{"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":"2026-08-23T20:51:16Z","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":83.8181052528922,"medium":68.70642652869618},"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":167,"losses":264,"wins":929},"match_totals_tracks":{"highest":{"draws":98,"losses":116,"wins":522},"medium":{"draws":69,"losses":148,"wins":407}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":75.13438841167155,"min":55.133363671974216},"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":79.58869492247467,"GB2-02":73.74954635252826,"GB2-03":72.45110481946428,"GB2-04":100.0,"GB2-05":91.20233840190105,"GB2-06":84.82657150590221,"GB2-07":68.72658602086715,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":61,"wins":127},"GB2-02":{"draws":68,"losses":13,"wins":81},"GB2-03":{"draws":32,"losses":7,"wins":29},"GB2-04":{"draws":52,"losses":22,"wins":108},"GB2-05":{"draws":0,"losses":58,"wins":148},"GB2-06":{"draws":14,"losses":32,"wins":130},"GB2-07":{"draws":0,"losses":55,"wins":129},"GB2-08":{"draws":1,"losses":16,"wins":177}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":35,"wins":67},"GB2-02":{"draws":37,"losses":4,"wins":43},"GB2-03":{"draws":32,"losses":7,"wins":29},"GB2-04":{"draws":19,"losses":5,"wins":78},"GB2-05":{"draws":0,"losses":16,"wins":84},"GB2-06":{"draws":9,"losses":10,"wins":65},"GB2-07":{"draws":0,"losses":35,"wins":59},"GB2-08":{"draws":1,"losses":4,"wins":97}},"medium":{"GB2-01":{"draws":0,"losses":26,"wins":60},"GB2-02":{"draws":31,"losses":9,"wins":38},"GB2-04":{"draws":33,"losses":17,"wins":30},"GB2-05":{"draws":0,"losses":42,"wins":64},"GB2-06":{"draws":5,"losses":22,"wins":65},"GB2-07":{"draws":0,"losses":20,"wins":70},"GB2-08":{"draws":0,"losses":12,"wins":80}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1824.3873130220802,"GB2-02":1705.9057480073943,"GB2-03":1699.478327839778,"GB2-04":1871.3393976382893,"GB2-05":2023.8636251018338,"GB2-06":1909.8483590250705,"GB2-07":1735.946996477361,"GB2-08":2070.226734381098},"medium":{"GB2-01":1746.9451046530367,"GB2-02":1685.6539281264988,"GB2-04":1582.2001981056562,"GB2-05":1679.6354629058385,"GB2-06":1815.5838157198623,"GB2-07":1769.0766033480754,"GB2-08":1817.575241405041}},"per_game_tracks":{"highest":{"GB2-01":79.58869492247467,"GB2-02":73.74954635252826,"GB2-03":72.45110481946428,"GB2-04":100.0,"GB2-05":91.20233840190105,"GB2-06":84.82657150590221,"GB2-07":68.72658602086715,"GB2-08":100.0},"medium":{"GB2-01":71.4108605082153,"GB2-02":68.84186917568367,"GB2-04":55.133363671974216,"GB2-05":62.71165398791373,"GB2-06":76.8393903737067,"GB2-07":71.7604520313932,"GB2-08":74.2473959519865}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.8181052528922,"medium":66.45067157045091},"reasoning_agg":{"highest":{"max":100.0,"mean":83.8181052528922,"min":68.72658602086715},"medium":{"max":76.8393903737067,"mean":66.45067157045091,"min":55.133363671974216}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":17.367433682441288},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":82.6854611631132,"reliability_score":91.56145946354827,"uncertainty_avg":8.438540536451729,"uncertainty_penalty":-1.1326440897789922},"medium":{"ceiling_score":76.8393903737067,"expected_score":82.8289305223702,"reliability_score":90.91259812783312,"uncertainty_avg":9.087401872166874,"uncertainty_penalty":16.378258951919292}}},{"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":22.07445},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.138875},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999},"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":22.07445}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":75.11744664685064,"highest":81.94688975391686,"medium":76.0249729036377,"none":70.35475020724844},"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":578,"losses":656,"wins":2571},"match_totals_tracks":{"highest":{"draws":66,"losses":158,"wins":698},"medium":{"draws":185,"losses":241,"wins":932},"none":{"draws":327,"losses":257,"wins":941}},"model_slug":"claude-opus-5","overall":{"max":100.0,"mean":73.125125657378,"min":51.08859351407519},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":61.97751151718376,"GB2-02":70.34600839013916,"GB2-03":98.71900811266804,"GB2-04":83.8367732821356,"GB2-05":86.6055678570907,"GB2-07":100.0,"GB2-08":72.14335911820079},"per_game_all":{"GB2-01":66.23681878130823,"GB2-02":64.76010798993828,"GB2-03":83.03058422917827,"GB2-04":62.43999194489251,"GB2-05":85.79636306093346,"GB2-07":88.80682421402798,"GB2-08":74.75143630767577},"per_game_match_totals_all":{"GB2-01":{"draws":126,"losses":134,"wins":319},"GB2-02":{"draws":182,"losses":51,"wins":223},"GB2-03":{"draws":43,"losses":80,"wins":331},"GB2-04":{"draws":200,"losses":132,"wins":242},"GB2-05":{"draws":0,"losses":74,"wins":530},"GB2-06":{"draws":11,"losses":5,"wins":88},"GB2-07":{"draws":0,"losses":56,"wins":322},"GB2-08":{"draws":16,"losses":124,"wins":516}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":47,"wins":79},"GB2-02":{"draws":38,"losses":21,"wins":59},"GB2-03":{"draws":0,"losses":9,"wins":107},"GB2-04":{"draws":26,"losses":19,"wins":119},"GB2-05":{"draws":0,"losses":22,"wins":118},"GB2-07":{"draws":0,"losses":1,"wins":81},"GB2-08":{"draws":0,"losses":39,"wins":135}},"medium":{"GB2-01":{"draws":19,"losses":64,"wins":127},"GB2-02":{"draws":68,"losses":16,"wins":68},"GB2-03":{"draws":8,"losses":15,"wins":139},"GB2-04":{"draws":90,"losses":57,"wins":59},"GB2-05":{"draws":0,"losses":28,"wins":198},"GB2-07":{"draws":0,"losses":33,"wins":163},"GB2-08":{"draws":0,"losses":28,"wins":178}},"none":{"GB2-01":{"draws":105,"losses":23,"wins":113},"GB2-02":{"draws":76,"losses":14,"wins":96},"GB2-03":{"draws":35,"losses":56,"wins":85},"GB2-04":{"draws":84,"losses":56,"wins":64},"GB2-05":{"draws":0,"losses":24,"wins":214},"GB2-06":{"draws":11,"losses":5,"wins":88},"GB2-07":{"draws":0,"losses":22,"wins":78},"GB2-08":{"draws":16,"losses":57,"wins":203}}},"per_game_raw_elo_all":{"GB2-01":1694.5579927086455,"GB2-02":1668.6242194658932,"GB2-03":1775.2024346834294,"GB2-04":1626.5149149429374,"GB2-05":1959.445091949363,"GB2-07":1949.6316380497592,"GB2-08":1819.8099523808648},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1660.4981048082484,"GB2-02":1698.998209186365,"GB2-03":1896.2197178100707,"GB2-04":1769.8664441103872,"GB2-05":1976.177267738965,"GB2-07":2071.119577926703,"GB2-08":1797.9285674036369},"medium":{"GB2-01":1705.5104108029932,"GB2-02":1652.4738991796207,"GB2-03":1867.8291510173494,"GB2-04":1559.023551151262,"GB2-05":1925.6591942822074,"GB2-07":1921.5873524622293,"GB2-08":1926.3153794356558},"none":{"GB2-01":1717.6654625146953,"GB2-02":1654.4005500316935,"GB2-03":1561.558435222868,"GB2-04":1550.6547495671625,"GB2-05":1976.4988138269168,"GB2-06":1978.901816863329,"GB2-07":1856.1879837603456,"GB2-08":1735.1859103033014}},"per_game_tracks":{"highest":{"GB2-01":61.97751151718376,"GB2-02":70.34600839013916,"GB2-03":98.71900811266804,"GB2-04":83.8367732821356,"GB2-05":86.6055678570907,"GB2-07":100.0,"GB2-08":72.14335911820079},"medium":{"GB2-01":67.61473995183059,"GB2-02":61.26562064904274,"GB2-03":95.92764370282903,"GB2-04":52.394609038466754,"GB2-05":83.24150998152905,"GB2-07":86.2614975844883,"GB2-08":85.4691894172775},"none":{"GB2-01":69.11820487491038,"GB2-02":62.66869493063295,"GB2-03":54.44510087203772,"GB2-04":51.08859351407519,"GB2-05":87.54201134418061,"GB2-06":91.17466067700593,"GB2-07":80.15897505759567,"GB2-08":66.64176038754904}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":77.80156217109193,"medium":73.52893696868458,"none":68.04487783235751},"reasoning_agg":{"highest":{"max":100.0,"mean":77.80156217109193,"min":61.97751151718376},"medium":{"max":95.92764370282903,"mean":73.52893696868458,"min":52.394609038466754},"none":{"max":91.17466067700593,"mean":68.04487783235751,"min":51.08859351407519}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":86.86667245071472,"reasoning_variance":9.756684338734416,"reliability_score":90.87444840807119,"uncertainty_avg":9.125551591928811,"uncertainty_penalty":13.74154679333671},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":80.97190742928763,"reliability_score":84.5663241857649,"uncertainty_avg":15.433675814235102,"uncertainty_penalty":3.1703452581956952},"medium":{"ceiling_score":95.92764370282903,"expected_score":89.65224849259961,"reliability_score":92.85016977355339,"uncertainty_avg":7.1498302264466105,"uncertainty_penalty":16.123311523915035},"none":{"ceiling_score":91.17466067700593,"expected_score":91.2288787514748,"reliability_score":95.17536940085503,"uncertainty_avg":4.824630599144965,"uncertainty_penalty":23.18400091911728}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:355993239c1ccc35","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":17},"evidence_basis":"Standard list-price estimate","max":6.83719875,"mean":5.427906484375001,"median":5.376420937500001,"min":4.5604125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":16,"token_priced_attempt_count":17,"total":86.84650375},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":18},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.44844375,"mean":0.352186484375,"median":0.3360778125,"min":0.30487875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18},"run_count":17,"token_priced_attempt_count":18,"total":5.952425},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":17},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.14688374999999998,"mean":0.12438640625,"median":0.12834374999999998,"min":0.09558187500000001,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":17,"token_priced_attempt_count":17,"total":2.0924099999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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":1.8325049999999998},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6689649999999999,"mean":0.46799875,"median":0.4352825,"min":0.36661499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":9,"token_priced_attempt_count":10,"total":4.1199200000000005},"historical-provider-setting-baseline-variant-1":{"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-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.147405,"mean":0.12146437500000001,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485},"historical-provider-setting-intensive-variant-1":{"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},"historical-provider-setting-intensive-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":12.915325,"mean":10.059243749999998,"median":10.0094025,"min":8.401555,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":80.47395}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":52},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":6.83719875,"mean":1.9681597916666664,"median":0.3360778125,"min":0.09558187500000001,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":52},"run_count":50,"token_priced_attempt_count":52,"total":94.89133875},"codegen_latency_ms":{"attempt_count":27,"max_ms":422464,"mean_ms":160017.42307692306,"min_ms":18406,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":422464,"mean_ms":390133.625,"min_ms":351613,"run_count":8},"medium":{"attempt_count":10,"max_ms":132971,"mean_ms":90177.0,"min_ms":75382,"run_count":9},"none":{"attempt_count":9,"max_ms":34692,"mean_ms":25310.11111111111,"min_ms":18406,"run_count":9}},"codegen_output_tokens":{"attempt_count":52,"output_max":428840,"output_mean":61739.14,"output_min":1810,"run_count":50},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":17,"output_max":428840,"output_mean":179327.8125,"output_min":19522,"run_count":16},"medium":{"attempt_count":18,"output_max":20628,"output_mean":10141.411764705883,"output_min":5176,"run_count":17},"none":{"attempt_count":17,"output_max":3573,"output_mean":2665.176470588235,"output_min":1810,"run_count":17}},"display_name":"GPT-5.6 