,"output_max":22812,"output_mean":8259.0625,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":33.37422795445095,"none":35.0433047714104},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.1875},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-08-22T06:50:55Z","match_totals_all":{"draws":896,"losses":1363,"wins":836},"match_totals_tracks":{"medium":{"draws":425,"losses":873,"wins":489},"none":{"draws":471,"losses":490,"wins":347}},"model_slug":"meituan-longcat-2-0","overall":{"max":55.24795980739564,"mean":32.47549452806633,"min":17.33176752068492},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":39,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":78,"losses":88,"wins":64},"GB2-02":{"draws":186,"losses":8,"wins":2},"GB2-03":{"draws":125,"losses":80,"wins":73},"GB2-04":{"draws":191,"losses":107,"wins":36},"GB2-05":{"draws":0,"losses":309,"wins":195},"GB2-06":{"draws":40,"losses":320,"wins":180},"GB2-07":{"draws":0,"losses":280,"wins":220},"GB2-08":{"draws":276,"losses":171,"wins":66}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":101,"losses":3,"wins":2},"GB2-03":{"draws":59,"losses":37,"wins":40},"GB2-04":{"draws":147,"losses":88,"wins":19},"GB2-05":{"draws":0,"losses":185,"wins":149},"GB2-06":{"draws":23,"losses":223,"wins":96},"GB2-07":{"draws":0,"losses":187,"wins":123},"GB2-08":{"draws":95,"losses":150,"wins":60}},"none":{"GB2-01":{"draws":78,"losses":88,"wins":64},"GB2-02":{"draws":85,"losses":5,"wins":0},"GB2-03":{"draws":66,"losses":43,"wins":33},"GB2-04":{"draws":44,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":124,"wins":46},"GB2-06":{"draws":17,"losses":97,"wins":84},"GB2-07":{"draws":0,"losses":93,"wins":97},"GB2-08":{"draws":181,"losses":21,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1480.559288564265,"GB2-03":1476.5878420683082,"GB2-04":1340.7970382156996,"GB2-05":1428.4869964909099,"GB2-06":1280.086612399988,"GB2-07":1377.2444957042999,"GB2-08":1370.878037318353},"none":{"GB2-01":1386.391363495254,"GB2-02":1460.934365357052,"GB2-03":1402.9868138511533,"GB2-04":1580.248490406413,"GB2-05":1134.3619315082324,"GB2-06":1476.509690149318,"GB2-07":1432.7430806795305,"GB2-08":1389.5031523076473}},"per_game_tracks":{"medium":{"GB2-02":24.109111227556788,"GB2-03":45.093217679579666,"GB2-04":19.52045526776426,"GB2-05":44.451721920222965,"GB2-06":33.20187949344528,"GB2-07":36.23200509894748,"GB2-08":31.011204993640277},"none":{"GB2-01":33.634762539218215,"GB2-02":19.00038445855571,"GB2-03":32.87102615666334,"GB2-04":55.24795980739564,"GB2-05":17.33176752068492,"GB2-06":48.921378822609434,"GB2-07":41.07920799575945,"GB2-08":32.25995087039648}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.058218703193194,"none":33.892770352939465},"reasoning_agg":{"medium":{"max":45.093217679579666,"mean":31.058218703193194,"min":19.52045526776426},"none":{"max":55.24795980739564,"mean":33.892770352939465,"min":17.33176752068492}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":55.24795980739564,"reasoning_variance":2.8345516497462704},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.093217679579666,"expected_score":24.038515162926014,"reliability_score":99.16795248166652,"uncertainty_avg":0.8320475183334842,"uncertainty_penalty":-7.01970354026718},"none":{"ceiling_score":55.24795980739564,"expected_score":42.777425940381356,"reliability_score":91.57649722336133,"uncertainty_avg":8.423502776638665,"uncertainty_penalty":8.884655587441891}}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:14c1d11c89476159","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.2116408500000002},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":41.61414741815097,"highest":36.09170623264679,"medium":34.48811830245897,"none":36.858071933974465},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":56,"finish_reasons":["error","length","stop"],"indexed_attempts":56,"output_token_observations":56,"total_output_tokens":194565},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-04","GB2-05"],"model_code_failure_rate":0.4444444444444444,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.5555555555555556},"baseline":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222},"intensive":{"admitted_plugins":9,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-06","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.125,"model_code_failure_rate":0.4375,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-08-05T04:29:54Z","match_totals_all":{"draws":614,"losses":592,"wins":383},"match_totals_tracks":{"highest":{"draws":303,"losses":259,"wins":153},"medium":{"draws":162,"losses":150,"wins":112},"none":{"draws":149,"losses":183,"wins":118}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":61.89486875016836,"mean":31.88162845501124,"min":10.490412921476183},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":40,"overall_ranking_status":"partial","per_game":{"GB2-01":37.80076732863321,"GB2-02":19.686387180079826,"GB2-04":35.776619836599615,"GB2-05":46.15142583047198,"GB2-06":43.29134777487506,"GB2-08":33.843689445221074},"per_game_all":{"GB2-01":44.800337231929404,"GB2-06":45.15645401938601,"GB2-08":34.885651003137504},"per_game_match_totals_all":{"GB2-01":{"draws":51,"losses":102,"wins":81},"GB2-02":{"draws":172,"losses":15,"wins":3},"GB2-03":{"draws":29,"losses":8,"wins":3},"GB2-04":{"draws":95,"losses":22,"wins":11},"GB2-05":{"draws":0,"losses":130,"wins":134},"GB2-06":{"draws":14,"losses":127,"wins":102},"GB2-07":{"draws":0,"losses":122,"wins":28},"GB2-08":{"draws":253,"losses":66,"wins":21}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":40,"wins":22},"GB2-02":{"draws":101,"losses":11,"wins":2},"GB2-04":{"draws":56,"losses":16,"wins":6},"GB2-05":{"draws":0,"losses":101,"wins":87},"GB2-06":{"draws":6,"losses":50,"wins":25},"GB2-08":{"draws":120,"losses":41,"wins":11}},"medium":{"GB2-01":{"draws":18,"losses":32,"wins":34},"GB2-02":{"draws":71,"losses":4,"wins":1},"GB2-06":{"draws":8,"losses":31,"wins":49},"GB2-07":{"draws":0,"losses":61,"wins":19},"GB2-08":{"draws":65,"losses":22,"wins":9}},"none":{"GB2-01":{"draws":13,"losses":30,"wins":25},"GB2-03":{"draws":29,"losses":8,"wins":3},"GB2-04":{"draws":39,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":29,"wins":47},"GB2-06":{"draws":0,"losses":46,"wins":28},"GB2-07":{"draws":0,"losses":61,"wins":9},"GB2-08":{"draws":68,"losses":3,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1502.3722378039477,"GB2-06":1435.8471772070081,"GB2-08":1419.0425949246867},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1433.4270688693366,"GB2-02":1474.6046613504113,"GB2-04":1455.207397477533,"GB2-05":1457.9789820510734,"GB2-06":1413.606033323522,"GB2-08":1408.5749166804935},"medium":{"GB2-01":1509.0881129608072,"GB2-02":1457.4123886391003,"GB2-06":1632.8708605783158,"GB2-07":1160.2853336204507,"GB2-08":1417.7124167603577},"none":{"GB2-01":1564.6015315816996,"GB2-03":1414.0125908179525,"GB2-04":1484.3591546604298,"GB2-05":1615.3072002247638,"GB2-06":1261.0646377191872,"GB2-07":1144.6688037728486,"GB2-08":1430.840451333209}},"per_game_tracks":{"highest":{"GB2-01":37.80076732863321,"GB2-02":19.686387180079826,"GB2-04":35.776619836599615,"GB2-05":46.15142583047198,"GB2-06":43.29134777487506,"GB2-08":33.843689445221074},"medium":{"GB2-01":45.6769093213218,"GB2-02":17.398846802778316,"GB2-06":61.89486875016836,"GB2-07":12.425400361217248,"GB2-08":35.04456627680913},"none":{"GB2-01":50.92333504583319,"GB2-03":32.268010627958816,"GB2-04":38.58942946961961,"GB2-05":59.683472652436585,"GB2-06":30.283145533114592,"GB2-07":10.490412921476183,"GB2-08":35.7686972873823}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.256334463397277,"medium":29.77497279227156,"none":34.61357810936488},"reasoning_agg":{"highest":{"max":46.15142583047198,"mean":31.256334463397277,"min":19.686387180079826},"medium":{"max":61.89486875016836,"mean":29.77497279227156,"min":12.425400361217248},"none":{"max":59.683472652436585,"mean":34.61357810936488,"min":10.490412921476183}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":61.89486875016836,"expected_score":34.55557484813354,"reasoning_variance":4.838605317093322,"reliability_score":88.38913256112419,"uncertainty_avg":11.610867438875813,"uncertainty_penalty":2.6739463931223},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":46.15142583047198,"expected_score":20.20006265520963,"reliability_score":87.55825996308462,"uncertainty_avg":12.441740036915384,"uncertainty_penalty":-11.056271808187645},"medium":{"ceiling_score":61.89486875016836,"expected_score":30.220411517007285,"reliability_score":89.64286790059249,"uncertainty_avg":10.357132099407504,"uncertainty_penalty":0.44543872473572677},"none":{"ceiling_score":59.683472652436585,"expected_score":47.10200470516535,"reliability_score":80.76874523641034,"uncertainty_avg":19.231254763589657,"uncertainty_penalty":12.488426595800469}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:0151b4f3ef2d8a82","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.4860581},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.3147617000000001},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.31476170000000003},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718000000002},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.11219570000000001,"mean":0.0416694575,"median":0.033877925,"min":0.00984735,"recorded_attempt_count":59,"run_count":24,"total":1.0000669800000002},"codegen_latency_ms":{"attempt_count":59,"max_ms":511905,"mean_ms":204675.625,"min_ms":73907,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":20,"max_ms":511905,"mean_ms":284845.75,"min_ms":132388,"run_count":8},"medium":{"attempt_count":19,"max_ms":302393,"mean_ms":201389.625,"min_ms":134501,"run_count":8},"none":{"attempt_count":20,"max_ms":209946,"mean_ms":127791.5,"min_ms":73907,"run_count":8}},"codegen_output_tokens":{"attempt_count":59,"output_max":93362,"output_mean":33067.75,"output_min":6729,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":93362,"output_mean":49316.75,"output_min":16213,"run_count":8},"medium":{"attempt_count":19,"output_max":59186,"output_mean":30987.25,"output_min":18109,"run_count":8},"none":{"attempt_count":20,"output_max":28972,"output_mean":18899.25,"output_min":6729,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":43.44559150873958,"highest":32.74111651500159,"medium":38.41283538965717,"none":36.916379646070055},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":59,"finish_reasons":["stop"],"indexed_attempts":59,"output_token_observations":59,"reasoning_token_observations":20,"total_output_tokens":793626,"total_reasoning_output_tokens":89090,"total_visible_output_tokens":62104,"visible_token_observations":20},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-08-19T15:24:00Z","match_totals_all":{"draws":318,"losses":682,"wins":425},"match_totals_tracks":{"highest":{"draws":71,"losses":222,"wins":134},"medium":{"draws":137,"losses":139,"wins":92},"none":{"draws":110,"losses":321,"wins":199}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":52.921447482930446,"mean":30.81849785585852,"min":9.651433101795904},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":41,"overall_ranking_status":"partial","per_game":{"GB2-01":9.651433101795904,"GB2-05":42.840832148787285,"GB2-06":46.55383945263552,"GB2-07":32.63495353216882,"GB2-08":32.024524339620434},"per_game_all":{"GB2-05":42.74400443681355,"GB2-06":44.14717858066562},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":54,"wins":12},"GB2-02":{"draws":67,"losses":6,"wins":1},"GB2-04":{"draws":69,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":200,"wins":150},"GB2-06":{"draws":14,"losses":184,"wins":152},"GB2-07":{"draws":0,"losses":161,"wins":100},"GB2-08":{"draws":162,"losses":68,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":54,"wins":12},"GB2-05":{"draws":0,"losses":45,"wins":51},"GB2-06":{"draws":2,"losses":50,"wins":38},"GB2-07":{"draws":0,"losses":56,"wins":33},"GB2-08":{"draws":63,"losses":17,"wins":0}},"medium":{"GB2-02":{"draws":67,"losses":6,"wins":1},"GB2-04":{"draws":69,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":56,"wins":50},"GB2-06":{"draws":1,"losses":68,"wins":31}},"none":{"GB2-05":{"draws":0,"losses":99,"wins":49},"GB2-06":{"draws":11,"losses":66,"wins":83},"GB2-07":{"draws":0,"losses":105,"wins":67},"GB2-08":{"draws":99,"losses":51,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1415.682006171869,"GB2-06":1417.35439930284},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1164.068130786268,"GB2-05":1420.039006789118,"GB2-06":1450.1280740563188,"GB2-07":1352.721001533367,"GB2-08":1392.660028685881},"medium":{"GB2-02":1483.1945310202682,"GB2-04":1519.768886248649,"GB2-05":1515.671430011153,"GB2-06":1286.5573647608894},"none":{"GB2-05":1311.3355817153363,"GB2-06":1515.3777590913119,"GB2-07":1392.9568971055057,"GB2-08":1292.5376746549155}},"per_game_tracks":{"highest":{"GB2-01":9.651433101795904,"GB2-05":42.840832148787285,"GB2-06":46.55383945263552,"GB2-07":32.63495353216882,"GB2-08":32.024524339620434},"medium":{"GB2-02":23.01907317579323,"GB2-04":46.188981149238096,"GB2-05":51.477038427166434,"GB2-06":32.9662488064309},"none":{"GB2-05":33.914142734486916,"GB2-06":52.921447482930446,"GB2-07":38.0307879145991,"GB2-08":22.799140452263753}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.11142668015633,"medium":32.301215578893725,"none":31.0428513085255},"reasoning_agg":{"highest":{"max":46.55383945263552,"mean":29.11142668015633,"min":9.651433101795904},"medium":{"max":51.477038427166434,"mean":32.301215578893725,"min":23.01907317579323},"none":{"max":52.921447482930446,"mean":31.0428513085255,"min":22.799140452263753}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":52.921447482930446,"expected_score":34.99747868147159,"reasoning_variance":3.189788898737394,"reliability_score":95.62162765740675,"uncertainty_avg":4.378372342593251,"uncertainty_penalty":4.1789808256130705},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":46.55383945263552,"expected_score":16.641226216369635,"reliability_score":89.75753861682585,"uncertainty_avg":10.24246138317414,"uncertainty_penalty":-12.470200463786696},"medium":{"ceiling_score":51.477038427166434,"expected_score":34.49986021014045,"reliability_score":91.5440987794842,"uncertainty_avg":8.455901220515804,"uncertainty_penalty":2.1986446312467223},"none":{"ceiling_score":52.921447482930446,"expected_score":36.15763111480197,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.1147798062764736}}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:a1783d1581f6f6d9","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.81977125},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.40579925},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":31.221768608847004,"none":38.57817288064592},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["length","stop"],"indexed_attempts":53,"output_token_observations":53,"total_output_tokens":2639964},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":7,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"model_code_failure_rate":0.5625,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":7,"repaired_rate":0.4375}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:20Z","match_totals_all":{"draws":312,"losses":431,"wins":257},"match_totals_tracks":{"medium":{"draws":51,"losses":257,"wins":116},"none":{"draws":261,"losses":174,"wins":141}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":63.528190114310334,"mean":29.567845015724004,"min":13.67320578769338},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-02":{"draws":64,"losses":10,"wins":2},"GB2-03":{"draws":62,"losses":32,"wins":20},"GB2-04":{"draws":74,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":112,"wins":78},"GB2-06":{"draws":12,"losses":129,"wins":39},"GB2-07":{"draws":0,"losses":70,"wins":106},"GB2-08":{"draws":100,"losses":71,"wins":7}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":28,"losses":19,"wins":11},"GB2-05":{"draws":0,"losses":64,"wins":30},"GB2-06":{"draws":10,"losses":68,"wins":18},"GB2-07":{"draws":0,"losses":46,"wins":50},"GB2-08":{"draws":13,"losses":60,"wins":7}},"none":{"GB2-02":{"draws":64,"losses":10,"wins":2},"GB2-03":{"draws":34,"losses":13,"wins":9},"GB2-04":{"draws":74,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":48,"wins":48},"GB2-06":{"draws":2,"losses":61,"wins":21},"GB2-07":{"draws":0,"losses":24,"wins":56},"GB2-08":{"draws":87,"losses":11,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1425.0159683307136,"GB2-05":1301.139212875865,"GB2-06":1208.098508332924,"GB2-07":1504.7368378046194,"GB2-08":1217.152242285979},"none":{"GB2-02":1453.9080120948634,"GB2-03":1466.1792879779643,"GB2-04":1483.8875603348063,"GB2-05":1474.7266136050657,"GB2-06":1212.912535347638,"GB2-07":1652.6540509725637,"GB2-08":1409.5476658850525}},"per_game_tracks":{"medium":{"GB2-03":35.28796962477342,"GB2-05":32.279757091350554,"GB2-06":26.29442357821482,"GB2-07":48.573486962202864,"GB2-08":13.67320578769338},"none":{"GB2-02":16.61661173350593,"GB2-03":40.969815876809534,"GB2-04":40.551305110490894,"GB2-05":47.68105445209972,"GB2-06":26.46626922181831,"GB2-07":63.528190114310334,"GB2-08":34.23396365548673}},"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":27.760514131056105,"none":31.375175900391902},"reasoning_agg":{"medium":{"max":48.573486962202864,"mean":27.760514131056105,"min":13.67320578769338},"none":{"max":63.528190114310334,"mean":31.375175900391902,"min":16.61661173350593}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.528190114310334,"reasoning_variance":3.6146617693357967},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":48.573486962202864,"expected_score":20.770419467319517,"reliability_score":89.05329096728258,"uncertainty_avg":10.946709032717418,"uncertainty_penalty":-6.990094663736588},"none":{"ceiling_score":63.528190114310334,"expected_score":46.18192079294154,"reliability_score":88.375728306454,"uncertainty_avg":11.624271693546007,"uncertainty_penalty":14.806744892549638}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:96d334950f7b14e7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.15725071},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.2552692799999998},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.25526928},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.15725071}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":145},"evidence_basis":"Provider-reported","failed_cell_count":21,"max":0.302804525,"mean":0.12502029041666668,"median":0.082332765,"min":0.01945095,"recorded_attempt_count":145,"run_count":48,"total":6.00097394},"codegen_latency_ms":{"attempt_count":145,"max_ms":712912,"mean_ms":234062.20833333334,"min_ms":20774,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":712912,"mean_ms":506639.625,"min_ms":278552,"run_count":16},"medium":{"attempt_count":53,"max_ms":476873,"mean_ms":144633.375,"min_ms":47325,"run_count":16},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":145,"output_max":80000,"output_mean":25786.458333333332,"output_min":1372,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":80000,"output_mean":58672.9375,"output_min":35008,"run_count":16},"medium":{"attempt_count":53,"output_max":32558,"output_mean":14052.75,"output_min":3762,"run_count":16},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":32.92178047440135,"highest":31.625906752195935,"medium":31.522734372110563,"none":36.58136186400597},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":145,"finish_reasons":["length","stop"],"indexed_attempts":145,"output_token_observations":145,"reasoning_token_observations":102,"total_output_tokens":1237750,"total_reasoning_output_tokens":697293,"total_visible_output_tokens":161414,"visible_token_observations":99},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.625,"model_code_failures":10,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.0625},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125},"intensive":{"admitted_plugins":9,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.25,"model_code_failure_rate":0.4375,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-08-22T23:41:33Z","match_totals_all":{"draws":971,"losses":1496,"wins":746},"match_totals_tracks":{"highest":{"draws":396,"losses":647,"wins":259},"medium":{"draws":237,"losses":384,"wins":172},"none":{"draws":338,"losses":465,"wins":315}},"model_slug":"thinkingmachines-inkling","overall":{"max":68.95924601863939,"mean":28.699834837367963,"min":6.641760874582254},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":43,"overall_ranking_status":"partial","per_game":{"GB2-01":15.649250107241665,"GB2-02":20.20918702880969,"GB2-03":41.56882637540658,"GB2-04":41.149311285803776,"GB2-05":20.247158692047016,"GB2-06":60.52933478522943,"GB2-07":25.78170138825857,"GB2-08":27.872484354770776},"per_game_all":{"GB2-01":20.127720444287903,"GB2-03":49.07939628664797,"GB2-04":38.246708003625635,"GB2-05":27.745441751114686,"GB2-07":21.17159251173317,"GB2-08":41.159823848998705},"per_game_match_totals_all":{"GB2-01":{"draws":159,"losses":277,"wins":54},"GB2-02":{"draws":187,"losses":15,"wins":4},"GB2-03":{"draws":140,"losses":104,"wins":140},"GB2-04":{"draws":276,"losses":66,"wins":56},"GB2-05":{"draws":0,"losses":454,"wins":182},"GB2-06":{"draws":9,"losses":123,"wins":128},"GB2-07":{"draws":0,"losses":308,"wins":108},"GB2-08":{"draws":200,"losses":149,"wins":74}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":49,"losses":83,"wins":6},"GB2-02":{"draws":109,"losses":7,"wins":2},"GB2-03":{"draws":48,"losses":41,"wins":29},"GB2-04":{"draws":81,"losses":18,"wins":27},"GB2-05":{"draws":0,"losses":242,"wins":70},"GB2-06":{"draws":8,"losses":68,"wins":78},"GB2-07":{"draws":0,"losses":121,"wins":45},"GB2-08":{"draws":101,"losses":67,"wins":2}},"medium":{"GB2-01":{"draws":31,"losses":72,"wins":27},"GB2-03":{"draws":24,"losses":31,"wins":69},"GB2-04":{"draws":90,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":77,"wins":41},"GB2-07":{"draws":0,"losses":135,"wins":17},"GB2-08":{"draws":92,"losses":50,"wins":11}},"none":{"GB2-01":{"draws":79,"losses":122,"wins":21},"GB2-02":{"draws":78,"losses":8,"wins":2},"GB2-03":{"draws":68,"losses":32,"wins":42},"GB2-04":{"draws":105,"losses":29,"wins":22},"GB2-05":{"draws":0,"losses":135,"wins":71},"GB2-06":{"draws":1,"losses":55,"wins":50},"GB2-07":{"draws":0,"losses":52,"wins":46},"GB2-08":{"draws":7,"losses":32,"wins":61}}},"per_game_raw_elo_all":{"GB2-01":1254.1395618573863,"GB2-03":1510.528879841835,"GB2-04":1465.3000917723923,"GB2-05":1244.8169147900423,"GB2-07":1234.6068187819974,"GB2-08":1469.7912094858805},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1209.1921036226092,"GB2-02":1461.0862907777541,"GB2-03":1454.1101031373976,"GB2-04":1480.354766936686,"GB2-05":1156.0898611341393,"GB2-06":1606.375142289731,"GB2-07":1275.4800377038869,"GB2-08":1339.095194087079},"medium":{"GB2-01":1370.0621525194288,"GB2-03":1565.2792867639394,"GB2-04":1457.7988288950792,"GB2-05":1258.1782378757614,"GB2-07":1092.4543600337247,"GB2-08":1329.0261862668438},"none":{"GB2-01":1183.164429430121,"GB2-02":1485.2026519480598,"GB2-03":1512.1972496241688,"GB2-04":1457.7466794854122,"GB2-05":1320.182645360226,"GB2-06":1335.1475676513953,"GB2-07":1335.8860586083808,"GB2-08":1741.2522481037183}},"per_game_tracks":{"highest":{"GB2-01":15.649250107241665,"GB2-02":20.20918702880969,"GB2-03":41.56882637540658,"GB2-04":41.149311285803776,"GB2-05":20.247158692047016,"GB2-06":60.52933478522943,"GB2-07":25.78170138825857,"GB2-08":27.872484354770776},"medium":{"GB2-01":32.17571462476984,"GB2-03":57.38467373838492,"GB2-04":37.42221478251373,"GB2-05":28.86430103882667,"GB2-07":6.641760874582254,"GB2-08":26.64774117358596},"none":{"GB2-01":12.558196600852206,"GB2-02":24.312887404123998,"GB2-03":48.28468874615239,"GB2-04":36.1685979425594,"GB2-05":34.124865522470365,"GB2-06":37.1510974048913,"GB2-07":31.09131527235869,"GB2-08":68.95924601863939}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.38883866511949,"medium":24.667872743768225,"none":34.04279310321619},"reasoning_agg":{"highest":{"max":60.52933478522943,"mean":27.38883866511949,"min":15.649250107241665},"medium":{"max":57.38467373838492,"mean":24.667872743768225,"min":6.641760874582254},"none":{"max":68.95924601863939,"mean":34.04279310321619,"min":12.558196600852206}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":68.95924601863939,"expected_score":26.175682693611364,"reasoning_variance":9.374920359447966,"reliability_score":96.8188325801339,"uncertainty_avg":3.181167419866093,"uncertainty_penalty":-2.5241521437565986},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":60.52933478522943,"expected_score":10.8714947333528,"reliability_score":99.40154060329665,"uncertainty_avg":0.5984593967033536,"uncertainty_penalty":-16.51734393176669},"medium":{"ceiling_score":57.38467373838492,"expected_score":23.094701329547643,"reliability_score":99.07811654108187,"uncertainty_avg":0.9218834589181313,"uncertainty_penalty":-1.5731714142205817},"none":{"ceiling_score":68.95924601863939,"expected_score":43.438438946049544,"reliability_score":92.14203988319177,"uncertainty_avg":7.857960116808227,"uncertainty_penalty":9.395645842833353}}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:1ff5d67f22d3eaab","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.008820586750000001,"median":0.007023681,"min":0.00271606,"recorded_attempt_count":19,"run_count":8,"total":0.07056469400000003},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.008820586750000001,"median":0.007023681,"min":0.00271606,"recorded_attempt_count":19,"run_count":8,"total":0.07056469400000003}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.01660212,"mean":0.00430918425,"median":0.0025298300000000003,"min":0.00045831,"recorded_attempt_count":48,"run_count":24,"total":0.10342042200000003},"codegen_latency_ms":{"attempt_count":48,"max_ms":622759,"mean_ms":232922.5,"min_ms":19833,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":622759,"mean_ms":483202.0,"min_ms":329312,"run_count":8},"medium":{"attempt_count":16,"max_ms":213246,"mean_ms":118332.0,"min_ms":41554,"run_count":8},"none":{"attempt_count":13,"max_ms":226636,"mean_ms":97233.5,"min_ms":19833,"run_count":8}},"codegen_output_tokens":{"attempt_count":48,"output_max":43929,"output_mean":12519.625,"output_min":1331,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":43929,"output_mean":28964.5,"output_min":18493,"run_count":8},"medium":{"attempt_count":16,"output_max":8961,"output_mean":5674.0,"output_min":2048,"run_count":8},"none":{"attempt_count":13,"output_max":5763,"output_mean":2920.375,"output_min":1331,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":33.092898402983856,"highest":39.10085728904717,"medium":36.76717792204459,"none":15.021272069324533},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["error","stop"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":13,"total_output_tokens":300471,"total_reasoning_output_tokens":2697,"total_visible_output_tokens":20666,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-08-23T05:21:37Z","match_totals_all":{"draws":665,"losses":1040,"wins":378},"match_totals_tracks":{"highest":{"draws":151,"losses":127,"wins":90},"medium":{"draws":284,"losses":203,"wins":134},"none":{"draws":230,"losses":710,"wins":154}},"model_slug":"openai-gpt-oss-120b","overall":{"max":67.33768307109139,"mean":28.284755733249842,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-02":13.814065400064843,"GB2-04":38.75509843220986,"GB2-06":67.33768307109139,"GB2-07":41.715724086496124,"GB2-08":33.88171545537361},"per_game_all":{"GB2-04":25.191117937546124,"GB2-06":43.8964833106115,"GB2-08":30.191093960793932},"per_game_match_totals_all":{"GB2-01":{"draws":54,"losses":143,"wins":53},"GB2-02":{"draws":117,"losses":15,"wins":4},"GB2-03":{"draws":101,"losses":80,"wins":17},"GB2-04":{"draws":157,"losses":94,"wins":25},"GB2-05":{"draws":0,"losses":207,"wins":80},"GB2-06":{"draws":7,"losses":213,"wins":130},"GB2-07":{"draws":0,"losses":192,"wins":54},"GB2-08":{"draws":229,"losses":96,"wins":15}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":52,"losses":10,"wins":0},"GB2-04":{"draws":32,"losses":20,"wins":14},"GB2-06":{"draws":6,"losses":25,"wins":43},"GB2-07":{"draws":0,"losses":54,"wins":30},"GB2-08":{"draws":61,"losses":18,"wins":3}},"medium":{"GB2-01":{"draws":23,"losses":35,"wins":26},"GB2-02":{"draws":65,"losses":5,"wins":4},"GB2-03":{"draws":41,"losses":7,"wins":6},"GB2-04":{"draws":75,"losses":7,"wins":2},"GB2-05":{"draws":0,"losses":59,"wins":47},"GB2-06":{"draws":1,"losses":70,"wins":40},"GB2-08":{"draws":79,"losses":20,"wins":9}},"none":{"GB2-01":{"draws":31,"losses":108,"wins":27},"GB2-03":{"draws":60,"losses":73,"wins":11},"GB2-04":{"draws":50,"losses":67,"wins":9},"GB2-05":{"draws":0,"losses":148,"wins":33},"GB2-06":{"draws":0,"losses":118,"wins":47},"GB2-07":{"draws":0,"losses":138,"wins":24},"GB2-08":{"draws":89,"losses":58,"wins":3}}},"per_game_raw_elo_all":{"GB2-04":1384.5046558307313,"GB2-06":1414.966830487484,"GB2-08":1368.937842714945},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1446.1637680119986,"GB2-04":1478.284379118747,"GB2-06":1701.327703247478,"GB2-07":1441.4354314549128,"GB2-08":1409.8830365675533},"medium":{"GB2-01":1446.8660097244824,"GB2-02":1477.2560006314968,"GB2-03":1446.9342129195318,"GB2-04":1460.309058381632,"GB2-05":1460.9826435606906,"GB2-06":1352.3710022776015,"GB2-08":1426.316763828664},"none":{"GB2-01":1226.334134979911,"GB2-03":1274.046932999176,"GB2-04":1214.9205299918149,"GB2-05":1100.5438465639747,"GB2-06":1191.2017859373725,"GB2-07":1114.7430613418464,"GB2-08":1270.6137277486175}},"per_game_tracks":{"highest":{"GB2-02":13.814065400064843,"GB2-04":38.75509843220986,"GB2-06":67.33768307109139,"GB2-07":41.715724086496124,"GB2-08":33.88171545537361},"medium":{"GB2-01":39.24390988896453,"GB2-02":21.69349452538362,"GB2-03":38.11887554806834,"GB2-04":36.81825538042852,"GB2-05":46.6367117182378,"GB2-06":38.6741764977918,"GB2-08":36.18482189543753},"none":{"GB2-01":17.729065008395047,"GB2-03":16.6420903975188,"GB2-04":0.0,"GB2-05":15.533730958964114,"GB2-06":25.677590362951314,"GB2-07":9.05968322587179,"GB2-08":20.506744531570664}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.76612471599146,"medium":35.560045662536105,"none":14.528096821221974},"reasoning_agg":{"highest":{"max":67.33768307109139,"mean":34.76612471599146,"min":13.814065400064843},"medium":{"max":46.6367117182378,"mean":35.560045662536105,"min":21.69349452538362},"none":{"max":25.677590362951314,"mean":14.528096821221974,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":67.33768307109139,"expected_score":21.76578552024769,"reasoning_variance":21.031948841314133,"reliability_score":93.20120084392877,"uncertainty_avg":6.7987991560712295,"uncertainty_penalty":-6.518970213002152},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.33768307109139,"expected_score":23.31658827319312,"reliability_score":85.56428552370087,"uncertainty_avg":14.43571447629912,"uncertainty_penalty":-11.44953644279834},"medium":{"ceiling_score":46.6367117182378,"expected_score":27.773548820311984,"reliability_score":89.87943715512728,"uncertainty_avg":10.120562844872719,"uncertainty_penalty":-7.786496842224121},"none":{"ceiling_score":25.677590362951314,"expected_score":13.265595194780943,"reliability_score":99.91173921845633,"uncertainty_avg":0.08826078154367042,"uncertainty_penalty":-1.262501626441031}}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:a91d2017566aaf6e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":45},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":45,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":45,"max_ms":905283,"mean_ms":194374.625,"min_ms":21975,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":905283,"mean_ms":509118.375,"min_ms":288605,"run_count":8},"none":{"attempt_count":30,"max_ms":62079,"mean_ms":37002.75,"min_ms":21975,"run_count":16}},"codegen_output_tokens":{"attempt_count":45,"output_max":52275,"output_mean":12297.333333333334,"output_min":1733,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":52275,"output_mean":30105.875,"output_min":9014,"run_count":8},"none":{"attempt_count":30,"output_max":6330,"output_mean":3393.0625,"output_min":1733,"run_count":16}},"display_name":"North Mini Code","economics":{"medium":36.059131406213616,"none":27.306622154385593},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":45,"finish_reasons":["stop"],"indexed_attempts":45,"output_token_observations":45,"total_output_tokens":295136},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.125}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":352,"losses":460,"wins":246},"match_totals_tracks":{"medium":{"draws":170,"losses":228,"wins":168},"none":{"draws":182,"losses":232,"wins":78}},"model_slug":"cohere-north-mini-code","overall":{"max":50.38149773221454,"mean":26.986632490268974,"min":20.41646207891444},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":45,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":96,"losses":89,"wins":21},"GB2-03":{"draws":23,"losses":21,"wins":4},"GB2-04":{"draws":75,"losses":12,"wins":7},"GB2-05":{"draws":0,"losses":50,"wins":64},"GB2-06":{"draws":1,"losses":67,"wins":32},"GB2-07":{"draws":0,"losses":182,"wins":114},"GB2-08":{"draws":157,"losses":39,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":23,"losses":21,"wins":4},"GB2-04":{"draws":75,"losses":12,"wins":7},"GB2-05":{"draws":0,"losses":50,"wins":64},"GB2-06":{"draws":1,"losses":67,"wins":32},"GB2-07":{"draws":0,"losses":59,"wins":61},"GB2-08":{"draws":71,"losses":19,"wins":0}},"none":{"GB2-01":{"draws":96,"losses":89,"wins":21},"GB2-07":{"draws":0,"losses":123,"wins":53},"GB2-08":{"draws":86,"losses":20,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1407.4114294677433,"GB2-04":1474.12603505286,"GB2-05":1518.9526866740612,"GB2-06":1289.8281165492485,"GB2-07":1441.5715457857082,"GB2-08":1369.9716806578233},"none":{"GB2-01":1287.6381095392642,"GB2-07":1278.282398636208,"GB2-08":1403.7240598409555}},"per_game_tracks":{"medium":{"GB2-03":28.834909047409482,"GB2-04":36.61467322762245,"GB2-05":50.38149773221454,"GB2-06":31.775234501033314,"GB2-07":40.8825963105233,"GB2-08":27.8658776184786},"none":{"GB2-01":23.179971665322682,"GB2-07":24.88114022139318,"GB2-08":33.85875457644092}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.55680290162351,"none":20.41646207891444},"reasoning_agg":{"medium":{"max":50.38149773221454,"mean":33.55680290162351,"min":27.8658776184786},"none":{"max":33.85875457644092,"mean":20.41646207891444,"min":23.179971665322682}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":50.38149773221454,"reasoning_variance":13.140340822709074},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":50.38149773221454,"expected_score":29.159124281416087,"reliability_score":68.05439085441536,"uncertainty_avg":31.94560914558464,"uncertainty_penalty":-4.397678620207426},"none":{"ceiling_score":33.85875457644092,"expected_score":30.57658316321123,"reliability_score":93.77819706363937,"uncertainty_avg":6.221802936360629,"uncertainty_penalty":10.16012108429679}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:0903ce17ebd3d72b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.348093},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":25.52269069782157,"highest":34.434364323170016,"medium":31.65005777345651,"none":18.361836436012375},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":150003},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-08-05T05:18:42Z","match_totals_all":{"draws":341,"losses":704,"wins":302},"match_totals_tracks":{"highest":{"draws":120,"losses":220,"wins":87},"medium":{"draws":141,"losses":284,"wins":149},"none":{"draws":80,"losses":200,"wins":66}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":46.38961044453501,"mean":25.465631974669503,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":46,"overall_ranking_status":"partial","per_game":{"GB2-04":40.36325367187167,"GB2-05":20.711146730771695,"GB2-06":32.519767162748906,"GB2-07":46.38961044453501,"GB2-08":32.18804360592281},"per_game_all":{"GB2-05":21.122297381759697,"GB2-06":39.81267518662841,"GB2-07":15.633099525076593},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":77,"wins":28},"GB2-02":{"draws":55,"losses":2,"wins":1},"GB2-04":{"draws":117,"losses":22,"wins":13},"GB2-05":{"draws":0,"losses":181,"wins":59},"GB2-06":{"draws":1,"losses":160,"wins":112},"GB2-07":{"draws":0,"losses":195,"wins":49},"GB2-08":{"draws":103,"losses":67,"wins":40}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":54,"losses":18,"wins":6},"GB2-05":{"draws":0,"losses":62,"wins":16},"GB2-06":{"draws":0,"losses":56,"wins":27},"GB2-07":{"draws":0,"losses":62,"wins":34},"GB2-08":{"draws":66,"losses":22,"wins":4}},"medium":{"GB2-01":{"draws":41,"losses":33,"wins":22},"GB2-04":{"draws":63,"losses":4,"wins":7},"GB2-05":{"draws":0,"losses":62,"wins":26},"GB2-06":{"draws":0,"losses":71,"wins":47},"GB2-07":{"draws":0,"losses":69,"wins":11},"GB2-08":{"draws":37,"losses":45,"wins":36}},"none":{"GB2-01":{"draws":24,"losses":44,"wins":6},"GB2-02":{"draws":55,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":57,"wins":17},"GB2-06":{"draws":1,"losses":33,"wins":38},"GB2-07":{"draws":0,"losses":64,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1178.5671859101608,"GB2-06":1370.4776064440484,"GB2-07":1191.1508632154967},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1484.7935464109898,"GB2-05":1174.3948018938386,"GB2-06":1285.0945886378513,"GB2-07":1483.6954722538387,"GB2-08":1391.2575126535978},"medium":{"GB2-01":1463.0985357998015,"GB2-04":1494.7535575112174,"GB2-05":1207.2298320637442,"GB2-06":1433.619465594597,"GB2-07":1045.4789996487496,"GB2-08":1432.4974729461187},"none":{"GB2-01":1168.6771765022436,"GB2-02":1482.2648473381566,"GB2-05":1154.0769237728996,"GB2-06":1392.718765099697,"GB2-07":1044.278117743902}},"per_game_tracks":{"highest":{"GB2-04":40.36325367187167,"GB2-05":20.711146730771695,"GB2-06":32.519767162748906,"GB2-07":46.38961044453501,"GB2-08":32.18804360592281},"medium":{"GB2-01":41.208769238182654,"GB2-04":41.723688617519116,"GB2-05":23.847704758895738,"GB2-06":45.60739618718008,"GB2-07":0.5096881306947669,"GB2-08":37.003099708266724},"none":{"GB2-01":10.192924369283574,"GB2-02":21.497354945210386,"GB2-05":18.808040655611663,"GB2-06":41.31086220995625,"GB2-07":0.0}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.616960536836054,"medium":29.45369755484081,"none":16.326237832331643},"reasoning_agg":{"highest":{"max":46.38961044453501,"mean":30.616960536836054,"min":20.711146730771695},"medium":{"max":45.60739618718008,"mean":29.45369755484081,"min":0.5096881306947669},"none":{"max":41.31086220995625,"mean":16.326237832331643,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":46.38961044453501,"expected_score":16.28221314924856,"reasoning_variance":14.290722704504411,"reliability_score":89.03721363009146,"uncertainty_avg":10.962786369908537,"uncertainty_penalty":-9.183418825420944},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":46.38961044453501,"expected_score":12.580235999777699,"reliability_score":89.81436887103946,"uncertainty_avg":10.185631128960543,"uncertainty_penalty":-18.036724537058355},"medium":{"ceiling_score":45.60739618718008,"expected_score":26.050923115022442,"reliability_score":92.29539426094362,"uncertainty_avg":7.70460573905637,"uncertainty_penalty":-3.4027744398183692},"none":{"ceiling_score":41.31086220995625,"expected_score":15.126642008177646,"reliability_score":83.8943981061426,"uncertainty_avg":16.10560189385739,"uncertainty_penalty":-1.199595824153997}}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:a9c28fc18da0cc0b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.3927285,"mean":0.1902770625,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":14,"run_count":9,"total":1.914945},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.042994687499999996,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.3439575}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.042994687499999996,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.3439575},"historical-provider-setting-intensive":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.3927285,"mean":0.1902770625,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":14,"run_count":9,"total":1.914945}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.3927285,"mean":0.116635875,"median":0.0747585,"min":0.0223935,"recorded_attempt_count":28,"run_count":17,"total":2.2589024999999996},"codegen_latency_ms":{"attempt_count":28,"max_ms":776640,"mean_ms":218770.82352941178,"min_ms":28440,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":776640,"mean_ms":364061.1111111111,"min_ms":132587,"run_count":9},"none":{"attempt_count":14,"max_ms":130711,"mean_ms":55319.25,"min_ms":28440,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":52664,"output_mean":15146.29411764706,"output_min":1452,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":52664,"output_mean":25839.666666666668,"output_min":10169,"run_count":9},"none":{"attempt_count":14,"output_max":5014,"output_mean":3116.25,"output_min":1452,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":21.756661652782977,"none":36.5441266046817},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":257487},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-08-05T04:49:34Z","match_totals_all":{"draws":121,"losses":381,"wins":192},"match_totals_tracks":{"highest":{"draws":17,"losses":226,"wins":75},"none":{"draws":104,"losses":155,"wins":117}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":40.86555647776021,"mean":24.2470324561767,"min":11.636247230495337},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":47,"overall_ranking_status":"partial","per_game":{"GB2-01":11.636247230495337,"GB2-05":24.36438641581923,"GB2-06":31.129646707507366,"GB2-07":19.89636625730998},"per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":98,"wins":48},"GB2-05":{"draws":0,"losses":104,"wins":64},"GB2-06":{"draws":8,"losses":97,"wins":59},"GB2-07":{"draws":0,"losses":64,"wins":20},"GB2-08":{"draws":87,"losses":18,"wins":1}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":51,"wins":8},"GB2-05":{"draws":0,"losses":57,"wins":21},"GB2-06":{"draws":0,"losses":54,"wins":26},"GB2-07":{"draws":0,"losses":64,"wins":20}},"none":{"GB2-01":{"draws":9,"losses":47,"wins":40},"GB2-05":{"draws":0,"losses":47,"wins":43},"GB2-06":{"draws":8,"losses":43,"wins":33},"GB2-08":{"draws":87,"losses":18,"wins":1}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1182.0336827681099,"GB2-05":1215.6711985096656,"GB2-06":1269.3787546862945,"GB2-07":1231.208763210193},"none":{"GB2-01":1459.7788681959753,"GB2-05":1366.1081717055815,"GB2-06":1341.437842566501,"GB2-08":1368.2539193575665}},"per_game_tracks":{"highest":{"GB2-01":11.636247230495337,"GB2-05":24.36438641581923,"GB2-06":31.129646707507366,"GB2-07":19.89636625730998},"none":{"GB2-01":40.86555647776021,"GB2-05":37.950977461561465,"GB2-06":37.28354233376265,"GB2-08":30.076430145642476}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.76423985189867,"none":30.729825060454733},"reasoning_agg":{"highest":{"max":31.129646707507366,"mean":17.76423985189867,"min":11.636247230495337},"none":{"max":40.86555647776021,"mean":30.729825060454733,"min":30.076430145642476}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":40.86555647776021,"reasoning_variance":12.965585208556064},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":31.129646707507366,"expected_score":2.6906575438894826,"reliability_score":87.99428667841505,"uncertainty_avg":12.005713321584942,"uncertainty_penalty":-15.073582308009186},"none":{"ceiling_score":40.86555647776021,"expected_score":36.09900216350426,"reliability_score":92.31225275006898,"uncertainty_avg":7.687747249931022,"uncertainty_penalty":5.369177103049527}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:879c7abb2fdbd104","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":92},"evidence_basis":"Provider-reported","failed_cell_count":15,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":92,"run_count":32,"total":0.0},"codegen_latency_ms":{"attempt_count":93,"max_ms":410978,"mean_ms":158095.9375,"min_ms":18717,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":53,"max_ms":410978,"mean_ms":269539.1875,"min_ms":161500,"run_count":16},"none":{"attempt_count":40,"max_ms":90441,"mean_ms":46652.6875,"min_ms":18717,"run_count":16}},"codegen_output_tokens":{"attempt_count":92,"output_max":92074,"output_mean":33594.125,"output_min":2036,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":52,"output_max":92074,"output_mean":60516.0,"output_min":20000,"run_count":16},"none":{"attempt_count":40,"output_max":17378,"output_mean":6672.25,"output_min":2036,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"medium":27.413423511790604,"none":28.744961396455825},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":93,"finish_reasons":["length","stop","unknown"],"indexed_attempts":94,"output_token_observations":93,"reasoning_token_observations":65,"total_output_tokens":1075012,"total_reasoning_output_tokens":626571,"total_visible_output_tokens":109787,"visible_token_observations":55},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":15,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.06666666666666667,"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":1,"model_code_failure_rate":0.6,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.3333333333333333},"baseline":{"admitted_plugins":10,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":6,"first_pass_rate":0.375,"model_code_failure_rate":0.375,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:59Z","match_totals_all":{"draws":861,"losses":901,"wins":418},"match_totals_tracks":{"medium":{"draws":254,"losses":493,"wins":227},"none":{"draws":607,"losses":408,"wins":191}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":43.039137688291845,"mean":23.679689895531027,"min":13.028496075357975},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold","fixed_coverage_incomplete"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":127,"losses":213,"wins":98},"GB2-02":{"draws":195,"losses":28,"wins":3},"GB2-03":{"draws":74,"losses":69,"wins":33},"GB2-04":{"draws":215,"losses":31,"wins":20},"GB2-06":{"draws":6,"losses":319,"wins":99},"GB2-07":{"draws":0,"losses":206,"wins":160},"GB2-08":{"draws":244,"losses":35,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":32,"losses":105,"wins":7},"GB2-02":{"draws":95,"losses":21,"wins":2},"GB2-04":{"draws":125,"losses":26,"wins":13},"GB2-06":{"draws":2,"losses":135,"wins":45},"GB2-07":{"draws":0,"losses":206,"wins":160}},"none":{"GB2-01":{"draws":95,"losses":108,"wins":91},"GB2-02":{"draws":100,"losses":7,"wins":1},"GB2-03":{"draws":74,"losses":69,"wins":33},"GB2-04":{"draws":90,"losses":5,"wins":7},"GB2-06":{"draws":4,"losses":184,"wins":54},"GB2-08":{"draws":244,"losses":35,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1255.2978439767162,"GB2-02":1458.0330816696924,"GB2-04":1437.5231110068432,"GB2-06":1258.6020053075358,"GB2-07":1457.2579842748223},"none":{"GB2-01":1414.6441048464835,"GB2-02":1447.0482654162681,"GB2-03":1375.6716512399985,"GB2-04":1480.6944633151002,"GB2-06":1095.9852006337294,"GB2-08":1374.3105536667902}},"per_game_tracks":{"medium":{"GB2-01":18.281722008614956,"GB2-02":13.028496075357975,"GB2-04":32.571165805690754,"GB2-06":30.146595980997496,"GB2-07":43.039137688291845},"none":{"GB2-01":36.99825914849188,"GB2-02":16.708450302583884,"GB2-03":29.68470258883002,"GB2-04":40.59443860612531,"GB2-06":17.22866796894646,"GB2-08":31.255249763757412}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":21.801093294221513,"none":25.558286496840537},"reasoning_agg":{"medium":{"max":43.039137688291845,"mean":21.801093294221513,"min":13.028496075357975},"none":{"max":40.59443860612531,"mean":25.558286496840537,"min":16.708450302583884}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":43.039137688291845,"reasoning_variance":3.7571932026190247},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.039137688291845,"expected_score":20.307726309604426,"reliability_score":78.53741857234075,"uncertainty_avg":21.462581427659252,"uncertainty_penalty":-1.4933669846170865},"none":{"ceiling_score":40.59443860612531,"expected_score":33.42244420280955,"reliability_score":96.5888514401961,"uncertainty_avg":3.411148559803902,"uncertainty_penalty":7.8641577059690135}}}],"public_release_id":"gb2-20260824-2dee950279ef","results_cut_id":"gb2-20260824-2dee950279ef","schema_version":2,"snapshot_id":"20260824_103349","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-08-24 