Sol","economics":{"all":62.80258612934627,"highest":76.55089975602554,"medium":62.05256256645748,"none":49.80429606555579},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":52,"finish_reasons":["stop"],"indexed_attempts":76,"output_token_observations":52,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":3086957,"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":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":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},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"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,"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}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-08-23T05:21:14Z","match_totals_all":{"draws":726,"losses":1021,"wins":2501},"match_totals_tracks":{"highest":{"draws":113,"losses":276,"wins":1029},"medium":{"draws":258,"losses":331,"wins":829},"none":{"draws":355,"losses":414,"wins":643}},"model_slug":"gpt-5-6-sol","overall":{"max":99.52317300196941,"mean":61.72068956858967,"min":26.469312004278905},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.86094003829044,"GB2-02":99.52317300196941,"GB2-03":79.44499279291648,"GB2-04":78.91168626964662,"GB2-05":63.91279578997471,"GB2-06":84.36878169555632,"GB2-07":76.37750292453808,"GB2-08":53.00732553531228},"per_game_all":{"GB2-01":67.84977773745561,"GB2-02":58.627319690201354,"GB2-03":61.30528857623003,"GB2-04":63.02160027748394,"GB2-05":62.19002781221378,"GB2-06":63.54092585556807,"GB2-07":67.2630683451895,"GB2-08":58.62268074042788},"per_game_match_totals_all":{"GB2-01":{"draws":37,"losses":154,"wins":377},"GB2-02":{"draws":225,"losses":38,"wins":185},"GB2-03":{"draws":107,"losses":117,"wins":262},"GB2-04":{"draws":266,"losses":38,"wins":222},"GB2-05":{"draws":0,"losses":186,"wins":376},"GB2-06":{"draws":28,"losses":179,"wins":346},"GB2-07":{"draws":0,"losses":157,"wins":406},"GB2-08":{"draws":63,"losses":152,"wins":327}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":44,"wins":149},"GB2-02":{"draws":28,"losses":11,"wins":119},"GB2-03":{"draws":8,"losses":32,"wins":122},"GB2-04":{"draws":52,"losses":8,"wins":116},"GB2-05":{"draws":0,"losses":57,"wins":125},"GB2-06":{"draws":9,"losses":24,"wins":143},"GB2-07":{"draws":0,"losses":31,"wins":157},"GB2-08":{"draws":13,"losses":69,"wins":98}},"medium":{"GB2-01":{"draws":22,"losses":60,"wins":110},"GB2-02":{"draws":79,"losses":13,"wins":54},"GB2-03":{"draws":22,"losses":41,"wins":87},"GB2-04":{"draws":97,"losses":9,"wins":80},"GB2-05":{"draws":0,"losses":54,"wins":138},"GB2-06":{"draws":13,"losses":69,"wins":102},"GB2-07":{"draws":0,"losses":49,"wins":141},"GB2-08":{"draws":25,"losses":36,"wins":117}},"none":{"GB2-01":{"draws":12,"losses":50,"wins":118},"GB2-02":{"draws":118,"losses":14,"wins":12},"GB2-03":{"draws":77,"losses":44,"wins":53},"GB2-04":{"draws":117,"losses":21,"wins":26},"GB2-05":{"draws":0,"losses":75,"wins":113},"GB2-06":{"draws":6,"losses":86,"wins":101},"GB2-07":{"draws":0,"losses":77,"wins":108},"GB2-08":{"draws":25,"losses":47,"wins":112}}},"per_game_raw_elo_all":{"GB2-01":1709.7690953518304,"GB2-02":1641.2835382070432,"GB2-03":1614.0877334811166,"GB2-04":1632.197561305222,"GB2-05":1675.8198074968298,"GB2-06":1661.8060917835335,"GB2-07":1720.4480049357105,"GB2-08":1663.4156077938476},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1798.2420883252416,"GB2-02":1822.4131382061005,"GB2-03":1747.1374541252894,"GB2-04":1736.262097079852,"GB2-05":1697.150154488464,"GB2-06":1903.5767486670418,"GB2-07":1817.2716653984826,"GB2-08":1607.952787052161},"medium":{"GB2-01":1652.5834654247703,"GB2-02":1602.7750164385534,"GB2-03":1599.4922084182406,"GB2-04":1663.9931662036106,"GB2-05":1743.0258196719778,"GB2-06":1571.4134191801722,"GB2-07":1749.555635636583,"GB2-08":1714.8191527570873},"none":{"GB2-01":1678.48173230548,"GB2-02":1498.6624599764757,"GB2-03":1495.6335378998199,"GB2-04":1496.3374206322035,"GB2-05":1587.2834483300476,"GB2-06":1510.428107503386,"GB2-07":1594.516713772066,"GB2-08":1667.474883572294}},"per_game_tracks":{"highest":{"GB2-01":76.86094003829044,"GB2-02":99.52317300196941,"GB2-03":79.44499279291648,"GB2-04":78.91168626964662,"GB2-05":63.91279578997471,"GB2-06":84.36878169555632,"GB2-07":76.37750292453808,"GB2-08":53.00732553531228},"medium":{"GB2-01":62.100714212737586,"GB2-02":49.889474064355774,"GB2-03":59.04540587223423,"GB2-04":68.03330219031832,"GB2-05":67.8135861604195,"GB2-06":55.7230339519561,"GB2-07":70.02605926216759,"GB2-08":63.78892481747077},"none":{"GB2-01":64.58767896133882,"GB2-02":26.469312004278905,"GB2-03":45.4254670635394,"GB2-04":42.11981237248688,"GB2-05":54.84370148624712,"GB2-06":50.53096191919179,"GB2-07":55.385642848862844,"GB2-08":59.07179186850058}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":76.55089975602554,"medium":60.252017078737964,"none":48.359151871005515},"reasoning_agg":{"highest":{"max":99.52317300196941,"mean":76.55089975602554,"min":53.00732553531228},"medium":{"max":70.02605926216759,"mean":60.252017078737964,"min":49.889474064355774},"none":{"max":64.58767896133882,"mean":48.359151871005515,"min":26.469312004278905}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":99.52317300196941,"expected_score":67.93533712367224,"reasoning_variance":28.19174788502003,"reliability_score":90.63210027029103,"uncertainty_avg":9.36789972970896,"uncertainty_penalty":6.214647555082571},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.52317300196941,"expected_score":72.66510506663998,"reliability_score":90.70156239144617,"uncertainty_avg":9.298437608553831,"uncertainty_penalty":-3.8857946893855626},"medium":{"ceiling_score":70.02605926216759,"expected_score":70.24887907842097,"reliability_score":90.53845336735839,"uncertainty_avg":9.461546632641612,"uncertainty_penalty":9.996861999683006},"none":{"ceiling_score":64.58767896133882,"expected_score":60.892027225955786,"reliability_score":90.65628505206857,"uncertainty_avg":9.343714947931433,"uncertainty_penalty":12.53287535495027}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:b646b36fcd253b5f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":18},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.44992,"mean":2.0808053125,"median":2.17314,"min":1.325615,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18},"run_count":16,"token_priced_attempt_count":18,"total":33.292885},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":17},"evidence_basis":"Standard list-price estimate","max":0.49506249999999996,"mean":0.39100906250000006,"median":0.40353625,"min":0.253325,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":16,"token_priced_attempt_count":17,"total":6.256145},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":20},"evidence_basis":"Standard list-price estimate","max":0.16978625,"mean":0.09482640625,"median":0.07918125000000001,"min":0.06869,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20},"run_count":16,"token_priced_attempt_count":20,"total":1.5172225000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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":2.2669949999999996},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.712055,"mean":0.49864374999999994,"median":0.5065824999999999,"min":0.29423750000000004,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":3.98915},"historical-provider-setting-baseline-variant-1":{"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},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.15985749999999999,"mean":0.09356500000000001,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7485199999999999},"historical-provider-setting-intensive-variant-1":{"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},"historical-provider-setting-intensive-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":2.642580625,"median":2.681945,"min":1.562975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.140645}},"codegen_cost_usd":{"admitted_cell_count":47,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":55},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.44992,"mean":0.8555469270833335,"median":0.40353625,"min":0.06869,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":55},"run_count":48,"token_priced_attempt_count":55,"total":41.0662525},"codegen_latency_ms":{"attempt_count":28,"max_ms":1461887,"mean_ms":367273.6666666667,"min_ms":21601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1461887,"mean_ms":911419.875,"min_ms":461183,"run_count":8},"medium":{"attempt_count":9,"max_ms":292880,"mean_ms":161490.125,"min_ms":88006,"run_count":8},"none":{"attempt_count":10,"max_ms":50293,"mean_ms":28911.0,"min_ms":21601,"run_count":8}},"codegen_output_tokens":{"attempt_count":55,"output_max":218271,"output_mean":55086.875,"output_min":3180,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":218271,"output_mean":135895.125,"output_min":71368,"run_count":16},"medium":{"attempt_count":17,"output_max":45034,"output_mean":24699.0625,"output_min":12941,"run_count":16},"none":{"attempt_count":20,"output_max":8643,"output_mean":4666.4375,"output_min":3180,"run_count":16}},"display_name":"GPT-5.4","economics":{"all":56.880522981501706,"highest":71.6443643604213,"medium":51.68213333592078,"none":47.31507124816302},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":55,"finish_reasons":["stop"],"indexed_attempts":55,"output_token_observations":55,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":2644170,"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":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},"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-5.4","is_recent_addition":false,"last_measured_at":"2026-08-23T08:23:52Z","match_totals_all":{"draws":1166,"losses":965,"wins":2166},"match_totals_tracks":{"highest":{"draws":225,"losses":195,"wins":937},"medium":{"draws":454,"losses":376,"wins":662},"none":{"draws":487,"losses":394,"wins":567}},"model_slug":"gpt-5-4","overall":{"max":96.95590676313576,"mean":56.88052298150171,"min":18.245710919802534},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":96.95590676313576,"GB2-02":54.7169870956697,"GB2-03":37.76802152050538,"GB2-04":61.22868483056382,"GB2-05":90.89912695137986,"GB2-06":88.93765075471762,"GB2-07":87.10047490567965,"GB2-08":55.54806206171865},"per_game_all":{"GB2-01":88.99247297781248,"GB2-02":31.77255979468657,"GB2-03":40.40417324421162,"GB2-04":44.018420022376255,"GB2-05":71.35390293271371,"GB2-06":81.30717090494059,"GB2-07":54.406307506675454,"GB2-08":42.78917646859697},"per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":51,"wins":486},"GB2-02":{"draws":331,"losses":35,"wins":33},"GB2-03":{"draws":215,"losses":158,"wins":136},"GB2-04":{"draws":299,"losses":112,"wins":124},"GB2-05":{"draws":0,"losses":153,"wins":433},"GB2-06":{"draws":38,"losses":66,"wins":430},"GB2-07":{"draws":0,"losses":227,"wins":351},"GB2-08":{"draws":258,"losses":163,"wins":173}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":8,"wins":184},"GB2-02":{"draws":51,"losses":9,"wins":22},"GB2-03":{"draws":45,"losses":56,"wins":54},"GB2-04":{"draws":79,"losses":28,"wins":71},"GB2-05":{"draws":0,"losses":9,"wins":179},"GB2-06":{"draws":13,"losses":13,"wins":154},"GB2-07":{"draws":0,"losses":18,"wins":176},"GB2-08":{"draws":37,"losses":54,"wins":97}},"medium":{"GB2-01":{"draws":19,"losses":17,"wins":142},"GB2-02":{"draws":138,"losses":12,"wins":9},"GB2-03":{"draws":86,"losses":51,"wins":39},"GB2-04":{"draws":107,"losses":47,"wins":30},"GB2-05":{"draws":0,"losses":87,"wins":129},"GB2-06":{"draws":12,"losses":13,"wins":149},"GB2-07":{"draws":0,"losses":95,"wins":105},"GB2-08":{"draws":92,"losses":54,"wins":59}},"none":{"GB2-01":{"draws":6,"losses":26,"wins":160},"GB2-02":{"draws":142,"losses":14,"wins":2},"GB2-03":{"draws":84,"losses":51,"wins":43},"GB2-04":{"draws":113,"losses":37,"wins":23},"GB2-05":{"draws":0,"losses":57,"wins":125},"GB2-06":{"draws":13,"losses":40,"wins":127},"GB2-07":{"draws":0,"losses":114,"wins":70},"GB2-08":{"draws":129,"losses":55,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1919.1664010665272,"GB2-02":1519.9162998282634,"GB2-03":1459.6667206452332,"GB2-04":1507.115604264735,"GB2-05":1785.450265338234,"GB2-06":1867.9977184597308,"GB2-07":1583.3169705797939,"GB2-08":1505.0185147287675},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1997.4300020219584,"GB2-02":1621.61381435049,"GB2-03":1442.7517819863665,"GB2-04":1619.9798243524701,"GB2-05":2021.4498788973235,"GB2-06":1955.9990288949302,"GB2-07":1930.5533799880245,"GB2-08":1632.292798608477},"medium":{"GB2-01":1869.548743151603,"GB2-02":1478.0972191858511,"GB2-03":1448.0849528487836,"GB2-04":1450.5740560255051,"GB2-05":1652.5584228156804,"GB2-06":1899.3144706102646,"GB2-07":1516.7622501223027,"GB2-08":1477.693698947328},"none":{"GB2-01":1890.5204580260204,"GB2-02":1460.0378659484488,"GB2-03":1488.1634271005496,"GB2-04":1450.7929324162299,"GB2-05":1682.3424943016976,"GB2-06":1748.6796558739966,"GB2-07":1302.6352816290546,"GB2-08":1405.0690466304977}},"per_game_tracks":{"highest":{"GB2-01":96.95590676313576,"GB2-02":54.7169870956697,"GB2-03":37.76802152050538,"GB2-04":61.22868483056382,"GB2-05":90.89912695137986,"GB2-06":88.93765075471762,"GB2-07":87.10047490567965,"GB2-08":55.54806206171865},"medium":{"GB2-01":83.87017034302815,"GB2-02":22.354981368587474,"GB2-03":38.977818353684654,"GB2-04":35.482620682862695,"GB2-05":60.47818486339551,"GB2-06":83.97561557170286,"GB2-07":48.214971045034304,"GB2-08":40.102704459070644},"none":{"GB2-01":86.15134182727353,"GB2-02":18.245710919802534,"GB2-03":44.46667985844482,"GB2-04":35.34395455370223,"GB2-05":62.68439698336576,"GB2-06":71.00824638840129,"GB2-07":27.903476569312414,"GB2-08":32.716762885001636}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":71.6443643604213,"medium":51.68213333592079,"none":47.31507124816302},"reasoning_agg":{"highest":{"max":96.95590676313576,"mean":71.6443643604213,"min":37.76802152050538},"medium":{"max":83.97561557170286,"mean":51.68213333592079,"min":22.354981368587474},"none":{"max":86.15134182727353,"mean":47.31507124816302,"min":18.245710919802534}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":96.95590676313576,"expected_score":58.124669281012984,"reasoning_variance":24.329293112258284,"reliability_score":91.45205440951408,"uncertainty_avg":8.547945590485925,"uncertainty_penalty":1.2441462995112715},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":96.95590676313576,"expected_score":65.71324795781588,"reliability_score":91.0310605954705,"uncertainty_avg":8.9689394045295,"uncertainty_penalty":-5.931116402605426},"medium":{"ceiling_score":83.97561557170286,"expected_score":52.38898748982911,"reliability_score":91.99233899564449,"uncertainty_avg":8.007661004355512,"uncertainty_penalty":0.7068541539083242},"none":