10:33 UTC","versus_totals_all":{"claude-fable-5":{"claude-fable-5":{"draws":4,"losses":12,"wins":12},"claude-opus-4-5":{"draws":7,"losses":8,"wins":45},"claude-opus-4-8":{"draws":6,"losses":26,"wins":28},"claude-opus-5":{"draws":25,"losses":58,"wins":57},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":22},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":28},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":8},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":34},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":13},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":37},"gpt-5.5":{"draws":8,"losses":22,"wins":24},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":48},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":27},"o3":{"draws":1,"losses":2,"wins":31},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":19},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":19},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":20},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":30},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":21}},"claude-opus-4-5":{"claude-fable-5":{"draws":5,"losses":29,"wins":6},"claude-opus-4-5":{"draws":35,"losses":32,"wins":37},"claude-opus-4-8":{"draws":8,"losses":29,"wins":17},"claude-opus-5":{"draws":23,"losses":130,"wins":17},"claude-sonnet-5":{"draws":36,"losses":23,"wins":53},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":20},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":11},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":8},"google/gemini-3.5-flash-lite":{"draws":91,"losses":55,"wins":122},"google/gemini-3.6-flash":{"draws":66,"losses":112,"wins":78},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":13},"gpt-4.1":{"draws":8,"losses":6,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":9,"wins":11},"gpt-5.4":{"draws":22,"losses":45,"wins":19},"gpt-5.4-mini":{"draws":17,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":24},"gpt-5.5":{"draws":18,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":32,"losses":23,"wins":39},"gpt-5.6-sol":{"draws":15,"losses":63,"wins":22},"gpt-5.6-terra":{"draws":24,"losses":21,"wins":17},"inclusionai/ling-3.0-flash":{"draws":19,"losses":10,"wins":23},"meituan/longcat-2.0":{"draws":31,"losses":22,"wins":48},"meta/muse-spark-1.2":{"draws":15,"losses":29,"wins":20},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":56,"losses":57,"wins":41},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":20},"o3":{"draws":30,"losses":54,"wins":118},"openai/gpt-oss-120b":{"draws":19,"losses":5,"wins":64},"poolside/laguna-s-2.1":{"draws":54,"losses":6,"wins":48},"qwen/qwen3.7-max":{"draws":5,"losses":9,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":10,"losses":11,"wins":35},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":13},"thinkingmachines/inkling":{"draws":31,"losses":13,"wins":64},"thinkingmachines/inkling-small":{"draws":3,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":48,"losses":61,"wins":41},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":9},"z-ai/glm-5.2":{"draws":8,"losses":17,"wins":19}},"claude-opus-4-8":{"claude-fable-5":{"draws":6,"losses":28,"wins":26},"claude-opus-4-5":{"draws":17,"losses":25,"wins":52},"claude-opus-4-8":{"draws":8,"losses":10,"wins":10},"claude-opus-5":{"draws":21,"losses":66,"wins":31},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":18,"wins":11},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":19,"losses":27,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":11},"gpt-5":{"draws":11,"losses":13,"wins":26},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":36},"gpt-5.5":{"draws":19,"losses":35,"wins":22},"gpt-5.6-terra":{"draws":22,"losses":17,"wins":27},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":17},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":31},"o3":{"draws":4,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":23},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":17},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":15,"losses":20,"wins":19},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":12,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":25}},"claude-opus-5":{"claude-fable-5":{"draws":25,"losses":57,"wins":58},"claude-opus-4-5":{"draws":35,"losses":29,"wins":172},"claude-opus-4-8":{"draws":21,"losses":31,"wins":66},"claude-opus-5":{"draws":48,"losses":172,"wins":172},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":46},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":55},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":11,"wins":60},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":94},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":109},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":20},"gpt-4.1":{"draws":10,"losses":2,"wins":41},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":5,"wins":51},"gpt-5.4":{"draws":0,"losses":0,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":32},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":54},"gpt-5.5":{"draws":21,"losses":33,"wins":94},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":6},"gpt-5.6-terra":{"draws":37,"losses":18,"wins":107},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":22},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":50},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":33},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":29},"moonshotai/kimi-k3":{"draws":15,"losses":13,"wins":62},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":43},"o3":{"draws":2,"losses":6,"wins":78},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":23},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":72},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":55},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":20},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":28},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":48},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":56},"x-ai/grok-4.5":{"draws":17,"losses":22,"wins":85},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":1,"wins":35},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":60}},"claude-sonnet-5":{"claude-opus-4-5":{"draws":36,"losses":53,"wins":23},"claude-opus-5":{"draws":2,"losses":3,"wins":3},"claude-sonnet-5":{"draws":28,"losses":38,"wins":38},"google/gemini-3.5-flash-lite":{"draws":72,"losses":56,"wins":124},"google/gemini-3.6-flash":{"draws":56,"losses":99,"wins":73},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5.4":{"draws":44,"losses":74,"wins":28},"gpt-5.6-luna":{"draws":51,"losses":40,"wins":64},"gpt-5.6-sol":{"draws":28,"losses":124,"wins":26},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":22,"losses":9,"wins":41},"meta/muse-spark-1.2":{"draws":29,"losses":37,"wins":36},"moonshotai/kimi-k3":{"draws":47,"losses":55,"wins":30},"o3":{"draws":12,"losses":59,"wins":67},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":33},"poolside/laguna-s-2.1":{"draws":28,"losses":5,"wins":41},"qwen/qwen3.8-max":{"draws":0,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":12},"thinkingmachines/inkling":{"draws":29,"losses":11,"wins":48},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":36,"losses":46,"wins":18},"z-ai/glm-5.2":{"draws":2,"losses":4,"wins":6}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":9,"losses":22,"wins":3},"claude-opus-4-8":{"draws":7,"losses":15,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":13,"wins":13},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":1},"google/gemini-3.5-flash-lite":{"draws":19,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":27,"wins":11},"gpt-5.5":{"draws":14,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":10,"wins":6},"meituan/longcat-2.0":{"draws":22,"losses":18,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":15,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":13},"o3":{"draws":12,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":21,"losses":2,"wins":15},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":5,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":24,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":5}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":3,"losses":22,"wins":3},"claude-opus-4-5":{"draws":28,"losses":33,"wins":11},"claude-opus-4-8":{"draws":11,"losses":28,"wins":7},"claude-opus-5":{"draws":8,"losses":46,"wins":2},"cohere/north-mini-code":{"draws":15,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":38,"losses":25,"wins":25},"deepseek/deepseek-v4-pro":{"draws":18,"losses":28,"wins":10},"google/gemini-3.1-flash-lite":{"draws":13,"losses":27,"wins":32},"google/gemini-3.5-flash":{"draws":18,"losses":15,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":9},"google/gemini-3.6-flash":{"draws":16,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":14,"losses":19,"wins":15},"gpt-4.1":{"draws":13,"losses":9,"wins":8},"gpt-5":{"draws":13,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":25,"losses":19,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":18,"wins":27},"gpt-5.5":{"draws":28,"losses":31,"wins":1},"gpt-5.6-terra":{"draws":22,"losses":37,"wins":7},"inclusionai/ling-3.0-flash":{"draws":26,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":13},"minimax/minimax-m3":{"draws":14,"losses":19,"wins":15},"mistralai/mistral-medium-3-5":{"draws":9,"losses":14,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":23,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":22,"wins":24},"o3":{"draws":11,"losses":15,"wins":20},"openai/gpt-oss-120b":{"draws":24,"losses":22,"wins":12},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":10},"qwen/qwen3.7-max":{"draws":18,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":18,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":18,"wins":20},"tencent/hy3-preview":{"draws":21,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":17,"wins":20},"x-ai/grok-4.5":{"draws":2,"losses":12,"wins":6},"x-ai/grok-build-0.1":{"draws":11,"losses":7,"wins":6},"xiaomi/mimo-v2.5":{"draws":48,"losses":49,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":32,"losses":34,"wins":12}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":19,"losses":19,"wins":12},"claude-opus-4-8":{"draws":11,"losses":23,"wins":12},"claude-opus-5":{"draws":6,"losses":55,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":28},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":14,"losses":6,"wins":14},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":10},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":4,"losses":6,"wins":14},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":12},"gpt-5.5":{"draws":15,"losses":16,"wins":3},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":10},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":12},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":14},"o3":{"draws":11,"losses":15,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":17,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":11,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":11,"wins":16}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":2,"losses":22,"wins":0},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":9,"losses":27,"wins":4},"claude-opus-5":{"draws":4,"losses":27,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":13,"losses":32,"wins":27},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":17,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":12},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":16,"wins":14},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-5":{"draws":14,"losses":18,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":21,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":29,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":25,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":11,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":24,"wins":13},"o3":{"draws":10,"losses":24,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":24,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.5":{"draws":35,"losses":42,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":21,"wins":8}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-opus-4-5":{"draws":18,"losses":16,"wins":22},"claude-opus-4-8":{"draws":13,"losses":11,"wins":18},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":14},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":8,"losses":8,"wins":18},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":17},"gpt-5.5":{"draws":11,"losses":21,"wins":16},"gpt-5.6-terra":{"draws":14,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":20},"o3":{"draws":8,"losses":18,"wins":10},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":9,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":7,"losses":11,"wins":16}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":92,"losses":122,"wins":56},"claude-opus-4-8":{"draws":13,"losses":24,"wins":9},"claude-opus-5":{"draws":17,"losses":94,"wins":9},"claude-sonnet-5":{"draws":72,"losses":124,"wins":56},"cohere/north-mini-code":{"draws":19,"losses":11,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":12,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":4},"google/gemini-3.5-flash-lite":{"draws":214,"losses":207,"wins":207},"google/gemini-3.6-flash":{"draws":208,"losses":315,"wins":130},"google/gemma-4-31b-it":{"draws":7,"losses":15,"wins":4},"gpt-4.1":{"draws":6,"losses":6,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":10,"wins":8},"gpt-5":{"draws":19,"losses":10,"wins":7},"gpt-5.4":{"draws":72,"losses":161,"wins":35},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":7},"gpt-5.4-nano":{"draws":19,"losses":12,"wins":19},"gpt-5.5":{"draws":30,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":79,"losses":100,"wins":71},"gpt-5.6-sol":{"draws":32,"losses":201,"wins":21},"gpt-5.6-terra":{"draws":26,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":69,"losses":30,"wins":75},"meituan/longcat-2.0":{"draws":70,"losses":96,"wins":101},"meta/muse-spark-1.2":{"draws":45,"losses":95,"wins":40},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":121,"losses":167,"wins":64},"nex-agi/nex-n2-pro":{"draws":13,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":8},"o3":{"draws":64,"losses":241,"wins":132},"openai/gpt-oss-120b":{"draws":41,"losses":30,"wins":85},"poolside/laguna-s-2.1":{"draws":117,"losses":81,"wins":72},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":12,"losses":5,"wins":4},"stepfun/step-3.7-flash":{"draws":21,"losses":41,"wins":36},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":109,"losses":80,"wins":115},"thinkingmachines/inkling-small":{"draws":5,"losses":4,"wins":11},"x-ai/grok-4.5":{"draws":72,"losses":162,"wins":62},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":17,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":11},"z-ai/glm-5.2":{"draws":14,"losses":14,"wins":18}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":22,"wins":14},"claude-opus-4-5":{"draws":67,"losses":78,"wins":113},"claude-opus-4-8":{"draws":19,"losses":16,"wins":27},"claude-opus-5":{"draws":16,"losses":109,"wins":33},"claude-sonnet-5":{"draws":56,"losses":73,"wins":99},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":22},"deepseek/deepseek-v4-pro":{"draws":13,"losses":7,"wins":16},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":208,"losses":130,"wins":315},"google/gemini-3.6-flash":{"draws":118,"losses":203,"wins":203},"google/gemma-4-31b-it":{"draws":10,"losses":9,"wins":7},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":10,"losses":6,"wins":4},"gpt-5":{"draws":5,"losses":12,"wins":21},"gpt-5.4":{"draws":52,"losses":120,"wins":70},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":23},"gpt-5.4-nano":{"draws":18,"losses":11,"wins":19},"gpt-5.5":{"draws":25,"losses":23,"wins":26},"gpt-5.6-luna":{"draws":62,"losses":58,"wins":114},"gpt-5.6-sol":{"draws":31,"losses":146,"wins":63},"gpt-5.6-terra":{"draws":21,"losses":19,"wins":30},"inclusionai/ling-3.0-flash":{"draws":90,"losses":29,"wins":75},"meituan/longcat-2.0":{"draws":73,"losses":46,"wins":138},"meta/muse-spark-1.2":{"draws":30,"losses":82,"wins":70},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":99,"losses":115,"wins":128},"nex-agi/nex-n2-pro":{"draws":15,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":21},"o3":{"draws":64,"losses":133,"wins":211},"openai/gpt-oss-120b":{"draws":28,"losses":6,"wins":95},"poolside/laguna-s-2.1":{"draws":105,"losses":41,"wins":108},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":21},"qwen/qwen3.8-max":{"draws":1,"losses":11,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":9,"wins":53},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":18},"thinkingmachines/inkling":{"draws":110,"losses":43,"wins":141},"thinkingmachines/inkling-small":{"draws":8,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":58,"losses":125,"wins":132},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":15,"losses":8,"wins":19}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":8,"wins":1},"claude-opus-4-5":{"draws":11,"losses":13,"wins":14},"claude-opus-4-8":{"draws":10,"losses":16,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":0},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":14,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":7,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":5,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":8,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":13},"gpt-5.5":{"draws":7,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":2},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":13},"o3":{"draws":8,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":4,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":1,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":13,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":26,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":3}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":8,"wins":10},"google/gemini-3.6-flash":{"draws":10,"losses":4,"wins":6},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":0},"o3":{"draws":0,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-fable-5":{"draws":2,"losses":34,"wins":2},"claude-opus-4-5":{"draws":25,"losses":21,"wins":20},"claude-opus-4-8":{"draws":11,"losses":26,"wins":13},"claude-opus-5":{"draws":10,"losses":51,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":4,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":18,"wins":8},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":21,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":8},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":13},"gpt-5.5":{"draws":11,"losses":21,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":15},"o3":{"draws":6,"losses":16,"wins":20},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":8,"losses":18,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":31,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":19}},"gpt-5.4":{"claude-opus-4-5":{"draws":22,"losses":19,"wins":45},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":44,"losses":28,"wins":74},"google/gemini-3.5-flash-lite":{"draws":72,"losses":35,"wins":161},"google/gemini-3.6-flash":{"draws":52,"losses":70,"wins":120},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":40,"losses":54,"wins":54},"gpt-5.6-luna":{"draws":53,"losses":22,"wins":90},"gpt-5.6-sol":{"draws":35,"losses":77,"wins":54},"inclusionai/ling-3.0-flash":{"draws":8,"losses":9,"wins":25},"meituan/longcat-2.0":{"draws":18,"losses":12,"wins":43},"meta/muse-spark-1.2":{"draws":19,"losses":33,"wins":48},"moonshotai/kimi-k3":{"draws":32,"losses":30,"wins":64},"o3":{"draws":11,"losses":29,"wins":106},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":34},"poolside/laguna-s-2.1":{"draws":28,"losses":3,"wins":37},"qwen/qwen3.8-max":{"draws":9,"losses":1,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":21},"thinkingmachines/inkling":{"draws":19,"losses":13,"wins":50},"thinkingmachines/inkling-small":{"draws":9,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":23,"losses":35,"wins":46},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":2}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-opus-4-5":{"draws":25,"losses":27,"wins":18},"claude-opus-4-8":{"draws":18,"losses":17,"wins":15},"claude-opus-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":21},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":9},"google/gemini-3.5-flash-lite":{"draws":17,"losses":7,"wins":16},"google/gemini-3.6-flash":{"draws":13,"losses":23,"wins":9},"google/gemma-4-31b-it":{"draws":5,"losses":10,"wins":11},"gpt-4.1":{"draws":14,"losses":3,"wins":9},"gpt-5":{"draws":7,"losses":6,"wins":9},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":14,"losses":29,"wins":15},"gpt-5.5":{"draws":19,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":26,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":17},"minimax/minimax-m3":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":9},"o3":{"draws":3,"losses":4,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":12},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":27,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"z-ai/glm-5.2":{"draws":30,"losses":17,"wins":7}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":37,"wins":5},"claude-opus-4-5":{"draws":24,"losses":33,"wins":33},"claude-opus-4-8":{"draws":13,"losses":36,"wins":17},"claude-opus-5":{"draws":14,"losses":54,"wins":12},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":27},"deepseek/deepseek-v4-flash":{"draws":17,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":19,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":17,"wins":6},"google/gemini-3.5-flash-lite":{"draws":19,"losses":19,"wins":12},"google/gemini-3.6-flash":{"draws":18,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":3,"losses":13,"wins":22},"gpt-4.1":{"draws":5,"losses":9,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":8,"losses":13,"wins":15},"gpt-5.4-mini":{"draws":14,"losses":15,"wins":29},"gpt-5.4-nano":{"draws":12,"losses":30,"wins":30},"gpt-5.5":{"draws":16,"losses":28,"wins":18},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":32},"inclusionai/ling-3.0-flash":{"draws":20,"losses":9,"wins":19},"meituan/longcat-2.0":{"draws":18,"losses":21,"wins":31},"minimax/minimax-m3":{"draws":14,"losses":18,"wins":30},"mistralai/mistral-medium-3-5":{"draws":5,"losses":13,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":16,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":15,"wins":17},"o3":{"draws":6,"losses":13,"wins":15},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":23},"poolside/laguna-s-2.1":{"draws":18,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":12,"losses":25,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":12,"losses":12,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":17,"wins":13},"x-ai/grok-4.5":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.5":{"draws":42,"losses":58,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":24,"wins":19},"z-ai/glm-5.2":{"draws":14,"losses":19,"wins":17}},"gpt-5.5":{"claude-fable-5":{"draws":8,"losses":24,"wins":22},"claude-opus-4-5":{"draws":31,"losses":24,"wins":33},"claude-opus-4-8":{"draws":19,"losses":22,"wins":35},"claude-opus-5":{"draws":21,"losses":94,"wins":33},"cohere/north-mini-code":{"draws":14,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":28,"losses":1,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":3,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":6,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":26,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":10,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":18,"wins":28},"gpt-5.5":{"draws":16,"losses":16,"wins":16},"gpt-5.6-terra":{"draws":28,"losses":16,"wins":26},"inclusionai/ling-3.0-flash":{"draws":27,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":5,"wins":23},"o3":{"draws":12,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":21,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.7-max":{"draws":17,"losses":11,"wins":16},"qwen/qwen3.7-plus":{"draws":13,"losses":4,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":5,"wins":17},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":22},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":16},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":37,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":10},"z-ai/glm-5.2":{"draws":22,"losses":13,"wins":21}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":32,"losses":39,"wins":23},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":51,"losses":64,"wins":40},"google/gemini-3.5-flash-lite":{"draws":79,"losses":71,"wins":100},"google/gemini-3.6-flash":{"draws":62,"losses":114,"wins":58},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":53,"losses":90,"wins":22},"gpt-5.6-luna":{"draws":52,"losses":29,"wins":29},"gpt-5.6-sol":{"draws":26,"losses":105,"wins":23},"inclusionai/ling-3.0-flash":{"draws":11,"losses":12,"wins":13},"meituan/longcat-2.0":{"draws":21,"losses":21,"wins":32},"meta/muse-spark-1.2":{"draws":29,"losses":54,"wins":31},"moonshotai/kimi-k3":{"draws":48,"losses":64,"wins":32},"o3":{"draws":18,"losses":64,"wins":62},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":21},"poolside/laguna-s-2.1":{"draws":32,"losses":16,"wins":24},"qwen/qwen3.8-max":{"draws":7,"losses":12,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":9},"thinkingmachines/inkling":{"draws":32,"losses":18,"wins":36},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":23,"losses":45,"wins":30},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":0}},"gpt-5.6-sol":{"claude-opus-4-5":{"draws":15,"losses":22,"wins":63},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":28,"losses":26,"wins":124},"google/gemini-3.5-flash-lite":{"draws":32,"losses":21,"wins":201},"google/gemini-3.6-flash":{"draws":31,"losses":63,"wins":146},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":35,"losses":54,"wins":77},"gpt-5.6-luna":{"draws":26,"losses":23,"wins":105},"gpt-5.6-sol":{"draws":16,"losses":52,"wins":52},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":29},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":54},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":71},"moonshotai/kimi-k3":{"draws":29,"losses":23,"wins":76},"o3":{"draws":5,"losses":24,"wins":113},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":43},"poolside/laguna-s-2.1":{"draws":14,"losses":1,"wins":63},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":19},"thinkingmachines/inkling":{"draws":14,"losses":5,"wins":73},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":30,"wins":57},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":8}},"gpt-5.6-terra":{"claude-fable-5":{"draws":7,"losses":48,"wins":5},"claude-opus-4-5":{"draws":42,"losses":29,"wins":37},"claude-opus-4-8":{"draws":22,"losses":27,"wins":17},"claude-opus-5":{"draws":37,"losses":107,"wins":18},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":22,"losses":7,"wins":37},"deepseek/deepseek-v4-pro":{"draws":17,"losses":10,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":17},"google/gemini-3.6-flash":{"draws":21,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":21},"gpt-4.1":{"draws":10,"losses":7,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":26,"losses":11,"wins":23},"gpt-5.4-nano":{"draws":17,"losses":32,"wins":23},"gpt-5.5":{"draws":28,"losses":26,"wins":16},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":13},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":8,"wins":27},"o3":{"draws":5,"losses":16,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":12},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":12,"wins":13},"x-ai/grok-4.5":{"draws":17,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":12,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":45,"losses":16,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":32,"losses":25,"wins":17}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":23,"losses":25,"wins":12},"claude-opus-4-8":{"draws":18,"losses":4,"wins":0},"claude-opus-5":{"draws":12,"losses":22,"wins":2},"claude-sonnet-5":{"draws":11,"losses":21,"wins":4},"cohere/north-mini-code":{"draws":18,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":11},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":69,"losses":75,"wins":30},"google/gemini-3.6-flash":{"draws":90,"losses":75,"wins":29},"google/gemma-4-31b-it":{"draws":12,"losses":19,"wins":5},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":6,"wins":1},"gpt-5":{"draws":6,"losses":6,"wins":8},"gpt-5.4":{"draws":8,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":18,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":9},"gpt-5.5":{"draws":27,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":4},"inclusionai/ling-3.0-flash":{"draws":20,"losses":20,"wins":20},"meituan/longcat-2.0":{"draws":47,"losses":46,"wins":33},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":7},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":41,"wins":11},"nex-agi/nex-n2-pro":{"draws":20,"losses":12,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":5},"o3":{"draws":9,"losses":54,"wins":19},"openai/gpt-oss-120b":{"draws":27,"losses":19,"wins":14},"poolside/laguna-s-2.1":{"draws":52,"losses":35,"wins":15},"qwen/qwen3.7-max":{"draws":21,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":8},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":18,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":41,"losses":38,"wins":33},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":25,"losses":60,"wins":11},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":30,"losses":24,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":8},"z-ai/glm-5.2":{"draws":18,"losses":2,"wins":4}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":38,"losses":54,"wins":27},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":12,"losses":50,"wins":10},"claude-sonnet-5":{"draws":22,"losses":41,"wins":9},"cohere/north-mini-code":{"draws":22,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":19,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":16,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":3},"google/gemini-3.5-flash-lite":{"draws":70,"losses":101,"wins":96},"google/gemini-3.6-flash":{"draws":73,"losses":138,"wins":46},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":13},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":8,"losses":16,"wins":6},"gpt-5.4":{"draws":18,"losses":43,"wins":12},"gpt-5.4-mini":{"draws":21,"losses":17,"wins":10},"gpt-5.4-nano":{"draws":18,"losses":31,"wins":21},"gpt-5.5":{"draws":16,"losses":12,"wins":12},"gpt-5.6-luna":{"draws":21,"losses":32,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":54,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":16,"wins":14},"inclusionai/ling-3.0-flash":{"draws":47,"losses":33,"wins":46},"meituan/longcat-2.0":{"draws":28,"losses":26,"wins":26},"meta/muse-spark-1.2":{"draws":15,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":6,"losses":18,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":69,"wins":17},"nex-agi/nex-n2-pro":{"draws":11,"losses":13,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":18,"wins":9},"o3":{"draws":18,"losses":90,"wins":48},"openai/gpt-oss-120b":{"draws":31,"losses":17,"wins":34},"poolside/laguna-s-2.1":{"draws":60,"losses":39,"wins":39},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-max":{"draws":2,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":7,"losses":29,"wins":24},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":35,"losses":60,"wins":49},"thinkingmachines/inkling-small":{"draws":1,"losses":3,"wins":0},"x-ai/grok-4.5":{"draws":36,"losses":87,"wins":25},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":29,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":18,"wins":14},"z-ai/glm-5.2":{"draws":20,"losses":19,"wins":11}},"meta/muse-spark-1.2":{"claude-opus-4-5":{"draws":15,"losses":20,"wins":29},"claude-opus-5":{"draws":1,"losses":3,"wins":0},"claude-sonnet-5":{"draws":29,"losses":36,"wins":37},"google/gemini-3.5-flash-lite":{"draws":45,"losses":40,"wins":95},"google/gemini-3.6-flash":{"draws":30,"losses":70,"wins":82},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5.4":{"draws":19,"losses":48,"wins":33},"gpt-5.6-luna":{"draws":29,"losses":31,"wins":54},"gpt-5.6-sol":{"draws":13,"losses":71,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":9},"meituan/longcat-2.0":{"draws":15,"losses":18,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":23,"wins":23},"moonshotai/kimi-k3":{"draws":24,"losses":41,"wins":33},"o3":{"draws":6,"losses":49,"wins":41},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":29},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":13},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":41},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":18,"losses":35,"wins":17},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":2}},"minimax/minimax-m3":{"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-opus-4-5":{"draws":11,"losses":28,"wins":7},"claude-opus-4-8":{"draws":11,"losses":19,"wins":4},"claude-opus-5":{"draws":3,"losses":33,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":9},"google/gemini-3.1-flash-lite":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":9,"losses":11,"wins":6},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":11,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":30,"wins":18},"gpt-5.5":{"draws":9,"losses":21,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":18},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":9},"o3":{"draws":5,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.7-max":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":26,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":10,"wins":6}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":20,"wins":0},"claude-opus-4-8":{"draws":2,"losses":18,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":15,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":14,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":9,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":14,"wins":4},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":13},"gpt-5.5":{"draws":2,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":8},"o3":{"draws":3,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":22,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":6}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":56,"losses":41,"wins":57},"claude-opus-4-8":{"draws":8,"losses":9,"wins":13},"claude-opus-5":{"draws":15,"losses":62,"wins":13},"claude-sonnet-5":{"draws":47,"losses":30,"wins":55},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":10,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":121,"losses":64,"wins":167},"google/gemini-3.6-flash":{"draws":99,"losses":128,"wins":115},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":3,"wins":5},"gpt-5.4":{"draws":32,"losses":64,"wins":30},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":19},"gpt-5.5":{"draws":15,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":48,"losses":32,"wins":64},"gpt-5.6-sol":{"draws":29,"losses":76,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":28,"losses":11,"wins":41},"meituan/longcat-2.0":{"draws":44,"losses":17,"wins":69},"meta/muse-spark-1.2":{"draws":24,"losses":33,"wins":41},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":56,"losses":40,"wins":40},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":4},"o3":{"draws":19,"losses":79,"wins":82},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":47},"poolside/laguna-s-2.1":{"draws":57,"losses":13,"wins":62},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":26},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":11},"thinkingmachines/inkling":{"draws":61,"losses":16,"wins":77},"thinkingmachines/inkling-small":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":60,"losses":68,"wins":58},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":4}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":9,"losses":20,"wins":7},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":0,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":8},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":4,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":16},"gpt-5.5":{"draws":8,"losses":15,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":16,"wins":9},"o3":{"draws":2,"losses":11,"wins":3},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":7},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":29,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":14,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":4,"losses":27,"wins":1},"claude-opus-4-5":{"draws":35,"losses":29,"wins":16},"claude-opus-4-8":{"draws":14,"losses":31,"wins":11},"claude-opus-5":{"draws":11,"losses":43,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":36,"losses":24,"wins":22},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":13,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-5":{"draws":17,"losses":15,"wins":6},"gpt-5.4-mini":{"draws":18,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":17,"wins":15},"gpt-5.5":{"draws":22,"losses":23,"wins":5},"gpt-5.6-terra":{"draws":25,"losses":27,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":18},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":3},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":7},"o3":{"draws":18,"losses":30,"wins":10},"openai/gpt-oss-120b":{"draws":21,"losses":11,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":18,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":24},"x-ai/grok-4.5":{"draws":10,"losses":15,"wins":1},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":23,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":3},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":11}},"o3":{"claude-fable-5":{"draws":1,"losses":31,"wins":2},"claude-opus-4-5":{"draws":34,"losses":127,"wins":57},"claude-opus-4-8":{"draws":4,"losses":34,"wins":6},"claude-opus-5":{"draws":2,"losses":78,"wins":6},"claude-sonnet-5":{"draws":12,"losses":67,"wins":59},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":11,"losses":20,"wins":15},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":15},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":8,"losses":10,"wins":18},"google/gemini-3.5-flash-lite":{"draws":64,"losses":132,"wins":241},"google/gemini-3.6-flash":{"draws":64,"losses":211,"wins":133},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":7},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":6},"gpt-5":{"draws":6,"losses":20,"wins":16},"gpt-5.4":{"draws":11,"losses":106,"wins":29},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":13},"gpt-5.5":{"draws":12,"losses":34,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":62,"wins":64},"gpt-5.6-sol":{"draws":5,"losses":113,"wins":24},"gpt-5.6-terra":{"draws":5,"losses":27,"wins":16},"inclusionai/ling-3.0-flash":{"draws":9,"losses":19,"wins":54},"meituan/longcat-2.0":{"draws":18,"losses":48,"wins":90},"meta/muse-spark-1.2":{"draws":6,"losses":41,"wins":49},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":82,"wins":79},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":30},"o3":{"draws":28,"losses":132,"wins":132},"openai/gpt-oss-120b":{"draws":23,"losses":14,"wins":64},"poolside/laguna-s-2.1":{"draws":35,"losses":34,"wins":53},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":1,"losses":12,"wins":3},"stepfun/step-3.7-flash":{"draws":15,"losses":28,"wins":59},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":12},"thinkingmachines/inkling":{"draws":37,"losses":38,"wins":92},"thinkingmachines/inkling-small":{"draws":4,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":93,"wins":49},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":14,"wins":8}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":4,"losses":19,"wins":1},"claude-opus-4-5":{"draws":28,"losses":68,"wins":10},"claude-opus-4-8":{"draws":13,"losses":23,"wins":6},"claude-opus-5":{"draws":4,"losses":23,"wins":3},"claude-sonnet-5":{"draws":10,"losses":33,"wins":1},"cohere/north-mini-code":{"draws":16,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":22},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":41,"losses":85,"wins":30},"google/gemini-3.6-flash":{"draws":28,"losses":95,"wins":6},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":14,"losses":6,"wins":2},"gpt-5.4":{"draws":6,"losses":34,"wins":2},"gpt-5.4-mini":{"draws":17,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":23,"wins":13},"gpt-5.5":{"draws":21,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":21,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":43,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":5},"inclusionai/ling-3.0-flash":{"draws":27,"losses":14,"wins":19},"meituan/longcat-2.0":{"draws":31,"losses":34,"wins":17},"meta/muse-spark-1.2":{"draws":4,"losses":29,"wins":3},"minimax/minimax-m3":{"draws":9,"losses":13,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":47,"wins":5},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":8,"wins":11},"o3":{"draws":23,"losses":64,"wins":14},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":24,"losses":25,"wins":17},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":13},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":7},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":3},"thinkingmachines/inkling":{"draws":23,"losses":42,"wins":23},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":17,"losses":45,"wins":8},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":36,"losses":26,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":1},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":9}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":4,"wins":6},"claude-opus-4-5":{"draws":57,"losses":54,"wins":7},"claude-opus-4-8":{"draws":12,"losses":23,"wins":5},"claude-opus-5":{"draws":8,"losses":72,"wins":8},"claude-sonnet-5":{"draws":28,"losses":41,"wins":5},"cohere/north-mini-code":{"draws":21,"losses":15,"wins":2},"deepseek/deepseek-v4-flash":{"draws":23,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":117,"losses":72,"wins":81},"google/gemini-3.6-flash":{"draws":105,"losses":108,"wins":41},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":5},"gpt-5":{"draws":11,"losses":6,"wins":9},"gpt-5.4":{"draws":28,"losses":37,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":18,"losses":14,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":14},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":16},"gpt-5.6-sol":{"draws":14,"losses":63,"wins":1},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"inclusionai/ling-3.0-flash":{"draws":52,"losses":15,"wins":35},"meituan/longcat-2.0":{"draws":60,"losses":39,"wins":39},"meta/muse-spark-1.2":{"draws":17,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":14},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":57,"losses":62,"wins":13},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":9},"o3":{"draws":35,"losses":53,"wins":34},"openai/gpt-oss-120b":{"draws":24,"losses":17,"wins":25},"poolside/laguna-s-2.1":{"draws":52,"losses":30,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":15,"losses":3,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":20,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":55,"losses":38,"wins":55},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":45,"losses":81,"wins":24},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":19,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":31,"losses":16,"wins":13}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":3,"losses":17,"wins":4},"claude-opus-4-5":{"draws":22,"losses":28,"wins":14},"claude-opus-4-8":{"draws":12,"losses":17,"wins":11},"claude-opus-5":{"draws":12,"losses":55,"wins":7},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":11,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":9},"google/gemini-3.5-flash-lite":{"draws":7,"losses":7,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":14},"gpt-4.1":{"draws":7,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":17,"losses":15,"wins":22},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":18,"losses":4,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"o3":{"draws":10,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":9}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":23,"losses":18,"wins":11},"claude-opus-4-8":{"draws":12,"losses":20,"wins":6},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":12,"losses":16,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":13,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":12,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":12,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":25},"gpt-5.5":{"draws":13,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":13},"o3":{"draws":3,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":8,"wins":13},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":25,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":6}},"qwen/qwen3.8-max":{"claude-opus-4-5":{"draws":5,"losses":2,"wins":4},"claude-sonnet-5":{"draws":0,"losses":3,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":1,"losses":4,"wins":11},"gpt-5.4":{"draws":9,"losses":12,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":2},"o3":{"draws":1,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":32,"losses":32,"wins":32},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling-small":{"draws":49,"losses":31,"wins":53},"x-ai/grok-4.5":{"draws":9,"losses":6,"wins":6}},"stealth/ox-alpha":{"stealth/ox-alpha":{"draws":224,"losses":369,"wins":369}