{"ceiling_score":86.15134182727353,"expected_score":56.27177239539395,"reliability_score":91.33276363742723,"uncertainty_avg":8.667236362572766,"uncertainty_penalty":8.95670114723093}}},{"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":0.5964052},"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":0.5087456},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036000000001}},"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":0.5087456},"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":0.5947035999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052000000001}},"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":53.52834806313026,"highest":60.36479324487097,"medium":55.33875461534285,"none":44.88149632917695},"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":850,"losses":996,"wins":1563},"match_totals_tracks":{"highest":{"draws":251,"losses":358,"wins":685},"medium":{"draws":196,"losses":248,"wins":396},"none":{"draws":403,"losses":390,"wins":482}},"model_slug":"x-ai-grok-4-5","overall":{"max":89.63424632680322,"mean":53.52834806313026,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.96417402361442,"GB2-02":51.08735602238606,"GB2-03":41.15892215398935,"GB2-04":32.171720342982304,"GB2-05":71.55758103790589,"GB2-06":54.06333802227879,"GB2-07":62.28100802900767,"GB2-08":89.63424632680322},"per_game_all":{"GB2-01":67.08837383786071,"GB2-02":35.04856666113611,"GB2-03":29.362964074253807,"GB2-04":35.260039176061284,"GB2-05":59.71666653864628,"GB2-06":50.065942523074426,"GB2-07":65.23359235340767,"GB2-08":86.4506393406018},"per_game_match_totals_all":{"GB2-01":{"draws":174,"losses":76,"wins":231},"GB2-02":{"draws":254,"losses":49,"wins":66},"GB2-03":{"draws":138,"losses":193,"wins":67},"GB2-04":{"draws":242,"losses":91,"wins":64},"GB2-05":{"draws":0,"losses":172,"wins":247},"GB2-06":{"draws":39,"losses":212,"wins":216},"GB2-07":{"draws":0,"losses":142,"wins":282},"GB2-08":{"draws":3,"losses":61,"wins":390}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":19,"wins":119},"GB2-02":{"draws":72,"losses":24,"wins":48},"GB2-03":{"draws":68,"losses":56,"wins":34},"GB2-04":{"draws":64,"losses":54,"wins":36},"GB2-05":{"draws":0,"losses":41,"wins":101},"GB2-06":{"draws":13,"losses":82,"wins":87},"GB2-07":{"draws":0,"losses":62,"wins":104},"GB2-08":{"draws":2,"losses":20,"wins":156}},"medium":{"GB2-01":{"draws":8,"losses":21,"wins":73},"GB2-02":{"draws":69,"losses":16,"wins":13},"GB2-03":{"draws":28,"losses":26,"wins":24},"GB2-04":{"draws":82,"losses":16,"wins":12},"GB2-05":{"draws":0,"losses":46,"wins":70},"GB2-06":{"draws":8,"losses":62,"wins":52},"GB2-07":{"draws":0,"losses":47,"wins":65},"GB2-08":{"draws":1,"losses":14,"wins":87}},"none":{"GB2-01":{"draws":134,"losses":36,"wins":39},"GB2-02":{"draws":113,"losses":9,"wins":5},"GB2-03":{"draws":42,"losses":111,"wins":9},"GB2-04":{"draws":96,"losses":21,"wins":16},"GB2-05":{"draws":0,"losses":85,"wins":76},"GB2-06":{"draws":18,"losses":68,"wins":77},"GB2-07":{"draws":0,"losses":33,"wins":113},"GB2-08":{"draws":0,"losses":27,"wins":147}}},"per_game_raw_elo_all":{"GB2-01":1693.8276919383472,"GB2-02":1526.32143247362,"GB2-03":1371.0531338697438,"GB2-04":1442.338527718525,"GB2-05":1638.8513958096644,"GB2-06":1496.812005708923,"GB2-07":1691.6496380184242,"GB2-08":1929.9807914284038},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1829.172240589223,"GB2-02":1594.752196706652,"GB2-03":1453.345041387723,"GB2-04":1419.3352985192469,"GB2-05":1780.9418496208198,"GB2-06":1540.3129835742382,"GB2-07":1657.3711692973993,"GB2-08":1958.1843507591848},"medium":{"GB2-01":1777.1699941075071,"GB2-02":1492.6220047983245,"GB2-03":1508.9890080189186,"GB2-04":1479.3694583369315,"GB2-05":1660.642134309636,"GB2-06":1443.9671489840152,"GB2-07":1656.3784608491428,"GB2-08":1930.9765683598841},"none":{"GB2-01":1475.140841118312,"GB2-02":1491.590095915884,"GB2-03":1150.82535220259,"GB2-04":1428.310826299396,"GB2-05":1474.9702034985373,"GB2-06":1506.1558845685156,"GB2-07":1761.1992839087297,"GB2-08":1900.781455166142}},"per_game_tracks":{"highest":{"GB2-01":80.96417402361442,"GB2-02":51.08735602238606,"GB2-03":41.15892215398935,"GB2-04":32.171720342982304,"GB2-05":71.55758103790589,"GB2-06":54.06333802227879,"GB2-07":62.28100802900767,"GB2-08":89.63424632680322},"medium":{"GB2-01":74.81649706686221,"GB2-02":26.601192408895606,"GB2-03":46.92997006877206,"GB2-04":40.43774279100727,"GB2-05":61.274740553352146,"GB2-06":45.169198045990534,"GB2-07":61.55931257885285,"GB2-08":85.92138340901016},"none":{"GB2-01":45.4844504231055,"GB2-02":27.457151552126646,"GB2-03":0.0,"GB2-04":33.17065439419427,"GB2-05":46.31767802468079,"GB2-06":50.965291500953946,"GB2-07":71.8604564523625,"GB2-08":83.79628828599199}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":60.36479324487097,"medium":55.33875461534285,"none":44.881496329176954},"reasoning_agg":{"highest":{"max":89.63424632680322,"mean":60.36479324487097,"min":32.171720342982304},"medium":{"max":85.92138340901016,"mean":55.33875461534285,"min":26.601192408895606},"none":{"max":83.79628828599199,"mean":44.881496329176954,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":89.63424632680322,"expected_score":51.48618821541806,"reasoning_variance":15.483296915694012,"reliability_score":98.27975713574462,"uncertainty_avg":1.7202428642553824,"uncertainty_penalty":-2.042159847712199},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.63424632680322,"expected_score":48.131743162293574,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-12.233050082577392},"medium":{"ceiling_score":85.92138340901016,"expected_score":56.944062612635165,"reliability_score":94.89479313525375,"uncertainty_avg":5.105206864746245,"uncertainty_penalty":1.6053079972923143},"none":{"ceiling_score":83.79628828599199,"expected_score":49.382758871325436,"reliability_score":99.9444782719801,"uncertainty_avg":0.05552172801990163,"uncertainty_penalty":4.501262542148481}}},{"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":3.542855},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":21.885474999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":54.308742966073105,"highest":68.8969621273796,"medium":51.90534748551461,"none":39.74621893216972},"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":741,"losses":558,"wins":835},"match_totals_tracks":{"highest":{"draws":126,"losses":147,"wins":379},"medium":{"draws":261,"losses":224,"wins":301},"none":{"draws":354,"losses":187,"wins":155}},"model_slug":"gpt-5-5","overall":{"max":92.32704029193545,"mean":52.32719281804168,"min":22.09524395964808},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.70600935658693,"GB2-03":49.85325759783324,"GB2-04":27.370645611635616,"GB2-05":83.16542149104123,"GB2-06":84.82408848503748,"GB2-07":92.32704029193545,"GB2-08":72.03227205758726},"per_game_all":{"GB2-01":60.064115978288605,"GB2-03":41.3981182360817,"GB2-04":36.07501469772322,"GB2-05":66.90586162473954,"GB2-07":68.33340256588923,"GB2-08":53.0759446937163},"per_game_match_totals_all":{"GB2-01":{"draws":187,"losses":49,"wins":94},"GB2-02":{"draws":122,"losses":18,"wins":20},"GB2-03":{"draws":103,"losses":81,"wins":56},"GB2-04":{"draws":174,"losses":70,"wins":40},"GB2-05":{"draws":0,"losses":92,"wins":196},"GB2-06":{"draws":6,"losses":89,"wins":111},"GB2-07":{"draws":0,"losses":92,"wins":212},"GB2-08":{"draws":149,"losses":67,"wins":106}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":30,"losses":16,"wins":54},"GB2-03":{"draws":30,"losses":29,"wins":23},"GB2-04":{"draws":45,"losses":35,"wins":6},"GB2-05":{"draws":0,"losses":21,"wins":77},"GB2-06":{"draws":5,"losses":16,"wins":63},"GB2-07":{"draws":0,"losses":6,"wins":92},"GB2-08":{"draws":16,"losses":24,"wins":64}},"medium":{"GB2-01":{"draws":65,"losses":14,"wins":29},"GB2-02":{"draws":45,"losses":9,"wins":20},"GB2-03":{"draws":37,"losses":24,"wins":15},"GB2-04":{"draws":63,"losses":17,"wins":22},"GB2-05":{"draws":0,"losses":31,"wins":67},"GB2-06":{"draws":1,"losses":73,"wins":48},"GB2-07":{"draws":0,"losses":32,"wins":62},"GB2-08":{"draws":50,"losses":24,"wins":38}},"none":{"GB2-01":{"draws":92,"losses":19,"wins":11},"GB2-02":{"draws":77,"losses":9,"wins":0},"GB2-03":{"draws":36,"losses":28,"wins":18},"GB2-04":{"draws":66,"losses":18,"wins":12},"GB2-05":{"draws":0,"losses":40,"wins":52},"GB2-07":{"draws":0,"losses":54,"wins":58},"GB2-08":{"draws":83,"losses":19,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1629.853516992536,"GB2-03":1467.8440153283466,"GB2-04":1453.7691875133285,"GB2-05":1732.1013480510348,"GB2-07":1730.353121928231,"GB2-08":1605.1372664184364},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1756.676617437372,"GB2-03":1529.349657382233,"GB2-04":1398.6125264834243,"GB2-05":1927.4799055461476,"GB2-06":1909.8196476234893,"GB2-07":1985.8838134621776,"GB2-08":1793.2236111969223},"medium":{"GB2-01":1625.1613317167532,"GB2-02":1576.1121672722809,"GB2-03":1436.9850240219848,"GB2-04":1475.5304118625747,"GB2-05":1717.6614023179375,"GB2-06":1468.311575824817,"GB2-07":1740.3549601868879,"GB2-08":1602.1188603960716},"none":{"GB2-01":1507.7226018234821,"GB2-02":1475.225904404823,"GB2-03":1437.1973645808223,"GB2-04":1487.1646241939861,"GB2-05":1551.1627362890197,"GB2-07":1464.820592135627,"GB2-08":1420.0693276623153}},"per_game_tracks":{"highest":{"GB2-01":72.70600935658693,"GB2-03":49.85325759783324,"GB2-04":27.370645611635616,"GB2-05":83.16542149104123,"GB2-06":84.82408848503748,"GB2-07":92.32704029193545,"GB2-08":72.03227205758726},"medium":{"GB2-01":59.564351449683706,"GB2-02":43.99378748372811,"GB2-03":37.041752080817375,"GB2-04":39.63154205082826,"GB2-05":65.742104336769,"GB2-06":47.27455398323267,"GB2-07":69.14142074882011,"GB2-08":52.85326775023768},"none":{"GB2-01":47.92198712859516,"GB2-02":22.09524395964808,"GB2-03":37.29934502959449,"GB2-04":41.222856430705775,"GB2-05":51.810059046408426,"GB2-07":43.53174665691214,"GB2-08":34.342294273323965}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.63495154439632,"medium":51.90534748551461,"none":38.44127942421412},"reasoning_agg":{"highest":{"max":92.32704029193545,"mean":66.63495154439632,"min":27.370645611635616},"medium":{"max":69.14142074882011,"mean":51.90534748551461,"min":37.041752080817375},"none":{"max":51.810059046408426,"mean":38.44127942421412,"min":22.09524395964808}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":92.32704029193545,"expected_score":54.96932879396701,"reasoning_variance":28.193672120182192,"reliability_score":93.29351710005812,"uncertainty_avg":6.706482899941868,"uncertainty_penalty":2.642135975925328},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":92.32704029193545,"expected_score":61.40114595823443,"reliability_score":92.06842630353624,"uncertainty_avg":7.9315736964637535,"uncertainty_penalty":-5.2338055861618855},"medium":{"ceiling_score":69.14142074882011,"expected_score":52.96766414394867,"reliability_score":93.05707164527206,"uncertainty_avg":6.942928354727943,"uncertainty_penalty":1.0623166584340566},"none":{"ceiling_score":51.810059046408426,"expected_score":48.479844469085755,"reliability_score":93.52728580931831,"uncertainty_avg":6.472714190681681,"uncertainty_penalty":10.038565044871632}}},{"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":1.7435250000000002},"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":1.2628249999999999}},"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":7.44989}},"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":10.456240000000001},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":53.775357120885815,"highest":68.9455842674663,"medium":44.86814560751495,"none":46.4863977297371},"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":"2026-08-05T04:35:38Z","match_totals_all":{"draws":548,"losses":582,"wins":948},"match_totals_tracks":{"highest":{"draws":89,"losses":185,"wins":416},"medium":{"draws":299,"losses":204,"wins":263},"none":{"draws":160,"losses":193,"wins":269}},"model_slug":"claude-opus-4-8","overall":{"max":81.45539006883097,"mean":52.170096342650396,"min":16.344385607773184},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.000169538136674,"GB2-02":81.45539006883097,"GB2-04":65.49748409048952,"GB2-05":51.00200589427959,"GB2-06":77.69399608634865,"GB2-07":77.1003159963057,"GB2-08":71.86972819787296},"per_game_all":{"GB2-01":51.53493235457234,"GB2-02":38.83129477492346,"GB2-04":48.056857287173194,"GB2-05":46.80817080798306,"GB2-06":69.2707030093432,"GB2-07":64.05509901177821,"GB2-08":57.87044260042729},"per_game_match_totals_all":{"GB2-01":{"draws":58,"losses":99,"wins":133},"GB2-02":{"draws":172,"losses":15,"wins":53},"GB2-03":{"draws":38,"losses":15,"wins":11},"GB2-04":{"draws":184,"losses":44,"wins":58},"GB2-05":{"draws":0,"losses":176,"wins":164},"GB2-06":{"draws":12,"losses":70,"wins":184},"GB2-07":{"draws":0,"losses":94,"wins":198},"GB2-08":{"draws":84,"losses":69,"wins":147}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":36,"wins":54},"GB2-02":{"draws":32,"losses":5,"wins":49},"GB2-04":{"draws":37,"losses":17,"wins":44},"GB2-05":{"draws":0,"losses":65,"wins":55},"GB2-06":{"draws":2,"losses":18,"wins":64},"GB2-07":{"draws":0,"losses":21,"wins":73},"GB2-08":{"draws":0,"losses":23,"wins":77}},"medium":{"GB2-01":{"draws":17,"losses":39,"wins":38},"GB2-02":{"draws":72,"losses":5,"wins":1},"GB2-03":{"draws":