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":3,"losses":19,"wins":0},"claude-opus-4-5":{"draws":16,"losses":46,"wins":14},"claude-opus-4-8":{"draws":7,"losses":21,"wins":8},"claude-opus-5":{"draws":5,"losses":28,"wins":1},"claude-sonnet-5":{"draws":3,"losses":12,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":8,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":3},"google/gemini-3.5-flash-lite":{"draws":21,"losses":36,"wins":41},"google/gemini-3.6-flash":{"draws":11,"losses":53,"wins":9},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":13},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":8,"losses":14,"wins":0},"gpt-5.4":{"draws":3,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":10},"gpt-5.5":{"draws":6,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":9},"gpt-5.6-sol":{"draws":1,"losses":19,"wins":4},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":8,"wins":18},"meituan/longcat-2.0":{"draws":7,"losses":24,"wins":29},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":26,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":10},"o3":{"draws":15,"losses":59,"wins":28},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":14},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":9},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":33},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":4}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":20,"wins":5},"claude-opus-4-5":{"draws":17,"losses":19,"wins":8},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":48,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":11,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":3},"gpt-5":{"draws":5,"losses":9,"wins":8},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":12},"gpt-5.5":{"draws":24,"losses":17,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":11,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":14},"o3":{"draws":10,"losses":12,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":11,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":20,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":19,"losses":8,"wins":9}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":4,"losses":10,"wins":0},"claude-opus-4-5":{"draws":44,"losses":75,"wins":17},"claude-opus-4-8":{"draws":8,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":56,"wins":11},"claude-sonnet-5":{"draws":29,"losses":48,"wins":11},"cohere/north-mini-code":{"draws":9,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":21,"losses":20,"wins":17},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":4},"google/gemini-3.1-flash-lite":{"draws":11,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":18,"wins":4},"google/gemini-3.5-flash-lite":{"draws":109,"losses":115,"wins":80},"google/gemini-3.6-flash":{"draws":110,"losses":141,"wins":43},"google/gemma-4-31b-it":{"draws":4,"losses":14,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":12,"wins":0},"gpt-5":{"draws":12,"losses":13,"wins":5},"gpt-5.4":{"draws":19,"losses":50,"wins":13},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":17},"gpt-5.5":{"draws":15,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":32,"losses":36,"wins":18},"gpt-5.6-sol":{"draws":14,"losses":73,"wins":5},"gpt-5.6-terra":{"draws":21,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":41,"losses":33,"wins":38},"meituan/longcat-2.0":{"draws":35,"losses":49,"wins":60},"meta/muse-spark-1.2":{"draws":20,"losses":41,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":14,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":61,"losses":77,"wins":16},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":24,"wins":15},"o3":{"draws":37,"losses":92,"wins":38},"openai/gpt-oss-120b":{"draws":23,"losses":23,"wins":42},"poolside/laguna-s-2.1":{"draws":55,"losses":55,"wins":38},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":15,"losses":33,"wins":20},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":24,"losses":28,"wins":28},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":45,"losses":67,"wins":22},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":42,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":12,"losses":23,"wins":11}},"thinkingmachines/inkling-small":{"claude-opus-4-5":{"draws":3,"losses":4,"wins":2},"claude-sonnet-5":{"draws":4,"losses":10,"wins":0},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":3,"wins":5},"gpt-5.4":{"draws":9,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":1},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":2},"o3":{"draws":4,"losses":8,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":49,"losses":53,"wins":31},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling-small":{"draws":42,"losses":31,"wins":31},"x-ai/grok-4.5":{"draws":5,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":7,"losses":30,"wins":7},"claude-opus-4-5":{"draws":52,"losses":44,"wins":66},"claude-opus-4-8":{"draws":15,"losses":19,"wins":20},"claude-opus-5":{"draws":17,"losses":85,"wins":22},"claude-sonnet-5":{"draws":36,"losses":18,"wins":46},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":6,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":17},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash-lite":{"draws":72,"losses":62,"wins":162},"google/gemini-3.6-flash":{"draws":58,"losses":132,"wins":125},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":10},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":6,"wins":18},"gpt-5.4":{"draws":23,"losses":46,"wins":35},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":14},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":23},"gpt-5.5":{"draws":14,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":23,"losses":30,"wins":45},"gpt-5.6-sol":{"draws":11,"losses":57,"wins":30},"gpt-5.6-terra":{"draws":17,"losses":16,"wins":23},"inclusionai/ling-3.0-flash":{"draws":25,"losses":11,"wins":60},"meituan/longcat-2.0":{"draws":36,"losses":25,"wins":87},"meta/muse-spark-1.2":{"draws":18,"losses":17,"wins":35},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":60,"losses":58,"wins":68},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":15},"o3":{"draws":14,"losses":49,"wins":93},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":45},"poolside/laguna-s-2.1":{"draws":45,"losses":24,"wins":81},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":13},"qwen/qwen3.8-max":{"draws":9,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":27},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":20},"thinkingmachines/inkling":{"draws":45,"losses":22,"wins":67},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":30,"losses":33,"wins":33},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":10},"z-ai/glm-5.2":{"draws":7,"losses":11,"wins":4}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":5,"losses":41,"wins":2},"claude-opus-4-5":{"draws":62,"losses":55,"wins":33},"claude-opus-4-8":{"draws":38,"losses":46,"wins":12},"claude-opus-5":{"draws":9,"losses":50,"wins":3},"cohere/north-mini-code":{"draws":27,"losses":15,"wins":24},"deepseek/deepseek-v4-flash":{"draws":48,"losses":31,"wins":49},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":11},"google/gemini-3.1-flash-lite":{"draws":35,"losses":25,"wins":42},"google/gemini-3.5-flash":{"draws":28,"losses":25,"wins":9},"google/gemini-3.5-flash-lite":{"draws":11,"losses":12,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":17,"losses":27,"wins":26},"gpt-4.1":{"draws":13,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":31,"losses":23,"wins":18},"gpt-5.4-mini":{"draws":39,"losses":28,"wins":27},"gpt-5.4-nano":{"draws":42,"losses":60,"wins":58},"gpt-5.5":{"draws":37,"losses":33,"wins":10},"gpt-5.6-terra":{"draws":45,"losses":35,"wins":16},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":24},"meituan/longcat-2.0":{"draws":23,"losses":32,"wins":29},"minimax/minimax-m3":{"draws":28,"losses":30,"wins":26},"mistralai/mistral-medium-3-5":{"draws":10,"losses":14,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":22,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":18,"losses":19,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":31,"wins":23},"o3":{"draws":12,"losses":24,"wins":4},"openai/gpt-oss-120b":{"draws":36,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":23,"losses":24,"wins":19},"qwen/qwen3.7-max":{"draws":28,"losses":31,"wins":19},"qwen/qwen3.7-plus":{"draws":23,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":28,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":42},"x-ai/grok-4.5":{"draws":16,"losses":23,"wins":5},"x-ai/grok-build-0.1":{"draws":24,"losses":18,"wins":10},"xiaomi/mimo-v2.5":{"draws":76,"losses":56,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":32,"losses":46,"wins":26}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":7,"losses":21,"wins":18},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":8,"losses":35,"wins":1},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":18},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":2,"losses":11,"wins":5},"gpt-5":{"draws":5,"losses":8,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":24},"gpt-5.5":{"draws":8,"losses":10,"wins":8},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":11},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":10},"o3":{"draws":4,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":16},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":30},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":10}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":24,"losses":46,"wins":42},"claude-opus-4-8":{"draws":23,"losses":25,"wins":16},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-sonnet-5":{"draws":2,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":32,"losses":12,"wins":34},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":21},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":11},"google/gemini-3.5-flash-lite":{"draws":14,"losses":18,"wins":14},"google/gemini-3.6-flash":{"draws":15,"losses":19,"wins":8},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":3},"gpt-4.1":{"draws":12,"losses":8,"wins":12},"gpt-5":{"draws":14,"losses":19,"wins":17},"gpt-5.4":{"draws":8,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":30,"losses":7,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":19},"gpt-5.5":{"draws":22,"losses":21,"wins":13},"gpt-5.6-luna":{"draws":7,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":32,"losses":17,"wins":25},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":20,"losses":11,"wins":19},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":7},"minimax/minimax-m3":{"draws":14,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":8},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":11},"o3":{"draws":6,"losses":8,"wins":14},"openai/gpt-oss-120b":{"draws":18,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":31,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":14,"losses":9,"wins":17},"qwen/qwen3.7-plus":{"draws":13,"losses":6,"wins":15},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":19,"losses":9,"wins":8},"thinkingmachines/inkling":{"draws":12,"losses":11,"wins":23},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":26,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":12},"z-ai/glm-5.2":{"draws":30,"losses":23,"wins":23}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":2,"wins":10},"claude-opus-4-5":{"draws":4,"losses":4,"wins":24},"claude-opus-4-8":{"draws":3,"losses":10,"wins":17},"claude-opus-5":{"draws":17,"losses":30,"wins":43},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":19},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":19},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":21},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":7,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":21},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":16},"gpt-5.5":{"draws":5,"losses":11,"wins":14},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":16},"o3":{"draws":0,"losses":2,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":11},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":15},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":20},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":13}},"claude-opus-4-5":{"claude-fable-5":{"draws":0,"losses":15,"wins":1},"claude-opus-4-5":{"draws":10,"losses":19,"wins":9},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":7,"losses":70,"wins":3},"claude-sonnet-5":{"draws":25,"losses":10,"wins":23},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":3},"google/gemini-3.5-flash-lite":{"draws":50,"losses":28,"wins":56},"google/gemini-3.6-flash":{"draws":34,"losses":57,"wins":35},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":5,"wins":4},"gpt-5.4":{"draws":14,"losses":23,"wins":9},"gpt-5.5":{"draws":2,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":20},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":12},"gpt-5.6-terra":{"draws":2,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":11,"wins":18},"meta/muse-spark-1.2":{"draws":7,"losses":15,"wins":12},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":23,"losses":31,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":8},"o3":{"draws":17,"losses":19,"wins":58},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":24},"poolside/laguna-s-2.1":{"draws":27,"losses":1,"wins":22},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":19},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":16,"losses":2,"wins":30},"thinkingmachines/inkling-small":{"draws":3,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":22,"losses":27,"wins":15},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":1}},"claude-opus-4-8":{"claude-fable-5":{"draws":4,"losses":12,"wins":18},"claude-opus-4-5":{"draws":3,"losses":8,"wins":25},"claude-opus-4-8":{"draws":0,"losses":3,"wins":5},"claude-opus-5":{"draws":14,"losses":33,"wins":23},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":5,"wins":16},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":8},"gpt-5.5":{"draws":4,"losses":14,"wins":10},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":15},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":18},"o3":{"draws":0,"losses":5,"wins":25},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":6,"wins":11}},"claude-opus-5":{"claude-fable-5":{"draws":7,"losses":19,"wins":26},"claude-opus-4-5":{"draws":3,"losses":6,"wins":53},"claude-opus-4-8":{"draws":2,"losses":12,"wins":16},"claude-opus-5":{"draws":14,"losses":51,"wins":81},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":13},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":23},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":34},"google/gemini-3.6-flash":{"draws":4,"losses":8,"wins":34},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":0,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":3},"gpt-5.5":{"draws":0,"losses":7,"wins":23},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":15},"o3":{"draws":0,"losses":3,"wins":41},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":19},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":23},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"claude-sonnet-5":{"claude-opus-4-5":{"draws":14,"losses":17,"wins":11},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":9,"losses":5,"wins":22},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":13,"losses":28,"wins":35},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":14,"losses":21,"wins":15},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":24},"gpt-5.6-sol":{"draws":11,"losses":38,"wins":11},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":6,"wins":19},"moonshotai/kimi-k3":{"draws":16,"losses":14,"wins":14},"o3":{"draws":1,"losses":17,"wins":28},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":17},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":18},"x-ai/grok-4.5":{"draws":15,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":3}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":0,"losses":12,"wins":2},"claude-opus-4-5":{"draws":9,"losses":11,"wins":8},"claude-opus-4-8":{"draws":0,"losses":9,"wins":5},"claude-opus-5":{"draws":3,"losses":15,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":3},"gpt-5.5":{"draws":3,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":8},"o3":{"draws":5,"losses":11,"wins":18},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":6}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":2},"claude-opus-4-5":{"draws":9,"losses":12,"wins":3},"claude-opus-4-8":{"draws":5,"losses":13,"wins":6},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":18},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":3,"losses":4,"wins":11},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":0},"gpt-5.5":{"draws":8,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":12},"o3":{"draws":7,"losses":13,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":7},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":8}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":6,"losses":14,"wins":2},"claude-opus-4-8":{"draws":3,"losses":13,"wins":2},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":3},"gpt-5.5":{"draws":4,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":3},"o3":{"draws":4,"losses":16,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":3}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":2,"losses":16,"wins":4},"claude-opus-4-5":{"draws":8,"losses":5,"wins":11},"claude-opus-4-8":{"draws":1,"losses":6,"wins":7},"claude-opus-5":{"draws":4,"losses":32,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":5,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":8,"losses":12,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":12},"o3":{"draws":7,"losses":12,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":9}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":24,"losses":35,"wins":23},"claude-opus-4-8":{"draws":0,"losses":12,"wins":2},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"claude-sonnet-5":{"draws":23,"losses":34,"wins":21},"deepseek/deepseek-v4-flash":{"draws":4,"losses":8,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":51,"losses":67,"wins":74},"google/gemini-3.6-flash":{"draws":48,"losses":105,"wins":47},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":10,"losses":6,"wins":2},"gpt-5.4":{"draws":16,"losses":54,"wins":16},"gpt-5.5":{"draws":6,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":24,"losses":27,"wins":27},"gpt-5.6-sol":{"draws":11,"losses":63,"wins":6},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":0},"inclusionai/ling-3.0-flash":{"draws":11,"losses":11,"wins":18},"meituan/longcat-2.0":{"draws":18,"losses":24,"wins":28},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":9},"moonshotai/kimi-k3":{"draws":31,"losses":50,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":6},"o3":{"draws":11,"losses":85,"wins":54},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":40},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":16,"wins":14},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":32,"losses":20,"wins":36},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":17,"losses":39,"wins":24},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":7}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":15,"wins":5},"claude-opus-4-5":{"draws":12,"losses":19,"wins":47},"claude-opus-4-8":{"draws":2,"losses":10,"wins":10},"claude-opus-5":{"draws":10,"losses":39,"wins":11},"claude-sonnet-5":{"draws":6,"losses":17,"wins":49},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":7},"google/gemini-3.5-flash-lite":{"draws":41,"losses":20,"wins":127},"google/gemini-3.6-flash":{"draws":27,"losses":50,"wins":95},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":7,"wins":12},"gpt-5.4":{"draws":9,"losses":38,"wins":29},"gpt-5.5":{"draws":4,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":42},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":34},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":14,"losses":3,"wins":17},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":46},"meta/muse-spark-1.2":{"draws":4,"losses":19,"wins":31},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":15,"wins":66},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":11},"o3":{"draws":18,"losses":27,"wins":93},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":41},"poolside/laguna-s-2.1":{"draws":17,"losses":2,"wins":35},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":1},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":23},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":12},"thinkingmachines/inkling":{"draws":24,"losses":13,"wins":43},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":30,"wins":55},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":6}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":20,"wins":1},"claude-opus-4-5":{"draws":19,"losses":9,"wins":10},"claude-opus-4-8":{"draws":4,"losses":15,"wins":5},"claude-opus-5":{"draws":3,"losses":37,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":7},"gpt-5.5":{"draws":8,"losses":12,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":10},"o3":{"draws":3,"losses":12,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":5,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":11,"wins":13}},"gpt-5.4":{"claude-opus-4-5":{"draws":3,"losses":4,"wins":19},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":6,"losses":7,"wins":31},"google/gemini-3.5-flash-lite":{"draws":10,"losses":7,"wins":65},"google/gemini-3.6-flash":{"draws":11,"losses":11,"wins":56},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":9,"losses":2,"wins":32},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":40},"gpt-5.6-sol":{"draws":11,"losses":16,"wins":25},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":19},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":22},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":30},"o3":{"draws":0,"losses":4,"wins":44},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":19},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":22},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":2}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":11,"wins":16},"claude-opus-4-5":{"draws":6,"losses":5,"wins":17},"claude-opus-4-8":{"draws":2,"losses":3,"wins":19},"claude-opus-5":{"draws":1,"losses":38,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":11},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":3,"wins":14},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":10},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":11},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":11},"o3":{"draws":1,"losses":2,"wins":27},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":12}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":11,"losses":7,"wins":12},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":14,"losses":13,"wins":23},"google/gemini-3.5-flash-lite":{"draws":30,"losses":11,"wins":43},"google/gemini-3.6-flash":{"draws":19,"losses":24,"wins":33},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":20,"losses":23,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":4,"wins":15},"gpt-5.6-sol":{"draws":11,"losses":27,"wins":14},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":13,"wins":18},"moonshotai/kimi-k3":{"draws":18,"losses":13,"wins":19},"o3":{"draws":7,"losses":9,"wins":32},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":11,"losses":3,"wins":10},"qwen/qwen3.8-max":{"draws":1,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":17},"x-ai/grok-4.5":{"draws":5,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":0}},"gpt-5.6-sol":{"claude-opus-4-5":{"draws":1,"losses":9,"wins":24},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":6,"wins":54},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":79},"google/gemini-3.6-flash":{"draws":5,"losses":13,"wins":60},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":12,"wins":36},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":43},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":33},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":21},"meta/muse-spark-1.2":{"draws":1,"losses":2,"wins":31},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":36},"o3":{"draws":0,"losses":8,"wins":42},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":24},"qwen/qwen3.8-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":27},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":29},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":6}},"gpt-5.6-terra":{"claude-fable-5":{"draws":4,"losses":30,"wins":4},"claude-opus-4-5":{"draws":11,"losses":8,"wins":17},"claude-opus-4-8":{"draws":1,"losses":16,"wins":5},"claude-opus-5":{"draws":12,"losses":52,"wins":10},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":5,"wins":16},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":6},"gpt-5.5":{"draws":5,"losses":11,"wins":10},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":13},"o3":{"draws":1,"losses":9,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":11}},"meta/muse-spark-1.2":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":4},"claude-sonnet-5":{"draws":1,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":1,"losses":8,"wins":13},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":0,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":0,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"meta/muse-spark-1.2":{"draws":1,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":5},"o3":{"draws":1,"losses":5,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":1,"losses":3,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":1}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":8,"wins":0},"claude-opus-4-8":{"draws":0,"losses":10,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":15,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":7},"gpt-5.5":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":9,"wins":5},"o3":{"draws":0,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":15,"losses":5,"wins":14},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":5,"losses":20,"wins":1},"claude-sonnet-5":{"draws":13,"losses":4,"wins":15},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":3},"google/gemini-3.5-flash-lite":{"draws":29,"losses":10,"wins":41},"google/gemini-3.6-flash":{"draws":16,"losses":25,"wins":33},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":1,"wins":5},"gpt-5.4":{"draws":10,"losses":7,"wins":11},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":13},"meituan/longcat-2.0":{"draws":9,"losses":1,"wins":18},"meta/muse-spark-1.2":{"draws":4,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":3},"o3":{"draws":0,"losses":12,"wins":26},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":5,"wins":13},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":4,"wins":16},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":17,"wins":15},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":2}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":3,"losses":15,"wins":0},"claude-opus-4-5":{"draws":25,"losses":18,"wins":5},"claude-opus-4-8":{"draws":8,"losses":18,"wins":4},"claude-opus-5":{"draws":1,"losses":13,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":22,"losses":9,"wins":13},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":4},"gpt-5.5":{"draws":7,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":21},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":21,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":5,"losses":6,"wins":5}},"o3":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":21,"losses":95,"wins":42},"claude-opus-4-8":{"draws":0,"losses":25,"wins":3},"claude-opus-5":{"draws":0,"losses":51,"wins":3},"claude-sonnet-5":{"draws":9,"losses":49,"wins":56},"deepseek/deepseek-v4-flash":{"draws":4,"losses":15,"wins":9},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":13},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":11},"google/gemini-3.5-flash-lite":{"draws":41,"losses":86,"wins":215},"google/gemini-3.6-flash":{"draws":36,"losses":168,"wins":116},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":3,"losses":13,"wins":12},"gpt-5.4":{"draws":8,"losses":89,"wins":25},"gpt-5.5":{"draws":1,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":46,"wins":58},"gpt-5.6-sol":{"draws":5,"losses":87,"wins":22},"gpt-5.6-terra":{"draws":0,"losses":19,"wins":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":10,"wins":36},"meituan/longcat-2.0":{"draws":6,"losses":29,"wins":65},"meta/muse-spark-1.2":{"draws":6,"losses":27,"wins":47},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":20},"moonshotai/kimi-k3":{"draws":14,"losses":57,"wins":73},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"o3":{"draws":18,"losses":102,"wins":124},"openai/gpt-oss-120b":{"draws":13,"losses":11,"wins":53},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"wins":37},"qwen/qwen3.8-max":{"draws":1,"losses":12,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":20,"wins":55},"tencent/hy3-preview":{"draws":3,"losses":13,"wins":10},"thinkingmachines/inkling":{"draws":18,"losses":25,"wins":80},"thinkingmachines/inkling-small":{"draws":4,"losses":6,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":70,"wins":42},"z-ai/glm-5.2":{"draws":2,"losses":6,"wins":0}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":10,"wins":1},"claude-opus-4-5":{"draws":9,"losses":4,"wins":5},"claude-opus-4-8":{"draws":6,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":13,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":11,"losses":3,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":7,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":2},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":5},"o3":{"draws":4,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":3}},"qwen/qwen3.8-max":{"claude-opus-4-5":{"draws":3,"losses":0,"wins":3},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":3},"gpt-5.4":{"draws":3,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":1,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":1},"o3":{"draws":0,"losses":0,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":18},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":1}},"stealth/ox-alpha":{"stealth/ox-alpha":{"draws":61,"losses":81,"wins":191}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":3,"losses":15,"wins":4},"claude-opus-4-8":{"draws":2,"losses":10,"wins":4},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":4,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":6},"gpt-5.5":{"draws":0,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":9},"o3":{"draws":5,"losses":19,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":17},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":17,"wins":1},"claude-opus-4-5":{"draws":11,"losses":12,"wins":5},"claude-opus-4-8":{"draws":3,"losses":10,"wins":7},"claude-opus-5":{"draws":3,"losses":35,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":9,"wins":8},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":12,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":12},"o3":{"draws":5,"losses":12,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":8,"wins":8},"z-ai/glm-5.2":{"draws":7,"losses":3,"wins":6}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":15,"losses":36,"wins":5},"claude-opus-4-8":{"draws":2,"losses":8,"wins":0},"claude-opus-5":{"draws":1,"losses":17,"wins":2},"claude-sonnet-5":{"draws":15,"losses":32,"wins":7},"deepseek/deepseek-v4-flash":{"draws":5,"losses":7,"wins":0},"deepseek/deepseek-v4-pro":{"draws":6,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":57,"losses":63,"wins":50},"google/gemini-3.6-flash":{"draws":42,"losses":84,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":12,"losses":32,"wins":8},"gpt-5.5":{"draws":1,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":22,"losses":22,"wins":10},"gpt-5.6-sol":{"draws":12,"losses":44,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":29},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":38,"losses":36,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":3},"o3":{"draws":18,"losses":64,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":24},"poolside/laguna-s-2.1":{"draws":25,"losses":25,"wins":12},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":8,"losses":11,"wins":11},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":17,"wins":8},"x-ai/grok-4.5":{"draws":21,"losses":37,"wins":8},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":0}},"thinkingmachines/inkling-small":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":0},"gpt-5.4":{"draws":1,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":2},"o3":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-max":{"draws":14,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":2}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":2,"losses":12,"wins":4},"claude-opus-4-5":{"draws":19,"losses":11,"wins":30},"claude-opus-4-8":{"draws":6,"losses":7,"wins":3},"claude-opus-5":{"draws":6,"losses":29,"wins":9},"claude-sonnet-5":{"draws":11,"losses":11,"wins":28},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":2},"google/gemini-3.5-flash-lite":{"draws":15,"losses":34,"wins":79},"google/gemini-3.6-flash":{"draws":16,"losses":53,"wins":71},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4":{"draws":11,"losses":17,"wins":24},"gpt-5.5":{"draws":3,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":27},"gpt-5.6-sol":{"draws":6,"losses":25,"wins":19},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":23},"meituan/longcat-2.0":{"draws":17,"losses":6,"wins":35},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":22},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":21,"losses":20,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":8},"o3":{"draws":6,"losses":13,"wins":53},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":18},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":37},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":16},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":13},"thinkingmachines/inkling":{"draws":20,"losses":9,"wins":25},"x-ai/grok-4.5":{"draws":15,"losses":8,"wins":21},"z-ai/glm-5.2":{"draws":0,"losses":6,"wins":0}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":12,"losses":5,"wins":3},"claude-opus-4-8":{"draws":7,"losses":2,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":3},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":2},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":4}},"z-ai/glm-5.2":{"claude-opus-4-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5":{"draws":2,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":15,"wins":13},"google/gemini-3.6-flash":{"draws":8,"losses":17,"wins":7},"gpt-5.4":{"draws":8,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":8},"o3":{"draws":2,"losses":0,"wins":6},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":14,"losses":0,"wins":6},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":8},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":8},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":2}}},"medium":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":3,"losses":4,"wins":21},"claude-opus-4-8":{"draws":3,"losses":16,"wins":11},"claude-opus-5":{"draws":8,"losses":28,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":1,"losses":2,"wins":13},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":9},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":21},"gpt-5.5":{"draws":3,"losses":11,"wins":10},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":11},"o3":{"draws":1,"losses":0,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":12},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":8}},"claude-opus-4-5":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":12,"losses":9,"wins":19},"claude-opus-4-8":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5":{"draws":11,"losses":13,"wins":30},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":5},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":66},"google/gemini-3.6-flash":{"draws":25,"losses":47,"wins":36},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":4,"wins":7},"gpt-5.4":{"draws":8,"losses":22,"wins":10},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":12},"gpt-5.5":{"draws":6,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":14,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":11,"losses":8,"wins":24},"meta/muse-spark-1.2":{"draws":8,"losses":14,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":26,"losses":20,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":4},"o3":{"draws":11,"losses":32,"wins":57},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":18,"losses":2,"wins":22},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":7},"qwen/qwen3.8-max":{"draws":2,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":24},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":21,"losses":28,"wins":21},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":3}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":10,"wins":6},"claude-opus-4-5":{"draws":6,"losses":11,"wins":13},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":3,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":14},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":4,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":10}},"claude-opus-5":{"claude-fable-5":{"draws":10,"losses":21,"wins":17},"claude-opus-4-5":{"draws":15,"losses":6,"wins":73},"claude-opus-4-8":{"draws":8,"losses":9,"wins":25},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":21},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":19},"google/gemini-3.6-flash":{"draws":3,"losses":11,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":19},"gpt-5":{"draws":3,"losses":2,"wins":17},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":19},"gpt-5.5":{"draws":7,"losses":16,"wins":35},"gpt-5.6-terra":{"draws":17,"losses":5,"wins":44},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":5,"losses":1,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":16},"o3":{"draws":0,"losses":0,"wins":14},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":31},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":24},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":13},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":32}},"claude-sonnet-5":{"claude-opus-4-5":{"draws":8,"losses":19,"wins":7},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":10,"losses":16,"wins":8},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":35},"google/gemini-3.6-flash":{"draws":25,"losses":34,"wins":17},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":15,"losses":26,"wins":7},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":43,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":3,"wins":12},"meta/muse-spark-1.2":{"draws":9,"losses":15,"wins":10},"moonshotai/kimi-k3":{"draws":15,"losses":21,"wins":8},"o3":{"draws":7,"losses":21,"wins":18},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":11},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":15},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":1,"losses":3,"wins":0}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":4,"losses":11,"wins":3},"claude-opus-4-8":{"draws":5,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":13,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":5},"gpt-5.5":{"draws":7,"losses":7,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":2,"losses":7,"wins":1},"claude-opus-4-5":{"draws":9,"losses":6,"wins":3},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":21,"wins":0},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":13},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":19,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":8},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-5":{"draws":7,"losses":6,"wins":1},"gpt-5.4-mini":{"draws":10,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":3,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":3},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":15,"wins":3},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":20,"wins":4}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":13,"wins":0},"claude-opus-4-5":{"draws":6,"losses":20,"wins":0},"claude-opus-4-8":{"draws":6,"losses":10,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":8,"wins":9},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":9},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":6,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":1},"xiaomi/mimo-v2.5":{"draws":17,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":4}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-5":{"draws":10,"losses":11,"wins":11},"claude-opus-4-8":{"draws":12,"losses":5,"wins":11},"claude-opus-5":{"draws":7,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":4,"losses":6,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":15},"gpt-5.5":{"draws":3,"losses":9,"wins":14},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":8},"o3":{"draws":1,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":7}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":32,"losses":51,"wins":5},"claude-opus-4-8":{"draws":11,"losses":7,"wins":0},"claude-opus-5":{"draws":6,"losses":18,"wins":2},"claude-sonnet-5":{"draws":22,"losses":46,"wins":12},"cohere/north-mini-code":{"draws":12,"losses":10,"wins":0},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash-lite":{"draws":74,"losses":69,"wins":61},"google/gemini-3.6-flash":{"draws":78,"losses":104,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":1},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":4},"gpt-5":{"draws":9,"losses":4,"wins":5},"gpt-5.4":{"draws":26,"losses":53,"wins":7},"gpt-5.4-mini":{"draws":11,"losses":13,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":10},"gpt-5.5":{"draws":13,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":25,"losses":41,"wins":12},"gpt-5.6-sol":{"draws":11,"losses":65,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":0},"inclusionai/ling-3.0-flash":{"draws":14,"losses":15,"wins":15},"meituan/longcat-2.0":{"draws":23,"losses":43,"wins":17},"meta/muse-spark-1.2":{"draws":14,"losses":38,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":39,"losses":54,"wins":11},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":2},"o3":{"draws":30,"losses":105,"wins":23},"openai/gpt-oss-120b":{"draws":21,"losses":17,"wins":24},"poolside/laguna-s-2.1":{"draws":40,"losses":32,"wins":16},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":28,"losses":25,"wins":33},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":27,"losses":57,"wins":6},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":15,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":10,"losses":7,"wins":7}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":0,"losses":7,"wins":9},"claude-opus-4-5":{"draws":19,"losses":18,"wins":41},"claude-opus-4-8":{"draws":10,"losses":4,"wins":14},"claude-opus-5":{"draws":3,"losses":29,"wins":14},"claude-sonnet-5":{"draws":16,"losses":16,"wins":28},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":45,"losses":27,"wins":107},"google/gemini-3.6-flash":{"draws":32,"losses":46,"wins":70},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":6},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":9},"gpt-5.4":{"draws":13,"losses":31,"wins":24},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":14},"gpt-5.5":{"draws":9,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":37},"gpt-5.6-sol":{"draws":9,"losses":34,"wins":21},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":14},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":23},"meituan/longcat-2.0":{"draws":21,"losses":8,"wins":43},"meta/muse-spark-1.2":{"draws":8,"losses":17,"wins":27},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":23,"losses":30,"wins":47},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":10},"o3":{"draws":16,"losses":21,"wins":81},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":36},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":19},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":20,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":2,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":21,"losses":31,"wins":40},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":4,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":7}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":4,"losses":5,"wins":11},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":6,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":10,"wins":5},"gpt-5.5":{"draws":2,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":4,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":6,"losses":12,"wins":10},"claude-opus-4-8":{"draws":7,"losses":11,"wins":8},"claude-opus-5":{"draws":7,"losses":14,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":6},"gpt-5.5":{"draws":3,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":5},"o3":{"draws":3,"losses":4,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":6}},"gpt-5.4":{"claude-opus-4-5":{"draws":10,"losses":5,"wins":15},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":21,"losses":9,"wins":22},"google/gemini-3.5-flash-lite":{"draws":29,"losses":14,"wins":49},"google/gemini-3.6-flash":{"draws":23,"losses":26,"wins":35},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":16,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":22,"losses":8,"wins":28},"gpt-5.6-sol":{"draws":10,"losses":33,"wins":17},"inclusionai/ling-3.0-flash":{"draws":3,"losses":7,"wins":8},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":15},"meta/muse-spark-1.2":{"draws":10,"losses":7,"wins":17},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":19},"o3":{"draws":5,"losses":8,"wins":35},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":16},"thinkingmachines/inkling-small":{"draws":7,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":0}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-opus-4-5":{"draws":11,"losses":16,"wins":13},"claude-opus-4-8":{"draws":8,"losses":8,"wins":12},"claude-opus-5":{"draws":6,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":9},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":7,"losses":2,"wins":5},"gpt-5":{"draws":3,"losses":4,"wins":9},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":14},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":5},"o3":{"draws":2,"losses":3,"wins":7},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":9},"xiaomi/mimo-v2.5":{"draws":17,"losses":7,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":10,"wins":5}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":27,"wins":5},"claude-opus-4-5":{"draws":14,"losses":17,"wins":21},"claude-opus-4-8":{"draws":6,"losses":20,"wins":8},"claude-opus-5":{"draws":3,"losses":22,"wins":11},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":10,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":8,"wins":9},"gpt-4.1":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":4,"losses":10,"wins":14},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":18},"gpt-5.4-nano":{"draws":2,"losses":13,"wins":21},"gpt-5.5":{"draws":7,"losses":17,"wins":10},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":19},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":8,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":9},"o3":{"draws":3,"losses":11,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":11},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.5":{"draws":24,"losses":27,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"z-ai/glm-5.2":{"draws":5,"losses":10,"wins":13}},"gpt-5.5":{"claude-fable-5":{"draws":5,"losses":13,"wins":6},"claude-opus-4-5":{"draws":11,"losses":9,"wins":10},"claude-opus-4-8":{"draws":8,"losses":10,"wins":12},"claude-opus-5":{"draws":10,"losses":28,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":7,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":6,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":5,"losses":7,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":4,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":12,"losses":12,"wins":8},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":22,"losses":20,"wins":12},"google/gemini-3.5-flash-lite":{"draws":30,"losses":19,"wins":33},"google/gemini-3.6-flash":{"draws":21,"losses":37,"wins":20},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":17,"losses":29,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":11,"losses":35,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":12},"meta/muse-spark-1.2":{"draws":9,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":9},"o3":{"draws":8,"losses":18,"wins":22},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":11,"losses":2,"wins":11},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":11},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":0,"losses":6,"wins":0}},"gpt-5.6-sol":{"claude-opus-4-5":{"draws":8,"losses":5,"wins":19},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":8,"losses":10,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":11,"wins":68},"google/gemini-3.6-flash":{"draws":11,"losses":25,"wins":44},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":10,"losses":16,"wins":28},"gpt-5.6-luna":{"draws":6,"losses":8,"wins":38},"gpt-5.6-sol":{"draws":8,"losses":25,"wins":7},"inclusionai/ling-3.0-flash":{"draws":1,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":15},"meta/muse-spark-1.2":{"draws":3,"losses":7,"wins":24},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":21},"o3":{"draws":5,"losses":6,"wins":35},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":22},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":6},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":27},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":18},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":1}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":17,"losses":10,"wins":13},"claude-opus-4-8":{"draws":9,"losses":4,"wins":7},"claude-opus-5":{"draws":11,"losses":32,"wins":3},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":5,"losses":6,"wins":7},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":10},"gpt-5.5":{"draws":11,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":4,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":5,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":9,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":9,"losses":19,"wins":10},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":5,"wins":1},"claude-sonnet-5":{"draws":11,"losses":21,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":36,"losses":60,"wins":26},"google/gemini-3.6-flash":{"draws":43,"losses":55,"wins":20},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":8,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":2},"gpt-5.5":{"draws":1,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":9},"meituan/longcat-2.0":{"draws":12,"losses":24,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":35,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":4,"losses":49,"wins":17},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":8,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":15,"wins":17},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":15,"losses":36,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":22,"losses":42,"wins":19},"claude-opus-4-8":{"draws":4,"losses":4,"wins":2},"claude-opus-5":{"draws":5,"losses":19,"wins":4},"claude-sonnet-5":{"draws":22,"losses":41,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":50,"losses":74,"wins":87},"google/gemini-3.6-flash":{"draws":47,"losses":113,"wins":29},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":1,"losses":7,"wins":0},"gpt-5.4":{"draws":18,"losses":43,"wins":12},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":5},"gpt-5.5":{"draws":3,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":21,"losses":32,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":54,"wins":8},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":14,"wins":22},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":15},"meta/muse-spark-1.2":{"draws":15,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":1,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":29,"losses":58,"wins":11},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":3},"o3":{"draws":11,"losses":86,"wins":35},"openai/gpt-oss-120b":{"draws":15,"losses":10,"wins":27},"poolside/laguna-s-2.1":{"draws":27,"losses":14,"wins":27},"qwen/qwen3.7-max":{"draws":1,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-max":{"draws":2,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":18,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":33,"wins":32},"thinkingmachines/inkling-small":{"draws":1,"losses":3,"wins":0},"x-ai/grok-4.5":{"draws":22,"losses":58,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":2}},"meta/muse-spark-1.2":{"claude-opus-4-5":{"draws":5,"losses":6,"wins":15},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":12,"losses":13,"wins":17},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"wins":45},"google/gemini-3.6-flash":{"draws":8,"losses":19,"wins":45},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":10,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":16,"losses":7,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":24,"wins":13},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":10},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":15},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":17},"o3":{"draws":3,"losses":14,"wins":19},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":11},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":1,"wins":17},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":1,"losses":3,"wins":0}},"minimax/minimax-m3":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-8":{"draws":10,"losses":8,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":13,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":5,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":4},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":24,"wins":8},"gpt-5.5":{"draws":5,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":3},"o3":{"draws":4,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":17,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":1}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":18,"losses":22,"wins":14},"claude-opus-4-8":{"draws":2,"losses":2,"wins":4},"claude-opus-5":{"draws":4,"losses":19,"wins":1},"claude-sonnet-5":{"draws":19,"losses":14,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":49,"losses":28,"wins":65},"google/gemini-3.6-flash":{"draws":42,"losses":52,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":17,"losses":31,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":3},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":13,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":17},"meituan/longcat-2.0":{"draws":16,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":10,"losses":12,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":1},"o3":{"draws":10,"losses":37,"wins":31},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":18},"poolside/laguna-s-2.1":{"draws":19,"losses":1,"wins":22},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":12},"thinkingmachines/inkling":{"draws":26,"losses":2,"wins":26},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":19,"losses":27,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":2}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-8":{"draws":3,"losses":9,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":1,"losses":7,"wins":14},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":12},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":1,"losses":6,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":7,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":0,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":14,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":12,"wins":4},"o3":{"draws":0,"losses":8,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":16,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":0}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":8,"losses":4,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":0},"claude-opus-5":{"draws":2,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":4,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":8},"gpt-5.5":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":3,"losses":5,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":1}},"o3":{"claude-fable-5":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":7,"losses":16,"wins":9},"claude-opus-4-8":{"draws":4,"losses":7,"wins":3},"claude-opus-5":{"draws":2,"losses":19,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":15},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":12},"gpt-5.5":{"draws":7,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":8}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":3,"losses":9,"wins":0},"claude-opus-4-5":{"draws":13,"losses":14,"wins":3},"claude-opus-4-8":{"draws":7,"losses":6,"wins":3},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.6-flash":{"draws":9,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":2},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":5},"gpt-5.5":{"draws":10,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":9},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":6},"o3":{"draws":4,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":12,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":3,"wins":6}},"poolside/laguna-s-2.1":{"claude-opus-4-5":{"draws":39,"losses":43,"wins":2},"claude-opus-4-8":{"draws":8,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":31,"wins":3},"claude-sonnet-5":{"draws":26,"losses":37,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":100,"losses":54,"wins":60},"google/gemini-3.6-flash":{"draws":83,"losses":82,"wins":19},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":23,"losses":36,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":29,"losses":23,"wins":14},"gpt-5.6-sol":{"draws":12,"losses":59,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":26,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":39,"losses":32,"wins":25},"meta/muse-spark-1.2":{"draws":15,"losses":27,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":40,"losses":51,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":28,"losses":42,"wins":28},"openai/gpt-oss-120b":{"draws":18,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":31,"losses":18,"wins":13},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":0},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":11,"wins":5},"thinkingmachines/inkling":{"draws":41,"losses":25,"wins":34},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":35,"losses":46,"wins":13},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":14,"losses":16,"wins":8},"claude-opus-4-8":{"draws":8,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":11,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":11},"gpt-5.5":{"draws":7,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":11,"losses":1,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":7},"o3":{"draws":7,"losses":2,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":8,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":6}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":12,"wins":1},"claude-opus-4-5":{"draws":7,"losses":11,"wins":8},"claude-opus-4-8":{"draws":6,"losses":11,"wins":3},"claude-opus-5":{"draws":4,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":9,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":3}},"qwen/qwen3.8-max":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":1},"claude-sonnet-5":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":5},"gpt-5.4":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"meta/muse-spark-1.2":{"draws":3,"losses":0,"wins":1},"o3":{"draws":1,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":12,"losses":8,"wins":13},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling-small":{"draws":14,"losses":14,"wins":19},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":4}},"stealth/ox-alpha":{"stealth/ox-alpha":{"draws":80,"losses":133,"wins":95}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-5":{"draws":9,"losses":8,"wins":1},"claude-opus-4-8":{"draws":5,"losses":4,"wins":3},"claude-opus-5":{"draws":5,"losses":18,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":0},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":1},"o3":{"draws":2,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":1}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":9,"losses":17,"wins":4},"claude-opus-4-8":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":2,"losses":10,"wins":2},"claude-sonnet-5":{"draws":14,"losses":16,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":39,"losses":35,"wins":20},"google/gemini-3.6-flash":{"draws":43,"losses":33,"wins":16},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":7,"losses":18,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":5},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":15,"wins":13},"meta/muse-spark-1.2":{"draws":6,"losses":16,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":25,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":5,"wins":1},"o3":{"draws":14,"losses":23,"wins":8},"openai/gpt-oss-120b":{"draws":3,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":5,"wins":10},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":9,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":6,"wins":2}},"thinkingmachines/inkling-small":{"claude-opus-4-5":{"draws":0,"losses":3,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":9,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":4},"gpt-5.4":{"draws":3,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"meta/muse-spark-1.2":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":0},"o3":{"draws":1,"losses":4,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":7},"thinkingmachines/inkling-small":{"draws":15,"losses":12,"wins":11},"x-ai/grok-4.5":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":0}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":5,"losses":18,"wins":3},"claude-opus-4-5":{"draws":9,"losses":10,"wins":13},"claude-opus-4-8":{"draws":4,"losses":10,"wins":12},"claude-opus-5":{"draws":6,"losses":39,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":5,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":12},"gpt-5.5":{"draws":6,"losses":9,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":27},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":7},"o3":{"draws":2,"losses":5,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":5,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":4}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":25,"wins":12},"claude-opus-4-8":{"draws":18,"losses":19,"wins":5},"claude-opus-5":{"draws":2,"losses":17,"wins":1},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":17},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":9},"gpt-4.1":{"draws":3,"losses":3,"wins":4},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4-mini":{"draws":19,"losses":20,"wins":5},"gpt-5.4-nano":{"draws":19,"losses":28,"wins":25},"gpt-5.5":{"draws":20,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":18,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":19,"losses":11,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":17,"wins":9},"o3":{"draws":8,"losses":20,"wins":0},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":7},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":22},"x-ai/grok-4.5":{"draws":11,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":14,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":6,"losses":20,"wins":8}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":2,"losses":12,"wins":8},"claude-opus-4-8":{"draws":3,"losses":12,"wins":1},"claude-opus-5":{"draws":5,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":7},"gpt-4.1":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":13},"gpt-5.5":{"draws":1,"losses":8,"wins":5},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":6},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":17},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":4,"losses":12,"wins":16},"claude-opus-4-8":{"draws":12,"losses":10,"wins":4},"claude-opus-5":{"draws":1,"losses":17,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":7,"losses":6,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":4},"gpt-5.5":{"draws":10,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":4},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":4}}},"none":{"claude-opus-4-5":{"claude-fable-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-5":{"draws":13,"losses":4,"wins":9},"claude-opus-4-8":{"draws":3,"losses":12,"wins":9},"claude-opus-5":{"draws":10,"losses":38,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":5,"losses":5,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":8},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":11,"wins":15}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":6,"wins":2},"claude-opus-4-5":{"draws":8,"losses":6,"wins":14},"claude-opus-4-8":{"draws":4,"losses":1,"wins":3},"claude-opus-5":{"draws":4,"losses":19,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":12},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":14},"gpt-5.5":{"draws":5,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":6},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":11,"losses":7,"wins":4}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":17,"wins":15},"claude-opus-4-5":{"draws":17,"losses":17,"wins":46},"claude-opus-4-8":{"draws":11,"losses":10,"wins":25},"claude-opus-5":{"draws":19,"losses":62,"wins":37},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":20},"deepseek/deepseek-v4-pro":{"draws":5,"losses":0,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":16},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":41},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":39},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":16},"gpt-4.1":{"draws":7,"losses":1,"wins":15},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":1,"wins":18},"gpt-5.4":{"draws":0,"losses":0,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":32},"gpt-5.5":{"draws":14,"losses":10,"wins":36},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":36},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":8,"losses":1,"wins":27},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":12},"o3":{"draws":2,"losses":3,"wins":23},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":22},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"thinkingmachines/inkling":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":7,"wins":33},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":18},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":26}},"claude-sonnet-5":{"claude-opus-4-5":{"draws":14,"losses":17,"wins":5},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":9,"losses":17,"wins":8},"google/gemini-3.5-flash-lite":{"draws":28,"losses":21,"wins":35},"google/gemini-3.6-flash":{"draws":18,"losses":37,"wins":21},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":15,"losses":27,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":14,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":7},"moonshotai/kimi-k3":{"draws":16,"losses":20,"wins":8},"o3":{"draws":4,"losses":21,"wins":21},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":9,"losses":4,"wins":15},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":3}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":5,"losses":11,"wins":0},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":2},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":14,"wins":6},"gpt-5.5":{"draws":7,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":8,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":16,"wins":0},"claude-opus-4-8":{"draws":3,"losses":11,"wins":2},"claude-opus-5":{"draws":2,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":8,"wins":3},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":5},"google/gemini-3.5-flash":{"draws":9,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":5},"gpt-4.1":{"draws":5,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":4},"gpt-5.5":{"draws":10,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":4},"o3":{"draws":3,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":13,"losses":13,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":9,"losses":5,"wins":2}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":10,"losses":7,"wins":9},"claude-opus-4-8":{"draws":6,"losses":10,"wins":6},"claude-opus-5":{"draws":3,"losses":23,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":9,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":12},"gpt-5.5":{"draws":7,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":12},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":1},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":8}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":16,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":7},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":10,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":21,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":12,"wins":1}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":36,"losses":36,"wins":28},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":44,"wins":6},"claude-sonnet-5":{"draws":27,"losses":44,"wins":23},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":89,"losses":71,"wins":72},"google/gemini-3.6-flash":{"draws":82,"losses":106,"wins":56},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":30,"losses":54,"wins":12},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":9},"gpt-5.5":{"draws":11,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":30,"losses":32,"wins":32},"gpt-5.6-sol":{"draws":10,"losses":73,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":44,"losses":4,"wins":42},"meituan/longcat-2.0":{"draws":29,"losses":29,"wins":56},"meta/muse-spark-1.2":{"draws":18,"losses":29,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":51,"losses":63,"wins":26},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":1},"o3":{"draws":23,"losses":51,"wins":55},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":49,"losses":32,"wins":33},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max":{"draws":7,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":13},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":49,"losses":35,"wins":46},"thinkingmachines/inkling-small":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":28,"losses":66,"wins":32},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":4}},"google/gemini-3.6-flash":{"claude-opus-4-5":{"draws":36,"losses":41,"wins":25},"claude-opus-4-8":{"draws":7,"losses":2,"wins":3},"claude-opus-5":{"draws":3,"losses":41,"wins":8},"claude-sonnet-5":{"draws":34,"losses":40,"wins":22},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-pro":{"draws":9,"losses":0,"wins":5},"google/gemini-3.5-flash-lite":{"draws":122,"losses":83,"wins":81},"google/gemini-3.6-flash":{"draws":59,"losses":107,"wins":38},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":6,"wins":0},"gpt-5.4":{"draws":30,"losses":51,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":5},"gpt-5.5":{"draws":12,"losses":4,"wins":8},"gpt-5.6-luna":{"draws":39,"losses":28,"wins":35},"gpt-5.6-sol":{"draws":16,"losses":76,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":58,"losses":23,"wins":35},"meituan/longcat-2.0":{"draws":39,"losses":32,"wins":49},"meta/muse-spark-1.2":{"draws":18,"losses":46,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":59,"losses":70,"wins":15},"nex-agi/nex-n2-pro":{"draws":12,"losses":3,"wins":7},"o3":{"draws":30,"losses":85,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":28},"poolside/laguna-s-2.1":{"draws":68,"losses":31,"wins":37},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"qwen/qwen3.8-max":{"draws":0,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":66,"losses":20,"wins":62},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":30,"losses":64,"wins":37},"xiaomi/mimo-v2.5":{"draws":2,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":6}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":7,"losses":8,"wins":3},"claude-opus-4-8":{"draws":6,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":3,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":5},"o3":{"draws":4,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":22,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":3}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":8,"wins":10},"google/gemini-3.6-flash":{"draws":10,"losses":4,"wins":6},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":0},"o3":{"draws":0,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5.4":{"claude-opus-4-5":{"draws":9,"losses":10,"wins":11},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":17,"losses":12,"wins":21},"google/gemini-3.5-flash-lite":{"draws":33,"losses":14,"wins":47},"google/gemini-3.6-flash":{"draws":18,"losses":33,"wins":29},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":15,"losses":42,"wins":1},"gpt-5.6-luna":{"draws":25,"losses":13,"wins":22},"gpt-5.6-sol":{"draws":14,"losses":28,"wins":12},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":9},"meta/muse-spark-1.2":{"draws":7,"losses":20,"wins":9},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":15},"o3":{"draws":6,"losses":17,"wins":27},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":15,"losses":0,"wins":9},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":6},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":15},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":0}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":14,"losses":11,"wins":5},"claude-opus-4-8":{"draws":10,"losses":9,"wins":3},"claude-opus-5":{"draws":4,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":11,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":8,"wins":3},"gpt-4.1":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":3},"gpt-5.5":{"draws":9,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":4},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":7,"wins":2}},"gpt-5.4-nano":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":10,"losses":16,"wins":12},"claude-opus-4-8":{"draws":7,"losses":16,"wins":9},"claude-opus-5":{"draws":11,"losses":32,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":19,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":8},"google/gemini-3.6-flash":{"draws":16,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":9},"gpt-5.5":{"draws":9,"losses":11,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":14},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":12,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":3,"losses":2,"wins":7},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":31,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":4}},"gpt-5.5":{"claude-opus-4-5":{"draws":14,"losses":10,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":4},"claude-opus-5":{"draws":10,"losses":28,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":8},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":15,"losses":4,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":11,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":2,"wins":9},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":22,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":1},"o3":{"draws":7,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":19,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":7}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":9,"losses":20,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":15,"losses":31,"wins":5},"google/gemini-3.5-flash-lite":{"draws":19,"losses":41,"wins":24},"google/gemini-3.6-flash":{"draws":22,"losses":53,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":16,"losses":38,"wins":4},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":43,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":12,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":26,"wins":4},"o3":{"draws":3,"losses":37,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":0},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":1,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":21,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":0}},"gpt-5.6-sol":{"claude-opus-4-5":{"draws":6,"losses":8,"wins":20},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":30},"google/gemini-3.5-flash-lite":{"draws":21,"losses":9,"wins":54},"google/gemini-3.6-flash":{"draws":15,"losses":25,"wins":42},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":21,"losses":26,"wins":13},"gpt-5.6-luna":{"draws":17,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":12},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":19},"o3":{"draws":0,"losses":10,"wins":36},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":15},"poolside/laguna-s-2.1":{"draws":9,"losses":0,"wins":17},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":19},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":5,"losses":17,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":0,"wins":1}},"gpt-5.6-terra":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":14,"losses":11,"wins":7},"claude-opus-4-8":{"draws":12,"losses":7,"wins":5},"claude-opus-5":{"draws":14,"losses":23,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":15,"losses":5,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":1},"google/gemini-3.6-flash":{"draws":11,"losses":6,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":7},"gpt-5.5":{"draws":12,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":6},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":4,"wins":11},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":14,"losses":6,"wins":2},"claude-opus-4-8":{"draws":14,"losses":4,"wins":0},"claude-opus-5":{"draws":8,"losses":17,"wins":1},"cohere/north-mini-code":{"draws":16,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":9},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":33,"losses":15,"wins":4},"google/gemini-3.6-flash":{"draws":47,"losses":20,"wins":9},"google/gemma-4-31b-it":{"draws":12,"losses":17,"wins":3},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":14,"wins":7},"gpt-5.5":{"draws":26,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":11},"meituan/longcat-2.0":{"draws":35,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":5,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":39,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":17,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":16},"x-ai/grok-4.5":{"draws":10,"losses":24,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":2,"wins":4}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":16,"losses":12,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":7,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":18,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":19,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":17},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":25,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":7,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":16,"losses":22,"wins":16},"gpt-5.5":{"draws":13,"losses":4,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":9},"inclusionai/ling-3.0-flash":{"draws":33,"losses":19,"wins":24},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":6},"o3":{"draws":7,"losses":4,"wins":13},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":12},"qwen/qwen3.7-max":{"draws":17,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":11,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":17},"x-ai/grok-4.5":{"draws":14,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":17,"wins":9}},"meta/muse-spark-1.2":{"claude-opus-4-5":{"draws":8,"losses":12,"wins":10},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":16,"losses":18,"wins":14},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":37},"google/gemini-3.6-flash":{"draws":18,"losses":46,"wins":24},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":9,"losses":24,"wins":13},"gpt-5.6-luna":{"draws":13,"losses":19,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":4},"meituan/longcat-2.0":{"draws":5,"losses":13,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":17,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":21,"wins":11},"o3":{"draws":2,"losses":30,"wins":18},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":13},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-max":{"draws":3,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":18},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":1}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":15,"wins":5},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":3,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":8},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":10},"gpt-5.5":{"draws":4,"losses":9,"wins":7},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":9,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":1,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":9,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":5}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-8":{"draws":2,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":4},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":3},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":5}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":23,"losses":14,"wins":29},"claude-opus-4-8":{"draws":4,"losses":3,"wins":7},"claude-opus-5":{"draws":6,"losses":23,"wins":11},"claude-sonnet-5":{"draws":15,"losses":12,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":7},"google/gemini-3.5-flash-lite":{"draws":43,"losses":26,"wins":61},"google/gemini-3.6-flash":{"draws":41,"losses":51,"wins":46},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":8},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":26,"wins":15},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":16},"gpt-5.5":{"draws":5,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":30},"gpt-5.6-sol":{"draws":11,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":3,"wins":11},"meituan/longcat-2.0":{"draws":19,"losses":13,"wins":24},"meta/muse-spark-1.2":{"draws":10,"losses":10,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":23,"losses":16,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"o3":{"draws":9,"losses":30,"wins":25},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":22,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":7},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":23,"losses":24,"wins":29},"xiaomi/mimo-v2.5":{"draws":8,"losses":8,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":2,"losses":4,"wins":0}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":7,"losses":9,"wins":6},"claude-opus-4-8":{"draws":11,"losses":12,"wins":3},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":9,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":12,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":15,"losses":8,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":8},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":5},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":2,"losses":7,"wins":3},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":14,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":3},"gpt-5.5":{"draws":12,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":12,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":5}},"o3":{"claude-opus-4-5":{"draws":6,"losses":16,"wins":6},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":3,"losses":18,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":21,"losses":45,"wins":11},"google/gemini-3.6-flash":{"draws":24,"losses":33,"wins":13},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":0},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":3,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":1},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":26,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":13,"wins":12},"meta/muse-spark-1.2":{"draws":0,"losses":14,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":20,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"o3":{"draws":10,"losses":30,"wins":8},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":15,"losses":12,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":9},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":18,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":6,"losses":50,"wins":2},"claude-opus-4-8":{"draws":0,"losses":9,"wins":3},"claude-opus-5":{"draws":1,"losses":4,"wins":1},"claude-sonnet-5":{"draws":10,"losses":33,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":5,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":27,"losses":75,"wins":20},"google/gemini-3.6-flash":{"draws":17,"losses":79,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":6,"losses":34,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":6},"gpt-5.5":{"draws":6,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":13,"losses":21,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":43,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":11,"losses":12,"wins":11},"meituan/longcat-2.0":{"draws":14,"losses":26,"wins":6},"meta/muse-spark-1.2":{"draws":4,"losses":29,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":8,"wins":1},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":43,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"o3":{"draws":15,"losses":54,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":20,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":11,"losses":37,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":31,"wins":4},"xiaomi/mimo-v2.5":{"draws":9,"losses":13,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":1,"losses":3,"wins":0}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":4,"wins":6},"claude-opus-4-5":{"draws":18,"losses":11,"wins":5},"claude-opus-4-8":{"draws":4,"losses":18,"wins":4},"claude-opus-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":17,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":23,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":4},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":17,"losses":18,"wins":21},"google/gemini-3.6-flash":{"draws":22,"losses":26,"wins":22},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":8},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":4,"wins":9},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":16,"losses":10,"wins":14},"gpt-5.5":{"draws":13,"losses":9,"wins":12},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":13},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":21},"meituan/longcat-2.0":{"draws":21,"losses":7,"wins":14},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":9},"o3":{"draws":7,"losses":11,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":21,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":14,"losses":13,"wins":21},"x-ai/grok-4.5":{"draws":10,"losses":35,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":23,"losses":12,"wins":13}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-8":{"draws":4,"losses":9,"wins":5},"claude-opus-5":{"draws":7,"losses":30,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":12,"losses":8,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":9},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":11},"gpt-5.5":{"draws":10,"losses":4,"wins":6},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":3},"o3":{"draws":3,"losses":4,"wins":1},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":8},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":11,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":3}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":16,"losses":7,"wins":3},"claude-opus-4-8":{"draws":6,"losses":9,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":10,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":9,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":6,"wins":6},"o3":{"draws":1,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":12,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":23,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"qwen/qwen3.8-max":{"claude-sonnet-5":{"draws":0,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":3},"gpt-5.4":{"draws":4,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":1},"o3":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":6},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":16},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":1}},"stealth/ox-alpha":{"stealth/ox-alpha":{"draws":83,"losses":155,"wins":83}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":4,"losses":23,"wins":9},"claude-opus-4-8":{"draws":0,"losses":7,"wins":1},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":3,"losses":12,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":14,"losses":28,"wins":30},"google/gemini-3.6-flash":{"draws":7,"losses":38,"wins":9},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":3,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":4},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":9},"gpt-5.6-sol":{"draws":1,"losses":19,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":19,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":0},"o3":{"draws":8,"losses":38,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":13},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":12,"wins":13},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":16,"wins":6},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":3,"wins":4},"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-opus-4-8":{"draws":8,"losses":7,"wins":3},"claude-opus-5":{"draws":8,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":10},"gpt-5.5":{"draws":12,"losses":6,"wins":4},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":5,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":3}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":20,"losses":22,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":6,"losses":29,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":17,"wins":10},"google/gemini-3.6-flash":{"draws":25,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":12},"gpt-5.5":{"draws":11,"losses":13,"wins":8},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":11},"o3":{"draws":5,"losses":5,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":14,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":33,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":9,"losses":14,"wins":9}},"thinkingmachines/inkling-small":{"claude-opus-4-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":2,"losses":8,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":1},"gpt-5.4":{"draws":5,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"o3":{"draws":1,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":11},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling-small":{"draws":14,"losses":14,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":0,"wins":0}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":24,"losses":23,"wins":23},"claude-opus-4-8":{"draws":5,"losses":2,"wins":5},"claude-opus-5":{"draws":5,"losses":17,"wins":6},"claude-sonnet-5":{"draws":25,"losses":7,"wins":18},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash-lite":{"draws":52,"losses":19,"wins":59},"google/gemini-3.6-flash":{"draws":32,"losses":61,"wins":34},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":12,"losses":29,"wins":11},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":11},"gpt-5.5":{"draws":5,"losses":0,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":15,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":32,"wins":11},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":17},"meituan/longcat-2.0":{"draws":16,"losses":13,"wins":25},"meta/muse-spark-1.2":{"draws":13,"losses":10,"wins":13},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":29,"losses":27,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"o3":{"draws":6,"losses":31,"wins":35},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":23,"losses":13,"wins":24},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":30},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":5},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":19,"losses":25,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":14},"deepseek/deepseek-v4-flash":{"draws":19,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":11,"losses":20,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":15,"wins":17},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":30},"gpt-5.5":{"draws":16,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":17,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":12},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":16,"wins":17},"poolside/laguna-s-2.1":{"draws":6,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":9,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":21,"wins":14}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":5,"losses":9,"wins":10},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":3,"losses":26,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":8,"losses":7,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":10,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":11},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":7}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":31,"wins":20},"claude-opus-4-8":{"draws":11,"losses":15,"wins":12},"claude-opus-5":{"draws":12,"losses":43,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":10,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":11,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-5":{"draws":9,"losses":13,"wins":12},"gpt-5.4-mini":{"draws":18,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":15},"gpt-5.5":{"draws":12,"losses":14,"wins":10},"gpt-5.6-terra":{"draws":27,"losses":11,"wins":18},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":6},"z-ai/glm-5.2":{"draws":16,"losses":13,"wins":17}}}}}