38,"losses":15,"wins":11},"GB2-04":{"draws":87,"losses":12,"wins":5},"GB2-05":{"draws":0,"losses":56,"wins":66},"GB2-06":{"draws":1,"losses":22,"wins":69},"GB2-07":{"draws":0,"losses":34,"wins":68},"GB2-08":{"draws":84,"losses":21,"wins":5}},"none":{"GB2-01":{"draws":23,"losses":24,"wins":41},"GB2-02":{"draws":68,"losses":5,"wins":3},"GB2-04":{"draws":60,"losses":15,"wins":9},"GB2-05":{"draws":0,"losses":55,"wins":43},"GB2-06":{"draws":9,"losses":30,"wins":51},"GB2-07":{"draws":0,"losses":39,"wins":57},"GB2-08":{"draws":0,"losses":25,"wins":65}}},"per_game_raw_elo_all":{"GB2-01":1547.987233516333,"GB2-02":1551.4101597478427,"GB2-04":1532.232801164281,"GB2-05":1486.993922416336,"GB2-06":1728.8534950989117,"GB2-07":1685.624814884762,"GB2-08":1654.0141258904284},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1609.684924746103,"GB2-02":1739.7423942603561,"GB2-04":1645.9101696696405,"GB2-05":1536.317407962045,"GB2-06":1827.373724966149,"GB2-07":1824.9248359828734,"GB2-08":1792.3813910887834},"medium":{"GB2-01":1470.264528764638,"GB2-02":1451.7183503047993,"GB2-03":1445.7477631553459,"GB2-04":1470.653364825019,"GB2-05":1537.859169314774,"GB2-06":1799.7073501929144,"GB2-07":1681.4932621274972,"GB2-08":1395.7974788159802},"none":{"GB2-01":1564.0122470382578,"GB2-02":1462.7697346783725,"GB2-04":1480.1348689981835,"GB2-05":1386.8051899721886,"GB2-06":1559.4794101376715,"GB2-07":1550.4563465439146,"GB2-08":1773.8635077665217}},"per_game_tracks":{"highest":{"GB2-01":58.000169538136674,"GB2-02":81.45539006883097,"GB2-04":65.49748409048952,"GB2-05":51.00200589427959,"GB2-06":77.69399608634865,"GB2-07":77.1003159963057,"GB2-08":71.86972819787296},"medium":{"GB2-01":43.63359523406752,"GB2-02":16.344385607773184,"GB2-03":37.68653930194108,"GB2-04":38.94522426719343,"GB2-05":51.154684162643335,"GB2-06":75.46636108950283,"GB2-07":63.75494931550506,"GB2-08":31.959425881493154},"none":{"GB2-01":52.971032291512834,"GB2-02":18.694108648166214,"GB2-04":39.727863503836645,"GB2-05":38.26782236702627,"GB2-06":54.6517518521781,"GB2-07":51.31003172352387,"GB2-08":69.78217372191577}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.68197733259686,"medium":44.86814560751494,"none":44.96016608783939},"reasoning_agg":{"highest":{"max":81.45539006883097,"mean":66.68197733259686,"min":51.00200589427959},"medium":{"max":75.46636108950283,"mean":44.86814560751494,"min":16.344385607773184},"none":{"max":69.78217372191577,"mean":44.96016608783939,"min":18.694108648166214}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":81.45539006883097,"expected_score":54.35566155242917,"reasoning_variance":21.81383172508192,"reliability_score":92.67614311284633,"uncertainty_avg":7.323856887153669,"uncertainty_penalty":2.1855652097787726},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.45539006883097,"expected_score":63.76004128912357,"reliability_score":93.3947473157322,"uncertainty_avg":6.605252684267798,"uncertainty_penalty":-2.9219360434732877},"medium":{"ceiling_score":75.46636108950283,"expected_score":42.823882679189744,"reliability_score":92.24736078020972,"uncertainty_avg":7.752639219790286,"uncertainty_penalty":-2.044262928325196},"none":{"ceiling_score":69.78217372191577,"expected_score":51.70447960965244,"reliability_score":90.88421723190937,"uncertainty_avg":9.115782768090629,"uncertainty_penalty":6.744313521813048}}},{"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":7.63796235},"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":4.1696877},"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":0.8934513},"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":12.701101349999998},"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":55.919344385738654,"highest":66.24088892568601,"medium":56.609375270608496,"none":36.379050545107496},"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":1689,"losses":1878,"wins":2723},"match_totals_tracks":{"highest":{"draws":301,"losses":484,"wins":1039},"medium":{"draws":479,"losses":457,"wins":999},"none":{"draws":909,"losses":937,"wins":685}},"model_slug":"google-gemini-3-6-flash","overall":{"max":90.98102138726986,"mean":50.924643935954116,"min":16.214567763911244},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.590003923577925,"GB2-03":83.98010770719294,"GB2-04":58.999575365642215,"GB2-05":82.98344935650789,"GB2-06":90.98102138726986,"GB2-07":47.781451793024814,"GB2-08":49.370612946586476},"per_game_all":{"GB2-01":47.63015719312144,"GB2-03":60.48717987925185,"GB2-04":45.06446900266382,"GB2-05":67.57080287938746,"GB2-06":70.0354769233014,"GB2-07":51.3245903636045,"GB2-08":49.322734458840074},"per_game_match_totals_all":{"GB2-01":{"draws":271,"losses":347,"wins":308},"GB2-02":{"draws":311,"losses":27,"wins":2},"GB2-03":{"draws":187,"losses":226,"wins":303},"GB2-04":{"draws":483,"losses":167,"wins":187},"GB2-05":{"draws":0,"losses":274,"wins":679},"GB2-06":{"draws":70,"losses":279,"wins":602},"GB2-07":{"draws":0,"losses":341,"wins":418},"GB2-08":{"draws":367,"losses":217,"wins":224}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":92,"losses":117,"wins":113},"GB2-03":{"draws":11,"losses":23,"wins":88},"GB2-04":{"draws":77,"losses":90,"wins":135},"GB2-05":{"draws":0,"losses":44,"wins":244},"GB2-06":{"draws":14,"losses":46,"wins":254},"GB2-07":{"draws":0,"losses":74,"wins":88},"GB2-08":{"draws":107,"losses":90,"wins":117}},"medium":{"GB2-01":{"draws":97,"losses":44,"wins":115},"GB2-02":{"draws":82,"losses":5,"wins":1},"GB2-03":{"draws":69,"losses":113,"wins":88},"GB2-04":{"draws":188,"losses":37,"wins":30},"GB2-05":{"draws":0,"losses":82,"wins":242},"GB2-06":{"draws":21,"losses":21,"wins":266},"GB2-07":{"draws":0,"losses":120,"wins":166},"GB2-08":{"draws":22,"losses":35,"wins":91}},"none":{"GB2-01":{"draws":82,"losses":186,"wins":80},"GB2-02":{"draws":229,"losses":22,"wins":1},"GB2-03":{"draws":107,"losses":90,"wins":127},"GB2-04":{"draws":218,"losses":40,"wins":22},"GB2-05":{"draws":0,"losses":148,"wins":193},"GB2-06":{"draws":35,"losses":212,"wins":82},"GB2-07":{"draws":0,"losses":147,"wins":164},"GB2-08":{"draws":238,"losses":92,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1501.3208571338575,"GB2-03":1597.4025602163292,"GB2-04":1505.5729376550205,"GB2-05":1731.1974016214917,"GB2-06":1727.1223363815946,"GB2-07":1542.2460865182381,"GB2-08":1561.2086608412083},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1519.7173895347846,"GB2-03":1772.0196909880037,"GB2-04":1595.56223467484,"GB2-05":1918.3075744153398,"GB2-06":1969.472492857064,"GB2-07":1503.6788239490022,"GB2-08":1561.8662103116926},"medium":{"GB2-01":1726.9291590923472,"GB2-02":1448.5362643626052,"GB2-03":1498.3603963409328,"GB2-04":1450.1461491938412,"GB2-05":1770.0664811162064,"GB2-06":1956.8985581879415,"GB2-07":1565.677153651903,"GB2-08":1758.2226139935103},"none":{"GB2-01":1257.316022774441,"GB2-02":1445.4683467098837,"GB2-03":1521.8275933200516,"GB2-04":1471.01042909638,"GB2-05":1505.2181493329292,"GB2-06":1254.9959580997784,"GB2-07":1557.3822819538093,"GB2-08":1363.5371582184212}},"per_game_tracks":{"highest":{"GB2-01":49.590003923577925,"GB2-03":83.98010770719294,"GB2-04":58.999575365642215,"GB2-05":82.98344935650789,"GB2-06":90.98102138726986,"GB2-07":47.781451793024814,"GB2-08":49.370612946586476},"medium":{"GB2-01":70.09758000861065,"GB2-02":16.214567763911244,"GB2-03":46.93983383805609,"GB2-04":36.37827885826509,"GB2-05":70.83047446085692,"GB2-06":89.86912515095916,"GB2-07":53.4179924942283,"GB2-08":69.12714958998048},"none":{"GB2-01":23.202887647175736,"GB2-02":17.072829141107093,"GB2-03":50.541598092506504,"GB2-04":39.81555278408415,"GB2-05":48.89848482079757,"GB2-06":29.256284231675217,"GB2-07":52.7743268035604,"GB2-08":29.47044083995327}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":61.644093105485865,"medium":54.750788157268985,"none":36.37905054510748},"reasoning_agg":{"highest":{"max":90.98102138726986,"mean":61.644093105485865,"min":47.781451793024814},"medium":{"max":89.86912515095916,"mean":54.750788157268985,"min":16.214567763911244},"none":{"max":52.7743268035604,"mean":36.37905054510748,"min":17.072829141107093}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":90.98102138726986,"expected_score":56.91552359086476,"reasoning_variance":25.265042560378383,"reliability_score":99.74395838503206,"uncertainty_avg":0.25604161496793465,"uncertainty_penalty":5.990879654910643},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.98102138726986,"expected_score":59.330880523345904,"reliability_score":99.80950260951835,"uncertainty_avg":0.190497390481659,"uncertainty_penalty":-2.313212582139961},"medium":{"ceiling_score":89.86912515095916,"expected_score":57.609471602321186,"reliability_score":98.33833922734087,"uncertainty_avg":1.6616607726591277,"uncertainty_penalty":2.8586834450522005},"none":{"ceiling_score":52.7743268035604,"expected_score":40.85729381781698,"reliability_score":99.91665739166427,"uncertainty_avg":0.08334260833572582,"uncertainty_penalty":4.4782432727094985}}},{"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":2.7900240000000007},"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":3.9126165000000004}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":24,"cost_basis_counts":{"provider_reported":51},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.6921525,"mean":0.30153312499999996,"median":0.335163,"min":0.025422,"recorded_attempt_count":51,"run_count":24,"total":7.236795},"codegen_latency_ms":{"attempt_count":37,"max_ms":391025,"mean_ms":206292.5625,"min_ms":126419,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":391025,"mean_ms":243664.625,"min_ms":198838,"run_count":8},"medium":{"attempt_count":19,"max_ms":243355,"mean_ms":168920.5,"min_ms":126419,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":74213,"output_mean":43169.4375,"output_min":25565,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":74213,"output_mean":51048.625,"output_min":41983,"run_count":8},"medium":{"attempt_count":19,"output_max":52941,"output_mean":35290.25,"output_min":25565,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"highest":49.715987926047966,"medium":53.68699728666814},"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":393,"losses":391,"wins":498},"match_totals_tracks":{"highest":{"draws":153,"losses":198,"wins":185},"medium":{"draws":240,"losses":193,"wins":313}},"model_slug":"google-gemini-3-5-flash","overall":{"max":86.87039539493097,"mean":49.976468612854845,"min":21.612048110556422},"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":47.29777519993979,"GB2-04":33.44484317358223,"GB2-05":52.08084603218233,"GB2-06":82.05588219794666,"GB2-07":61.804532842080334,"GB2-08":21.612048110556422},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":11,"wins":77},"GB2-02":{"draws":74,"losses":10,"wins":10},"GB2-03":{"draws":86,"losses":27,"wins":33},"GB2-04":{"draws":87,"losses":54,"wins":49},"GB2-05":{"draws":0,"losses":109,"wins":103},"GB2-06":{"draws":16,"losses":29,"wins":125},"GB2-07":{"draws":0,"losses":95,"wins":101},"GB2-08":{"draws":130,"losses":56,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":56,"losses":12,"wins":10},"GB2-04":{"draws":30,"losses":38,"wins":22},"GB2-05":{"draws":0,"losses":55,"wins":45},"GB2-06":{"draws":5,"losses":17,"wins":62},"GB2-07":{"draws":0,"losses":42,"wins":46},"GB2-08":{"draws":62,"losses":34,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":11,"wins":77},"GB2-02":{"draws":74,"losses":10,"wins":10},"GB2-03":{"draws":30,"losses":15,"wins":23},"GB2-04":{"draws":57,"losses":16,"wins":27},"GB2-05":{"draws":0,"losses":54,"wins":58},"GB2-06":{"draws":11,"losses":12,"wins":63},"GB2-07":{"draws":0,"losses":53,"wins":55},"GB2-08":{"draws":68,"losses":22,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1511.688890303186,"GB2-04":1437.4852159713996,"GB2-05":1552.7470805088597,"GB2-06":1877.810620435143,"GB2-07":1663.7552103873281,"GB2-08":1296.1001435676862},"medium":{"GB2-01":1899.4210224251667,"GB2-02":1490.007826929545,"GB2-03":1577.6092570519809,"GB2-04":1552.5455372468282,"GB2-05":1553.2266000489765,"GB2-06":1868.3321704609657,"GB2-07":1543.7114866663292,"GB2-08":1332.5013086471351}},"per_game_tracks":{"highest":{"GB2-03":47.29777519993979,"GB2-04":33.44484317358223,"GB2-05":52.08084603218233,"GB2-06":82.05588219794666,"GB2-07":61.804532842080334,"GB2-08":21.612048110556422},"medium":{"GB2-01":86.87039539493097,"GB2-02":25.82657411049858,"GB2-03":55.84887374161656,"GB2-04":51.31859933665385,"GB2-05":52.301082285856566,"GB2-06":81.27954496028467,"GB2-07":50.89179952279148,"GB2-08":25.159108940712393}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.26593993904155,"medium":53.68699728666813},"reasoning_agg":{"highest":{"max":82.05588219794666,"mean":46.26593993904155,"min":21.612048110556422},"medium":{"max":86.87039539493097,"mean":53.68699728666813,"min":25.159108940712393}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":86.87039539493097,"reasoning_variance":7.421057347626579},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.05588219794666,"expected_score":35.70939456065681,"reliability_score":91.01328114924007,"uncertainty_avg":8.98671885075993,"uncertainty_penalty":-10.55654537838474},"medium":{"ceiling_score":86.87039539493097,"expected_score":57.04552015143046,"reliability_score":91.85114701047715,"uncertainty_avg":8.148852989522858,"uncertainty_penalty":3.358522864762328}}},{"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":0.6080262}},"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":2.3233295999999997},"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":7.1402928},"codegen_latency_ms":{"attempt_count":40,"max_ms":1201344,"mean_ms":515468.5833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":1201344,"mean_ms":973286.5,"min_ms":605299,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":40000,"output_mean":17970.666666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":40000,"output_mean":33312.25,"output_min":20000,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":45.75739189471031,"highest":52.396363285760984,"medium":46.486279873467986,"none":52.16308170204557},"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":1040,"losses":976,"wins":1361},"match_totals_tracks":{"highest":{"draws":233,"losses":193,"wins":330},"medium":{"draws":391,"losses":406,"wins":428},"none":{"draws":416,"losses":377,"wins":603}},"model_slug":"moonshotai-kimi-k3","overall":{"max":96.03018425662745,"mean":48.93950951309686,"min":19.758668893473487},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":10,"overall_ranking_status":"partial","per_game":{"GB2-01":61.26830836120785,"GB2-02":23.676197661918458,"GB2-03":38.53169274626354,"GB2-04":80.31858860898552,"GB2-07":58.18702905042954},"per_game_all":{"GB2-01":58.001000452416314,"GB2-02":22.111718248933204,"GB2-03":54.190178062165906,"GB2-04":56.22134036098647,"GB2-07":38.262722349049646},"per_game_match_totals_all":{"GB2-01":{"draws":172,"losses":139,"wins":202},"GB2-02":{"draws":327,"losses":40,"wins":21},"GB2-03":{"draws":149,"losses":96,"wins":167},"GB2-04":{"draws":222,"losses":67,"wins":152},"GB2-05":{"draws":0,"losses":135,"wins":226},"GB2-06":{"draws":36,"losses":144,"wins":194},"GB2-07":{"draws":0,"losses":301,"wins":217},"GB2-08":{"draws":134,"losses":54,"wins":182}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":59,"wins":98},"GB2-02":{"draws":112,"losses":12,"wins":6},"GB2-03":{"draws":57,"losses":35,"wins":28},"GB2-04":{"draws":47,"losses":19,"wins":86},"GB2-07":{"draws":0,"losses":68,"wins":112}},"medium":{"GB2-01":{"draws":16,"losses":48,"wins":72},"GB2-02":{"draws":79,"losses":18,"wins":7},"GB2-03":{"draws":52,"losses":21,"wins":61},"GB2-04":{"draws":94,"losses":17,"wins":22},"GB2-05":{"draws":0,"losses":70,"wins":106},"GB2-06":{"draws":16,"losses":74,"wins":100},"GB2-07":{"draws":0,"losses":112,"wins":48},"GB2-08":{"draws":134,"losses":46,"wins":12}},"none":{"GB2-01":{"draws":139,"losses":32,"wins":32},"GB2-02":{"draws":136,"losses":10,"wins":8},"GB2-03":{"draws":40,"losses":40,"wins":78},"GB2-04":{"draws":81,"losses":31,"wins":44},"GB2-05":{"draws":0,"losses":65,"wins":120},"GB2-06":{"draws":20,"losses":70,"wins":94},"GB2-07":{"draws":0,"losses":121,"wins":57},"GB2-08":{"draws":0,"losses":8,"wins":170}}},"per_game_raw_elo_all":{"GB2-01":1602.1857832209068,"GB2-02":1467.7857940222975,"GB2-03":1551.4499603378943,"GB2-04":1577.8278955826793,"GB2-07":1401.5885242066524},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1633.9448139210695,"GB2-02":1474.3344994862955,"GB2-03":1438.701374575963,"GB2-04":1735.222095654677,"GB2-07":1612.648077127973},"medium":{"GB2-01":1694.6446506662096,"GB2-02":1460.9653251764248,"GB2-03":1644.1494064849203,"GB2-04":1483.9182974099629,"GB2-05":1544.3586605576277,"GB2-06":1661.6059928496998,"GB2-07":1302.1666353464232,"GB2-08":1378.0442055713736},"none":{"GB2-01":1477.9678850754415,"GB2-02":1468.0575574041725,"GB2-03":1571.4990999527986,"GB2-04":1514.343293683398,"GB2-05":1633.2331677471427,"GB2-06":1623.3658987890403,"GB2-07":1289.9508601455611,"GB2-08":2021.4459228627536}},"per_game_tracks":{"highest":{"GB2-01":61.26830836120785,"GB2-02":23.676197661918458,"GB2-03":38.53169274626354,"GB2-04":80.31858860898552,"GB2-07":58.18702905042954},"medium":{"GB2-01":67.00524526280067,"GB2-02":19.758668893473487,"GB2-03":66.78378455408968,"GB2-04":41.65185972817385,"GB2-05":52.19271965091757,"GB2-06":64.6071323338313,"GB2-07":28.7988247426727,"GB2-08":31.092003821784623},"none":{"GB2-01":45.72944773324043,"GB2-02":22.900288191407675,"GB2-03":57.255056886144494,"GB2-04":46.69357274580004,"GB2-05":59.63400603920557,"GB2-06":61.25978450989219,"GB2-07":27.802313254046688,"GB2-08":96.03018425662745}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.169166963777016,"medium":46.486279873467986,"none":52.163081702045574},"reasoning_agg":{"highest":{"max":80.31858860898552,"mean":48.169166963777016,"min":23.676197661918458},"medium":{"max":67.00524526280067,"mean":46.486279873467986,"min":19.758668893473487},"none":{"max":96.03018425662745,"mean":52.163081702045574,"min":22.900288191407675}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":96.03018425662745,"expected_score":45.08598986628671,"reasoning_variance":5.676801828577588,"reliability_score":99.55003005986852,"uncertainty_avg":0.4499699401314749,"uncertainty_penalty":-3.853519646810149},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.31858860898552,"expected_score":38.09691607829169,"reliability_score":99.6590909090909,"uncertainty_avg":0.3409090909090917,"uncertainty_penalty":-10.072250885485325},"medium":{"ceiling_score":67.00524526280067,"expected_score":45.42154229678903,"reliability_score":99.36937454407166,"uncertainty_avg":0.6306254559283331,"uncertainty_penalty":-1.064737576678958},"none":{"ceiling_score":96.03018425662745,"expected_score":62.10351693745986,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":9.940435235414284}}},{"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":0.37616799999999995},"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":0.1914105}},"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":53.589806561025966,"highest":51.295019038484355,"medium":53.00511108061398,"none":39.04345088587002},"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":323,"losses":527,"wins":625},"match_totals_tracks":{"highest":{"draws":22,"losses":71,"wins":89},"medium":{"draws":135,"losses":157,"wins":309},"none":{"draws":166,"losses":299,"wins":227}},"model_slug":"meta-muse-spark-1-2","overall":{"max":80.14955515143204,"mean":47.20110944537896,"min":16.50878695816217},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":11,"overall_ranking_status":"partial","per_game":{"GB2-01":53.82210709138648,"GB2-03":48.767930985582225},"per_game_all":{"GB2-01":55.721102630804666,"GB2-03":51.458510491247274},"per_game_match_totals_all":{"GB2-01":{"draws":46,"losses":93,"wins":131},"GB2-02":{"draws":107,"losses":14,"wins":14},"GB2-03":{"draws":56,"losses":100,"wins":122},"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":7,"losses":37,"wins":46},"GB2-03":{"draws":15,"losses":34,"wins":43}},"medium":{"GB2-01":{"draws":0,"losses":12,"wins":76},"GB2-02":{"draws":50,"losses":6,"wins":11},"GB2-03":{"draws":29,"losses":30,"wins":35},"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":39,"losses":44,"wins":9},"GB2-02":{"draws":57,"losses":8,"wins":3},"GB2-03":{"draws":12,"losses":36,"wins":44},"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":1590.7586742743142,"GB2-03":1538.5591068574097},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1571.9644721957648,"GB2-03":1518.9551554503532},"medium":{"GB2-01":1832.923348449229,"GB2-02":1509.5573026507243,"GB2-03":1547.3955110326083,"GB2-04":1411.1381799035316,"GB2-05":1554.8886887946508,"GB2-07":1713.3713882243446,"GB2-08":1697.4882744755037},"none":{"GB2-01":1367.3882021779489,"GB2-02":1455.6017691862596,"GB2-03":1549.3266540892673,"GB2-04":1482.7694515360909,"GB2-05":1565.788333723547,"GB2-06":1250.7317045501534,"GB2-07":1339.6829441858488,"GB2-08":1653.2616124943645}},"per_game_tracks":{"highest":{"GB2-01":53.82210709138648,"GB2-03":48.767930985582225},"medium":{"GB2-01":80.14955515143204,"GB2-02":28.53778014221482,"GB2-03":52.70215835783597,"GB2-04":28.86928741865205,"GB2-05":52.15591097203426,"GB2-07":66.56068088153548,"GB2-08":62.06040464059319},"none":{"GB2-01":33.19164564959547,"GB2-02":16.50878695816217,"GB2-03":52.90544213032362,"GB2-04":39.7944295068769,"GB2-05":53.02456786594432,"GB2-06":28.027781786573513,"GB2-07":31.305998996116344,"GB2-08":57.58895419336781}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.295019038484355,"medium":51.26485841178252,"none":39.043450885870016},"reasoning_agg":{"highest":{"max":53.82210709138648,"mean":51.295019038484355,"min":48.767930985582225},"medium":{"max":80.14955515143204,"mean":51.26485841178252,"min":28.53778014221482},"none":{"max":57.58895419336781,"mean":39.043450885870016,"min":16.50878695816217}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":80.14955515143204,"expected_score":53.44915295028345,"reasoning_variance":12.25156815261434,"reliability_score":91.70736539162743,"uncertainty_avg":8.29263460837257,"uncertainty_penalty":6.248043504904487},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.82210709138648,"expected_score":35.274478079440584,"reliability_score":91.61908671369142,"uncertainty_avg":8.380913286308589,"uncertainty_penalty":-16.02054095904377},"medium":{"ceiling_score":80.14955515143204,"expected_score":54.91389972813363,"reliability_score":89.82517853280675,"uncertainty_avg":10.174821467193258,"uncertainty_penalty":3.6490413163511093},"none":{"ceiling_score":57.58895419336781,"expected_score":46.599729719843886,"reliability_score":90.07137219713263,"uncertainty_avg":9.928627802867371,"uncertainty_penalty":7.55627883397387}}},{"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":65.32801249999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.24673750000000003,"mean":0.16744,"median":0.15809499999999999,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":1.3395199999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":1.3395199999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063375000000001},"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":65.32801249999999}},"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":47.51080673249359,"highest":58.104311412434335,"medium":42.52513592340232,"none":41.9029728616441},"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":756,"losses":740,"wins":804},"match_totals_tracks":{"highest":{"draws":157,"losses":234,"wins":341},"medium":{"draws":290,"losses":254,"wins":250},"none":{"draws":309,"losses":252,"wins":213}},"model_slug":"gpt-5-6-terra","overall":{"max":72.91627837470821,"mean":47.10551480154788,"min":25.970772760443374},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.410294640288974,"GB2-02":46.84121932685183,"GB2-03":60.60474629403735,"GB2-04":53.506645149871794,"GB2-05":62.53998912556835,"GB2-06":72.24215339252389,"GB2-07":72.91627837470821,"GB2-08":54.77316499562428},"per_game_all":{"GB2-01":45.430284661400435,"GB2-02":33.73702499370265,"GB2-03":50.51211825609266,"GB2-04":48.192940667206415,"GB2-05":57.53576472191228,"GB2-06":53.6639161159301,"GB2-07":48.8448629535759,"GB2-08":42.16954149012824},"per_game_match_totals_all":{"GB2-01":{"draws":95,"losses":112,"wins":91},"GB2-02":{"draws":219,"losses":38,"wins":23},"GB2-03":{"draws":90,"losses":65,"wins":65},"GB2-04":{"draws":196,"losses":33,"wins":53},"GB2-05":{"draws":0,"losses":125,"wins":175},"GB2-06":{"draws":14,"losses":129,"wins":153},"GB2-07":{"draws":0,"losses":148,"wins":168},"GB2-08":{"draws":142,"losses":90,"wins":76}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":31,"losses":42,"wins":29},"GB2-02":{"draws":52,"losses":20,"wins":18},"GB2-03":{"draws":15,"losses":16,"wins":31},"GB2-04":{"draws":44,"losses":18,"wins":32},"GB2-05":{"draws":0,"losses":42,"wins":56},"GB2-06":{"draws":0,"losses":34,"wins":58},"GB2-07":{"draws":0,"losses":29,"wins":65},"GB2-08":{"draws":15,"losses":33,"wins":52}},"medium":{"GB2-01":{"draws":34,"losses":31,"wins":33},"GB2-02":{"draws":76,"losses":9,"wins":1},"GB2-03":{"draws":39,"losses":25,"wins":14},"GB2-04":{"draws":76,"losses":9,"wins":13},"GB2-05":{"draws":0,"losses":45,"wins":65},"GB2-06":{"draws":12,"losses":42,"wins":48},"GB2-07":{"draws":0,"losses":59,"wins":55},"GB2-08":{"draws":53,"losses":34,"wins":21}},"none":{"GB2-01":{"draws":30,"losses":39,"wins":29},"GB2-02":{"draws":91,"losses":9,"wins":4},"GB2-03":{"draws":36,"losses":24,"wins":20},"GB2-04":{"draws":76,"losses":6,"wins":8},"GB2-05":{"draws":0,"losses":38,"wins":54},"GB2-06":{"draws":2,"losses":53,"wins":47},"GB2-07":{"draws":0,"losses":60,"wins":48},"GB2-08":{"draws":74,"losses":23,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1486.94102126944,"GB2-02":1525.50265119967,"GB2-03":1536.8947435165935,"GB2-04":1533.3078500627232,"GB2-05":1618.5178564210782,"GB2-06":1546.2270500362545,"GB2-07":1522.532159158888,"GB2-08":1498.1237171193325},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1446.6406737765797,"GB2-02":1584.5440638410278,"GB2-03":1614.760774095997,"GB2-04":1568.1292217619282,"GB2-05":1679.100259521219,"GB2-06":1762.4255362201798,"GB2-07":1780.4659593446845,"GB2-08":1623.2810218217542},"medium":{"GB2-01":1468.1014264525709,"GB2-02":1492.4957620772557,"GB2-03":1480.6473394621028,"GB2-04":1510.6341572765252,"GB2-05":1609.1466507381233,"GB2-06":1502.2749957494511,"GB2-07":1379.3006758761821,"GB2-08":1480.0543554717117},"none":{"GB2-01":1546.0809635791695,"GB2-02":1499.4681276807262,"GB2-03":1515.2761169916803,"GB2-04":1521.160171149716,"GB2-05":1567.3066590038927,"GB2-06":1373.9806181391325,"GB2-07":1407.8298422557973,"GB2-08":1391.0357740645313}},"per_game_tracks":{"highest":{"GB2-01":41.410294640288974,"GB2-02":46.84121932685183,"GB2-03":60.60474629403735,"GB2-04":53.506645149871794,"GB2-05":62.53998912556835,"GB2-06":72.24215339252389,"GB2-07":72.91627837470821,"GB2-08":54.77316499562428},"medium":{"GB2-01":43.49963047361349,"GB2-02":25.970772760443374,"GB2-03":43.06898280210667,"GB2-04":44.865298973012386,"GB2-05":56.91665552510462,"GB2-06":49.922377861903456,"GB2-07":35.51437146013137,"GB2-08":40.442997530903185},"none":{"GB2-01":51.380928870298845,"GB2-02":28.399082893812732,"GB2-03":47.862625672133966,"GB2-04":46.206877878735085,"GB2-05":53.15064951506388,"GB2-06":38.82721709336295,"GB2-07":38.10393902588812,"GB2-08":31.292461943857255}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":58.10431141243433,"medium":42.525135923402324,"none":40.68709706880698},"reasoning_agg":{"highest":{"max":72.91627837470821,"mean":58.10431141243433,"min":41.410294640288974},"medium":{"max":56.91665552510462,"mean":42.525135923402324,"min":25.970772760443374},"none":{"max":53.15064951506388,"mean":40.68709706880698,"min":28.399082893812732}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.91627837470821,"expected_score":46.91914200730853,"reasoning_variance":17.41721434362735,"reliability_score":92.6457253875402,"uncertainty_avg":7.3542746124598,"uncertainty_penalty":-0.18637279423935382},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.91627837470821,"expected_score":49.05473034687004,"reliability_score":91.35950565029019,"uncertainty_avg":8.640494349709813,"uncertainty_penalty":-9.04958106556429},"medium":{"ceiling_score":56.91665552510462,"expected_score":40.830068128865236,"reliability_score":93.54940978962188,"uncertainty_avg":6.450590210378126,"uncertainty_penalty":-1.6950677945370884},"none":{"ceiling_score":53.15064951506388,"expected_score":50.87262754619031,"reliability_score":93.02826072270854,"uncertainty_avg":6.97173927729146,"uncertainty_penalty":10.185530477383331}}},{"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":0.97393}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.4245200000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-08-08":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785000000003},"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":46.60302574146441,"highest":42.08032376046519,"medium":50.773332684552884,"none":46.955420779375146},"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":998,"losses":1128,"wins":1331},"match_totals_tracks":{"highest":{"draws":373,"losses":485,"wins":470},"medium":{"draws":347,"losses":421,"wins":579},"none":{"draws":278,"losses":222,"wins":282}},"model_slug":"claude-opus-4-5","overall":{"max":82.15300774815739,"mean":46.6030257414644,"min":13.32462959183295},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":13,"overall_ranking_status":"partial","per_game":{"GB2-01":63.991356251926845,"GB2-02":13.32462959183295,"GB2-03":39.20269156862466,"GB2-04":35.688547830022806,"GB2-05":49.55470457849347,"GB2-06":59.34143229501704,"GB2-07":47.705624366124106,"GB2-08":27.83360360167963},"per_game_all":{"GB2-01":53.604631665313036,"GB2-02":20.32970227175244,"GB2-03":45.03967815662429,"GB2-04":42.067406156160786,"GB2-05":52.59856677126553,"GB2-06":51.322424894428764,"GB2-07":48.05354291148814,"GB2-08":59.80825310468225},"per_game_match_totals_all":{"GB2-01":{"draws":154,"losses":105,"wins":190},"GB2-02":{"draws":310,"losses":44,"wins":8},"GB2-03":{"draws":180,"losses":127,"wins":95},"GB2-04":{"draws":209,"losses":89,"wins":42},"GB2-05":{"draws":0,"losses":217,"wins":289},"GB2-06":{"draws":38,"losses":197,"wins":235},"GB2-07":{"draws":0,"losses":232,"wins":244},"GB2-08":{"draws":107,"losses":117,"wins":228}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":26,"losses":36,"wins":91},"GB2-02":{"draws":107,"losses":22,"wins":1},"GB2-03":{"draws":41,"losses":64,"wins":47},"GB2-04":{"draws":83,"losses":59,"wins":17},"GB2-05":{"draws":0,"losses":86,"wins":114},"GB2-06":{"draws":17,"losses":71,"wins":90},"GB2-07":{"draws":0,"losses":77,"wins":93},"GB2-08":{"draws":99,"losses":70,"wins":17}},"medium":{"GB2-01":{"draws":51,"losses":43,"wins":84},"GB2-02":{"draws":125,"losses":11,"wins":2},"GB2-03":{"draws":77,"losses":48,"wins":35},"GB2-04":{"draws":76,"losses":16,"wins":11},"GB2-05":{"draws":0,"losses":91,"wins":109},"GB2-06":{"draws":16,"losses":82,"wins":98},"GB2-07":{"draws":0,"losses":102,"wins":94},"GB2-08":{"draws":2,"losses":28,"wins":146}},"none":{"GB2-01":{"draws":77,"losses":26,"wins":15},"GB2-02":{"draws":78,"losses":11,"wins":5},"GB2-03":{"draws":62,"losses":15,"wins":13},"GB2-04":{"draws":50,"losses":14,"wins":14},"GB2-05":{"draws":0,"losses":40,"wins":66},"GB2-06":{"draws":5,"losses":44,"wins":47},"GB2-07":{"draws":0,"losses":53,"wins":57},"GB2-08":{"draws":6,"losses":19,"wins":65}}},"per_game_raw_elo_all":{"GB2-01":1560.814076530365,"GB2-02":1461.1122053729798,"GB2-03":1485.3743904096943,"GB2-04":1490.704619064112,"GB2-05":1550.8792278821722,"GB2-06":1512.0540556608819,"GB2-07":1507.5909016362627,"GB2-08":1667.0304562150623},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1662.883091394821,"GB2-02":1428.2065730933373,"GB2-03":1439.6013043122741,"GB2-04":1441.887567292159,"GB2-05":1510.738619126404,"GB2-06":1601.6726322378718,"GB2-07":1502.1314410426282,"GB2-08":1346.2739670506865},"medium":{"GB2-01":1593.5115898273448,"GB2-02":1466.4846616121374,"GB2-03":1498.8789320043286,"GB2-04":1477.6181811749257,"GB2-05":1557.6899839620967,"GB2-06":1500.9782452617544,"GB2-07":1557.3437342280079,"GB2-08":1884.3566176372763},"none":{"GB2-01":1426.0475483689286,"GB2-02":1488.645381413465,"GB2-03":1517.64293491248,"GB2-04":1552.6081087252508,"GB2-05":1584.2090805580165,"GB2-06":1433.511289483019,"GB2-07":1463.297529638152,"GB2-08":1770.4607839572238}},"per_game_tracks":{"highest":{"GB2-01":63.991356251926845,"GB2-02":13.32462959183295,"GB2-03":39.20269156862466,"GB2-04":35.688547830022806,"GB2-05":49.55470457849347,"GB2-06":59.34143229501704,"GB2-07":47.705624366124106,"GB2-08":27.83360360167963},"medium":{"GB2-01":57.216109384642444,"GB2-02":22.143649514386354,"GB2-03":47.38893238646811,"GB2-04":39.978937009585955,"GB2-05":53.45354337379487,"GB2-06":50.754127680852754,"GB2-07":53.09835437853516,"GB2-08":82.15300774815739},"none":{"GB2-01":39.60642935936982,"GB2-02":25.52082770903801,"GB2-03":48.527410514780094,"GB2-04":50.534733628873596,"GB2-05":54.787452361508244,"GB2-06":43.871714707416494,"GB2-07":43.356649989805135,"GB2-08":69.43814796420975}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.080323760465184,"medium":50.773332684552884,"none":46.955420779375146},"reasoning_agg":{"highest":{"max":63.991356251926845,"mean":42.080323760465184,"min":13.32462959183295},"medium":{"max":82.15300774815739,"mean":50.773332684552884,"min":22.143649514386354},"none":{"max":69.43814796420975,"mean":46.955420779375146,"min":25.52082770903801}},"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":82.15300774815739,"expected_score":44.24198843690072,"reasoning_variance":8.6930089240877,"reliability_score":97.49759218936265,"uncertainty_avg":2.5024078106373504,"uncertainty_penalty":-2.3610373045636806},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":63.991356251926845,"expected_score":25.710219727490344,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-16.37010403297484},"medium":{"ceiling_score":82.15300774815739,"expected_score":49.60279054921557,"reliability_score":99.34012077693176,"uncertainty_avg":0.6598792230682515,"uncertainty_penalty":-1.170542135337314},"none":{"ceiling_score":69.43814796420975,"expected_score":57.41295503399626,"reliability_score":93.1526557911562,"uncertainty_avg":6.8473442088438,"uncertainty_penalty":10.457534254621116}}},{"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":0.5271659940000001},"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":0.35917138039999996}},"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":0.35917138039999996},"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":44.1620380231494,"highest":51.704133366709385,"medium":42.11595469371871,"none":42.11163766096654},"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":700,"losses":641,"wins":655},"match_totals_tracks":{"highest":{"draws":80,"losses":69,"wins":95},"medium":{"draws":234,"losses":164,"wins":182},"none":{"draws":386,"losses":408,"wins":378}},"model_slug":"z-ai-glm-5-2","overall":{"max":65.44552694683463,"mean":45.31057524046488,"min":16.009458011887702},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","below_generation_quality_threshold"],"overall_official_rank":14,"overall_ranking_status":"partial","per_game":{"GB2-03":51.704133366709385},"per_game_all":{"GB2-03":44.1620380231494},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":106,"wins":94},"GB2-02":{"draws":181,"losses":10,"wins":1},"GB2-03":{"draws":179,"losses":113,"wins":122},"GB2-04":{"draws":149,"losses":39,"wins":32},"GB2-05":{"draws":0,"losses":124,"wins":126},"GB2-06":{"draws":25,"losses":90,"wins":107},"GB2-07":{"draws":0,"losses":117,"wins":117},"GB2-08":{"draws":130,"losses":42,"wins":56}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":80,"losses":69,"wins":95}},"medium":{"GB2-01":{"draws":7,"losses":30,"wins":43},"GB2-02":{"draws":63,"losses":1,"wins":0},"GB2-03":{"draws":40,"losses":11,"wins":3},"GB2-04":{"draws":49,"losses":10,"wins":7},"GB2-05":{"draws":0,"losses":42,"wins":42},"GB2-06":{"draws":9,"losses":25,"wins":38},"GB2-07":{"draws":0,"losses":34,"wins":48},"GB2-08":{"draws":66,"losses":11,"wins":1}},"none":{"GB2-01":{"draws":29,"losses":76,"wins":51},"GB2-02":{"draws":118,"losses":9,"wins":1},"GB2-03":{"draws":59,"losses":33,"wins":24},"GB2-04":{"draws":100,"losses":29,"wins":25},"GB2-05":{"draws":0,"losses":82,"wins":84},"GB2-06":{"draws":16,"losses":65,"wins":69},"GB2-07":{"draws":0,"losses":83,"wins":69},"GB2-08":{"draws":64,"losses":31,"wins":55}}},"per_game_raw_elo_all":{"GB2-03":1491.0355458952456},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1535.1007128451727},"medium":{"GB2-01":1437.7540280999642,"GB2-02":1468.1999436475344,"GB2-03":1442.1124041249502,"GB2-04":1489.7254504864673,"GB2-05":1563.1378187943271,"GB2-06":1689.1739025328532,"GB2-07":1539.4625749629602,"GB2-08":1412.1516499621744},"none":{"GB2-01":1325.5609213423263,"GB2-02":1454.8538739796686,"GB2-03":1495.8935207156142,"GB2-04":1504.1231788792588,"GB2-05":1518.119904446422,"GB2-06":1599.5647166016763,"GB2-07":1519.489111184017,"GB2-08":1586.4595448981868}},"per_game_tracks":{"highest":{"GB2-03":51.704133366709385},"medium":{"GB2-01":40.0036272413998,"GB2-02":19.008405115879473,"GB2-03":36.602494823476015,"GB2-04":40.35454880564338,"GB2-05":52.64602705866004,"GB2-06":65.44552694683463,"GB2-07":49.96560708699275,"GB2-08":32.90140047086365},"none":{"GB2-01":28.603518652489697,"GB2-02":16.009458011887702,"GB2-03":44.17948587926281,"GB2-04":43.08531679812856,"GB2-05":48.88616759311684,"GB2-06":57.774334362784295,"GB2-07":47.92684620493954,"GB2-08":50.42797378512286}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.704133366709385,"medium":42.11595469371872,"none":42.11163766096654},"reasoning_agg":{"highest":{"max":51.704133366709385,"mean":51.704133366709385,"min":51.704133366709385},"medium":{"max":65.44552694683463,"mean":42.11595469371872,"min":19.008405115879473},"none":{"max":57.774334362784295,"mean":42.11163766096654,"min":16.009458011887702}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.44552694683463,"expected_score":38.29428065976908,"reasoning_variance":9.592495705742849,"reliability_score":84.53984411385169,"uncertainty_avg":15.460155886148309,"uncertainty_penalty":-7.016294580695799},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.704133366709385,"expected_score":24.262081786147714,"reliability_score":98.66204749772938,"uncertainty_avg":1.3379525022706273,"uncertainty_penalty":-27.44205158056167},"medium":{"ceiling_score":65.44552694683463,"expected_score":40.63843494481459,"reliability_score":85.00408195393597,"uncertainty_avg":14.99591804606404,"uncertainty_penalty":-1.477519748904129},"none":{"ceiling_score":57.774334362784295,"expected_score":50.85514514493471,"reliability_score":85.43015669601063,"uncertainty_avg":14.569843303989368,"uncertainty_penalty":8.743507483968173}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:351ed472be23eda4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":18,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":19},"evidence_basis":"Standard list-price estimate","max":0.48068,"mean":0.36446575,"median":0.3730325,"min":0.22767700000000002,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":17},"run_count":18,"token_priced_attempt_count":19,"total":6.692412},"medium":{"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":0.107477,"mean":0.071838625,"median":0.0695145,"min":0.054787,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":16,"token_priced_attempt_count":17,"total":1.149418},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"estimated":1,"local_list_price_estimate":16,"provider_dashboard_reconciled":1},"evidence_basis":"Combined: Provider-reported + Recorded attempt + Standard list-price estimate","max":0.078265,"mean":0.06253833333333332,"median":0.0614995,"min":0.050688,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"recorded_attempt_count":2,"run_count":17,"token_priced_attempt_count":16,"total":1.07324}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.132112,"mean":0.0780535,"median":0.06797,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.624428},"historical-provider-setting-baseline-variant-1":{"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},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.07806,"mean":0.06121625,"median":0.061152,"min":0.049788,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.48973},"historical-provider-setting-baseline-variant-3":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"provider_dashboard_reconciled":1},"evidence_basis":"Combined: Provider-reported + Recorded attempt","max":0.09014,"mean":0.09014,"median":0.09014,"min":0.09014,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":1},"recorded_attempt_count":2,"run_count":1,"total":0.09014},"historical-provider-setting-intensive-variant-1":{"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},"historical-provider-setting-intensive-variant-2":{"admitted_cell_count":2,"cell_count":1,"cost_basis_counts":{"local_list_price_estimate":3},"evidence_basis":"Standard list-price estimate","max":0.469661,"mean":0.469661,"median":0.469661,"min":0.469661,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":1},"run_count":2,"token_priced_attempt_count":3,"total":0.939322},"historical-provider-setting-intensive-variant-3":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.4567,"mean":0.36814250000000004,"median":0.355077,"min":0.234622,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.94514}},"codegen_cost_usd":{"admitted_cell_count":50,"cell_count":24,"cost_basis_counts":{"estimated":1,"local_list_price_estimate":52,"provider_dashboard_reconciled":1},"evidence_basis":"Combined: Provider-reported + Recorded attempt + Standard list-price estimate","failed_cell_count":1,"max":0.48068,"mean":0.1662809027777778,"median":0.07628299999999999,"min":0.050688,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":51},"recorded_attempt_count":2,"run_count":51,"token_priced_attempt_count":52,"total":8.91507},"codegen_latency_ms":{"attempt_count":29,"max_ms":590864,"mean_ms":143367.25925925927,"min_ms":2034,"run_count":27},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":590864,"mean_ms":331567.4,"min_ms":185272,"run_count":10},"medium":{"attempt_count":9,"max_ms":95118,"mean_ms":42408.875,"min_ms":23645,"run_count":8},"none":{"attempt_count":9,"max_ms":31612,"mean_ms":23996.777777777777,"min_ms":2034,"run_count":9}},"codegen_output_tokens":{"attempt_count":54,"output_max":62762,"output_mean":14824.588235294117,"output_min":2627,"run_count":51},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":62762,"output_mean":34507.77777777778,"output_min":19731,"run_count":18},"medium":{"attempt_count":17,"output_max":10845,"output_mean":4547.8125,"output_min":2639,"run_count":16},"none":{"attempt_count":18,"output_max":4635,"output_mean":3655.823529411765,"output_min":2627,"run_count":17}},"display_name":"Claude Sonnet 5","economics":{"all":44.185070130624254,"highest":49.75918410793966,"medium":40.78463603177035,"none":42.011390252162784},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":53,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":72,"output_token_observations":54,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":756054,"total_reasoning_output_tokens":290926,"total_visible_output_tokens":86120,"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":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":16,"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":1570,"losses":1561,"wins":1621},"match_totals_tracks":{"highest":{"draws":479,"losses":554,"wins":665},"medium":{"draws":450,"losses":484,"wins":485},"none":{"draws":641,"losses":523,"wins":471}},"model_slug":"claude-sonnet-5","overall":{"max":61.83534732022994,"mean":44.18507013062426,"min":21.114044974233778},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":61.83534732022994,"GB2-02":24.11617014323098,"GB2-03":46.8105199390742,"GB2-04":53.04143463463096,"GB2-05":52.09853206595015,"GB2-06":45.84440293052995,"GB2-07":56.320806353852134,"GB2-08":58.006259476018926},"per_game_all":{"GB2-01":50.86404614089222,"GB2-02":23.48202353122548,"GB2-03":47.00616424726544,"GB2-04":44.991912636818846,"GB2-05":46.92570568782671,"GB2-06":47.54746947657922,"GB2-07":51.034506084435314,"GB2-08":41.62873323995086},"per_game_match_totals_all":{"GB2-01":{"draws":231,"losses":258,"wins":271},"GB2-02":{"draws":387,"losses":45,"wins":22},"GB2-03":{"draws":263,"losses":207,"wins":212},"GB2-04":{"draws":325,"losses":75,"wins":98},"GB2-05":{"draws":0,"losses":283,"wins":301},"GB2-06":{"draws":30,"losses":295,"wins":257},"GB2-07":{"draws":0,"losses":266,"wins":332},"GB2-08":{"draws":334,"losses":132,"wins":128}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":62,"wins":98},"GB2-02":{"draws":117,"losses":20,"wins":13},"GB2-03":{"draws":165,"losses":127,"wins":128},"GB2-04":{"draws":94,"losses":24,"wins":42},"GB2-05":{"draws":0,"losses":92,"wins":104},"GB2-06":{"draws":16,"losses":99,"wins":73},"GB2-07":{"draws":0,"losses":79,"wins":121},"GB2-08":{"draws":55,"losses":51,"wins":86}},"medium":{"GB2-01":{"draws":29,"losses":80,"wins":78},"GB2-02":{"draws":128,"losses":7,"wins":5},"GB2-03":{"draws":31,"losses":36,"wins":23},"GB2-04":{"draws":118,"losses":27,"wins":33},"GB2-05":{"draws":0,"losses":82,"wins":114},"GB2-06":{"draws":7,"losses":112,"wins":95},"GB2-07":{"draws":0,"losses":91,"wins":123},"GB2-08":{"draws":137,"losses":49,"wins":14}},"none":{"GB2-01":{"draws":170,"losses":116,"wins":95},"GB2-02":{"draws":142,"losses":18,"wins":4},"GB2-03":{"draws":67,"losses":44,"wins":61},"GB2-04":{"draws":113,"losses":24,"wins":23},"GB2-05":{"draws":0,"losses":109,"wins":83},"GB2-06":{"draws":7,"losses":84,"wins":89},"GB2-07":{"draws":0,"losses":96,"wins":88},"GB2-08":{"draws":142,"losses":32,"wins":28}}},"per_game_raw_elo_all":{"GB2-01":1540.2015025692338,"GB2-02":1484.5159429662835,"GB2-03":1506.7239079095878,"GB2-04":1515.1198684406593,"GB2-05":1491.2396678730613,"GB2-06":1475.9702577660355,"GB2-07":1547.0003714152851,"GB2-08":1493.6756003000194},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1649.9903636318293,"GB2-02":1487.3769341262514,"GB2-03":1504.8216008851805,"GB2-04":1568.5761718074618,"GB2-05":1553.3847277464513,"GB2-06":1456.7537777777416,"GB2-07":1602.9817039067634,"GB2-08":1656.130025467018},"medium":{"GB2-01":1484.6768021174773,"GB2-02":1493.9466411620278,"GB2-03":1455.2008449551374,"GB2-04":1476.9729843342425,"GB2-05":1535.9510213460148,"GB2-06":1436.5416474435287,"GB2-07":1533.6638531866352,"GB2-08":1395.6840270777425},"none":{"GB2-01":1485.937341958395,"GB2-02":1472.2242536105712,"GB2-03":1560.1492778884449,"GB2-04":1499.810449180274,"GB2-05":1384.3832545267173,"GB2-06":1534.6153480768362,"GB2-07":1504.3555571524566,"GB2-08":1429.212748355298}},"per_game_tracks":{"highest":{"GB2-01":61.83534732022994,"GB2-02":24.11617014323098,"GB2-03":46.8105199390742,"GB2-04":53.04143463463096,"GB2-05":52.09853206595015,"GB2-06":45.84440293052995,"GB2-07":56.320806353852134,"GB2-08":58.006259476018926},"medium":{"GB2-01":45.075725762217715,"GB2-02":25.215855476211686,"GB2-03":40.02092072410418,"GB2-04":39.38095957381465,"GB2-05":50.64827352806712,"GB2-06":44.29917985650991,"GB2-07":49.89528239094483,"GB2-08":31.740890942292665},"none":{"GB2-01":45.681065340229,"GB2-02":21.114044974233778,"GB2-03":54.18705207861794,"GB2-04":42.553343702010935,"GB2-05":38.030311469462845,"GB2-06":52.49882564269781,"GB2-07":46.88742950850896,"GB2-08":35.139049301541}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.75918410793966,"medium":40.78463603177035,"none":42.01139025216278},"reasoning_agg":{"highest":{"max":61.83534732022994,"mean":49.75918410793966,"min":24.11617014323098},"medium":{"max":50.64827352806712,"mean":40.78463603177035,"min":25.215855476211686},"none":{"max":54.18705207861794,"mean":42.01139025216278,"min":21.114044974233778}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":61.83534732022994,"expected_score":41.94118335574046,"reasoning_variance":8.974548076169313,"reliability_score":91.59571596627654,"uncertainty_avg":8.404284033723458,"uncertainty_penalty":-2.243886774883798},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":61.83534732022994,"expected_score":37.059547783339006,"reliability_score":91.19636000302391,"uncertainty_avg":8.80363999697609,"uncertainty_penalty":-12.699636324600654},"medium":{"ceiling_score":50.64827352806712,"expected_score":37.9789700701619,"reliability_score":92.00951135173925,"uncertainty_avg":7.990488648260757,"uncertainty_penalty":-2.8056659616084474},"none":{"ceiling_score":54.18705207861794,"expected_score":50.7850322137205,"reliability_score":91.58127654406647,"uncertainty_avg":8.418723455933529,"uncertainty_penalty":8.773641961557722}}},{"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":2.2561125000000004},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"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":1.4205012499999998},"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":1.4205012499999998},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793050000000001},"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":45.9522195129153,"medium":42.041377666110684},"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":413,"losses":527,"wins":472},"match_totals_tracks":{"highest":{"draws":236,"losses":272,"wins":250},"medium":{"draws":177,"losses":255,"wins":222}},"model_slug":"gpt-5","overall":{"max":66.00620122264021,"mean":43.306651750904074,"min":20.557432544949897},"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":47.822980600607565,"GB2-02":20.557432544949897,"GB2-03":39.527524812029206,"GB2-04":39.423521122325184,"GB2-05":62.830767356755665,"GB2-06":66.00620122264021,"GB2-07":57.24690808187588,"GB2-08":34.20242036213885},"per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":109,"wins":72},"GB2-02":{"draws":58,"losses":16,"wins":2},"GB2-03":{"draws":64,"losses":49,"wins":27},"GB2-04":{"draws":130,"losses":40,"wins":24},"GB2-05":{"draws":0,"losses":99,"wins":105},"GB2-06":{"draws":16,"losses":73,"wins":105},"GB2-07":{"draws":0,"losses":83,"wins":113},"GB2-08":{"draws":122,"losses":58,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":54,"wins":50},"GB2-02":{"draws":58,"losses":16,"wins":2},"GB2-03":{"draws":29,"losses":30,"wins":17},"GB2-04":{"draws":68,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":47,"wins":55},"GB2-06":{"draws":9,"losses":31,"wins":50},"GB2-07":{"draws":0,"losses":43,"wins":53},"GB2-08":{"draws":66,"losses":32,"wins":16}},"medium":{"GB2-01":{"draws":17,"losses":55,"wins":22},"GB2-03":{"draws":35,"losses":19,"wins":10},"GB2-04":{"draws":62,"losses":21,"wins":17},"GB2-05":{"draws":0,"losses":52,"wins":50},"GB2-06":{"draws":7,"losses":42,"wins":55},"GB2-07":{"draws":0,"losses":40,"wins":60},"GB2-08":{"draws":56,"losses":26,"wins":8}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1508.6425409214996,"GB2-02":1471.072947000906,"GB2-03":1455.2318976814317,"GB2-04":1475.7924746051574,"GB2-05":1681.8135849530192,"GB2-06":1690.7719660077682,"GB2-07":1613.540591357989,"GB2-08":1417.3165817886681},"medium":{"GB2-01":1257.9362460272719,"GB2-03":1402.0902606081052,"GB2-04":1483.6589592065263,"GB2-05":1607.1651624106053,"GB2-06":1580.3019624316037,"GB2-07":1636.8698724185067,"GB2-08":1347.8497544240654}},"per_game_tracks":{"highest":{"GB2-01":47.822980600607565,"GB2-02":20.557432544949897,"GB2-03":39.527524812029206,"GB2-04":39.423521122325184,"GB2-05":62.830767356755665,"GB2-06":66.00620122264021,"GB2-07":57.24690808187588,"GB2-08":34.20242036213885},"medium":{"GB2-01":22.173830070391556,"GB2-03":31.739075020104682,"GB2-04":40.81207563674785,"GB2-05":56.63196638824444,"GB2-06":56.70292816921177,"GB2-07":59.51888474627783,"GB2-08":26.71088363179663}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.95221951291531,"medium":40.661083988892834},"reasoning_agg":{"highest":{"max":66.00620122264021,"mean":45.95221951291531,"min":20.557432544949897},"medium":{"max":59.51888474627783,"mean":40.661083988892834,"min":22.173830070391556}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.00620122264021,"reasoning_variance":5.291135524022479},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.00620122264021,"expected_score":32.80596925509525,"reliability_score":92.27616896693402,"uncertainty_avg":7.723831033065976,"uncertainty_penalty":-13.146250257820064},"medium":{"ceiling_score":59.51888474627783,"expected_score":38.22979697341641,"reliability_score":91.85061238405741,"uncertainty_avg":8.149387615942585,"uncertainty_penalty":-2.4312870154764212}}},{"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":0.124499531}},"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":0.787281562},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214284,"mean_ms":465438.125,"min_ms":42870,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":1214284,"mean_ms":845698.625,"min_ms":162422,"run_count":8},"none":{"attempt_count":12,"max_ms":162843,"mean_ms":85177.625,"min_ms":42870,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":80681,"output_mean":29459.75,"output_min":2689,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":80681,"output_mean":54027.75,"output_min":8210,"run_count":8},"none":{"attempt_count":12,"output_max":7681,"output_mean":4891.75,"output_min":2689,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"highest":46.78401626089681,"none":40.82810271436163},"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":374,"losses":469,"wins":427},"match_totals_tracks":{"highest":{"draws":140,"losses":252,"wins":206},"none":{"draws":234,"losses":217,"wins":221}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":74.1333084252556,"mean":41.512537943055854,"min":21.894015414373516},"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":42.10203075533094,"GB2-04":36.42341278591467,"GB2-05":74.1333084252556,"GB2-06":41.31141247367678,"GB2-07":55.8831215680576,"GB2-08":30.850811557145292},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":96,"wins":67},"GB2-02":{"draws":80,"losses":6,"wins":2},"GB2-03":{"draws":18,"losses":29,"wins":17},"GB2-04":{"draws":54,"losses":25,"wins":9},"GB2-05":{"draws":0,"losses":85,"wins":111},"GB2-06":{"draws":10,"losses":87,"wins":107},"GB2-07":{"draws":0,"losses":99,"wins":101},"GB2-08":{"draws":147,"losses":42,"wins":13}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":48,"wins":33},"GB2-04":{"draws":54,"losses":25,"wins":9},"GB2-05":{"draws":0,"losses":35,"wins":63},"GB2-06":{"draws":2,"losses":63,"wins":53},"GB2-07":{"draws":0,"losses":56,"wins":44},"GB2-08":{"draws":65,"losses":25,"wins":4}},"none":{"GB2-01":{"draws":46,"losses":48,"wins":34},"GB2-02":{"draws":80,"losses":6,"wins":2},"GB2-03":{"draws":18,"losses":29,"wins":17},"GB2-05":{"draws":0,"losses":50,"wins":48},"GB2-06":{"draws":8,"losses":24,"wins":54},"GB2-07":{"draws":0,"losses":43,"wins":57},"GB2-08":{"draws":82,"losses":17,"wins":9}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1453.8732003554912,"GB2-04":1457.4828868208863,"GB2-05":1818.7116137409091,"GB2-06":1399.9603695080434,"GB2-07":1598.2368673537846,"GB2-08":1387.905101445435},"none":{"GB2-01":1453.1514954467345,"GB2-02":1473.8446177830178,"GB2-03":1410.1567925431275,"GB2-05":1393.141045545112,"GB2-06":1670.4616001827212,"GB2-07":1445.5598229415996,"GB2-08":1516.1908415956534}},"per_game_tracks":{"highest":{"GB2-01":42.10203075533094,"GB2-04":36.42341278591467,"GB2-05":74.1333084252556,"GB2-06":41.31141247367678,"GB2-07":55.8831215680576,"GB2-08":30.850811557145292},"none":{"GB2-01":42.49233284225822,"GB2-02":21.894015414373516,"GB2-03":32.83797916630326,"GB2-05":38.79395147095302,"GB2-06":64.1672924244156,"GB2-07":41.51464116371525,"GB2-08":44.09650651851254}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.53743286070221,"none":39.4876430254095},"reasoning_agg":{"highest":{"max":74.1333084252556,"mean":43.53743286070221,"min":30.850811557145292},"none":{"max":64.1672924244156,"mean":39.4876430254095,"min":21.894015414373516}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":74.1333084252556,"reasoning_variance":4.049789835292714},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.1333084252556,"expected_score":33.986197084052456,"reliability_score":93.76844229334236,"uncertainty_avg":6.231557706657635,"uncertainty_penalty":-9.551235776649754},"none":{"ceiling_score":64.1672924244156,"expected_score":44.31497131811409,"reliability_score":92.24421458748417,"uncertainty_avg":7.755785412515828,"uncertainty_penalty":4.827328292704593}}},{"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":1.2830031539999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":44.4008015163166},"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":184,"losses":223,"wins":241},"match_totals_tracks":{"medium":{"draws":184,"losses":223,"wins":241}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":64.14078623679886,"mean":41.31960163911211,"min":23.349084470138546},"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":51,"wins":51},"GB2-02":{"draws":91,"losses":23,"wins":4},"GB2-04":{"draws":79,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":51,"wins":57},"GB2-07":{"draws":0,"losses":53,"wins":63},"GB2-08":{"draws":10,"losses":30,"wins":58}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":51,"wins":51},"GB2-02":{"draws":91,"losses":23,"wins":4},"GB2-04":{"draws":79,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":51,"wins":57},"GB2-07":{"draws":0,"losses":53,"wins":63},"GB2-08":{"draws":10,"losses":30,"wins":58}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1457.399910028884,"GB2-02":1474.596618403244,"GB2-04":1431.1215027312614,"GB2-05":1601.2213719654865,"GB2-07":1503.7235320013426,"GB2-08":1716.3352365750259}},"per_game_tracks":{"medium":{"GB2-01":42.57288379544755,"GB2-02":23.349084470138546,"GB2-04":32.85833209398961,"GB2-05":56.229748233144726,"GB2-07":47.25397426838036,"GB2-08":64.14078623679886}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.31960163911211},"reasoning_agg":{"medium":{"max":64.14078623679886,"mean":41.31960163911211,"min":23.349084470138546}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":64.14078623679886},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":64.14078623679886,"expected_score":46.330820688548435,"reliability_score":95.78226090199517,"uncertainty_avg":4.2177390980048335,"uncertainty_penalty":5.011219049436328}}},{"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":40.511310783890416},"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":39,"losses":69,"wins":60},"match_totals_tracks":{"none":{"draws":39,"losses":69,"wins":60}},"model_slug":"gpt-4-1-nano","overall":{"max":40.511310783890416,"mean":40.511310783890416,"min":40.511310783890416},"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":19,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":69,"wins":60}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":39,"losses":69,"wins":60}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1429.1019623450045}},"per_game_tracks":{"none":{"GB2-01":40.511310783890416}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":40.511310783890416},"reasoning_agg":{"none":{"max":40.511310783890416,"mean":40.511310783890416,"min":40.511310783890416}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":40.511310783890416},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":40.511310783890416,"expected_score":41.2544091507466,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.7430983668561879}}},{"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":0.72882375},"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":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999997},"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":42.252226079601506,"none":40.86417247608275},"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":490,"losses":471,"wins":431},"match_totals_tracks":{"medium":{"draws":267,"losses":247,"wins":226},"none":{"draws":223,"losses":224,"wins":205}},"model_slug":"qwen-qwen3-7-max","overall":{"max":72.79240290081826,"mean":40.193769211935795,"min":15.965232157159793},"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":57,"losses":84,"wins":55},"GB2-02":{"draws":149,"losses":19,"wins":12},"GB2-03":{"draws":52,"losses":10,"wins":6},"GB2-04":{"draws":66,"losses":23,"wins":17},"GB2-05":{"draws":0,"losses":116,"wins":114},"GB2-06":{"draws":14,"losses":105,"wins":89},"GB2-07":{"draws":0,"losses":53,"wins":123},"GB2-08":{"draws":152,"losses":61,"wins":15}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":30,"losses":54,"wins":12},"GB2-02":{"draws":83,"losses":13,"wins":4},"GB2-04":{"draws":66,"losses":23,"wins":17},"GB2-05":{"draws":0,"losses":63,"wins":61},"GB2-06":{"draws":12,"losses":42,"wins":56},"GB2-07":{"draws":0,"losses":21,"wins":65},"GB2-08":{"draws":76,"losses":31,"wins":11}},"none":{"GB2-01":{"draws":27,"losses":30,"wins":43},"GB2-02":{"draws":66,"losses":6,"wins":8},"GB2-03":{"draws":52,"losses":10,"wins":6},"GB2-05":{"draws":0,"losses":53,"wins":53},"GB2-06":{"draws":2,"losses":63,"wins":33},"GB2-07":{"draws":0,"losses":32,"wins":58},"GB2-08":{"draws":76,"losses":30,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1196.0815382797539,"GB2-02":1462.125463708624,"GB2-04":1490.791657928284,"GB2-05":1544.3386733865298,"GB2-06":1579.5531911998273,"GB2-07":1780.9950468049765,"GB2-08":1440.8004114495486},"none":{"GB2-01":1573.513576219901,"GB2-02":1485.2151308299296,"GB2-03":1426.0472522295584,"GB2-05":1515.586736592979,"GB2-06":1225.4277449994963,"GB2-07":1703.2609653449783,"GB2-08":1397.181675768906}},"per_game_tracks":{"medium":{"GB2-01":15.965232157159793,"GB2-02":19.847233163024622,"GB2-04":42.07260490289768,"GB2-05":51.71679831534971,"GB2-06":56.73068128436687,"GB2-07":72.79240290081826,"GB2-08":36.640629833593636},"none":{"GB2-01":54.19394021291321,"GB2-02":23.986859461426256,"GB2-03":35.201572417188274,"GB2-05":49.08905663197634,"GB2-06":25.9118827156635,"GB2-07":65.56652347725021,"GB2-08":32.09937241616148}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.86500987157832,"none":39.522528552293274},"reasoning_agg":{"medium":{"max":72.79240290081826,"mean":40.86500987157832,"min":15.965232157159793},"none":{"max":65.56652347725021,"mean":39.522528552293274,"min":23.986859461426256}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.79240290081826,"reasoning_variance":1.3424813192850493},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":72.79240290081826,"expected_score":42.3089027117281,"reliability_score":95.11059954994505,"uncertainty_avg":4.88940045005495,"uncertainty_penalty":1.443892840149779},"none":{"ceiling_score":65.56652347725021,"expected_score":44.7161925653116,"reliability_score":91.75554307887082,"uncertainty_avg":8.24445692112918,"uncertainty_penalty":5.193664013018328}}},{"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":1.0777302952},"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":1.2846227784000002},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":44.414913787081844,"none":39.507754503351535},"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":"2026-08-05T05:17:07Z","match_totals_all":{"draws":268,"losses":427,"wins":401},"match_totals_tracks":{"medium":{"draws":128,"losses":226,"wins":184},"none":{"draws":140,"losses":201,"wins":217}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":65.17750853680307,"mean":39.67345826674859,"min":25.222210730949445},"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":21,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":32,"losses":51,"wins":33},"GB2-02":{"draws":66,"losses":7,"wins":5},"GB2-03":{"draws":41,"losses":15,"wins":14},"GB2-04":{"draws":51,"losses":23,"wins":22},"GB2-05":{"draws":0,"losses":117,"wins":91},"GB2-06":{"draws":3,"losses":90,"wins":119},"GB2-07":{"draws":0,"losses":99,"wins":115},"GB2-08":{"draws":75,"losses":25,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":51,"losses":23,"wins":22},"GB2-05":{"draws":0,"losses":71,"wins":39},"GB2-06":{"draws":2,"losses":45,"wins":63},"GB2-07":{"draws":0,"losses":62,"wins":58},"GB2-08":{"draws":75,"losses":25,"wins":2}},"none":{"GB2-01":{"draws":32,"losses":51,"wins":33},"GB2-02":{"draws":66,"losses":7,"wins":5},"GB2-03":{"draws":41,"losses":15,"wins":14},"GB2-05":{"draws":0,"losses":46,"wins":52},"GB2-06":{"draws":1,"losses":45,"wins":56},"GB2-07":{"draws":0,"losses":37,"wins":57}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1566.3530638646457,"GB2-05":1293.3384425319216,"GB2-06":1677.2246416402638,"GB2-07":1467.492796093447,"GB2-08":1367.9946417839965},"none":{"GB2-01":1402.395743836614,"GB2-02":1491.2790874838233,"GB2-03":1448.8646223820033,"GB2-05":1444.8486850159818,"GB2-06":1421.6211054795062,"GB2-07":1539.1060983283344}},"per_game_tracks":{"medium":{"GB2-04":53.300611514890754,"GB2-05":30.691959004825147,"GB2-06":65.17750853680307,"GB2-07":43.90229671853825,"GB2-08":29.00219316035198},"none":{"GB2-01":37.18442894600758,"GB2-02":25.222210730949445,"GB2-03":38.40303950625073,"GB2-05":43.08775105458573,"GB2-06":42.94726409759388,"GB2-07":50.20183268472181}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.332734586859196,"none":38.01418194663798},"reasoning_agg":{"medium":{"max":65.17750853680307,"mean":41.332734586859196,"min":29.00219316035198},"none":{"max":50.20183268472181,"mean":38.01418194663798,"min":25.222210730949445}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.17750853680307,"reasoning_variance":3.3185526402212133},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":65.17750853680307,"expected_score":49.23226334059572,"reliability_score":95.6691765610618,"uncertainty_avg":4.330823438938195,"uncertainty_penalty":7.899528753736526},"none":{"ceiling_score":50.20183268472181,"expected_score":45.81195403068773,"reliability_score":91.64403890274512,"uncertainty_avg":8.355961097254875,"uncertainty_penalty":7.797772084049747}}},{"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":0.45756399999999997}},"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":0.45756399999999997}},"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":0.45756399999999997},"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":39.175380343627474},"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":260,"losses":271,"wins":218},"match_totals_tracks":{"none":{"draws":260,"losses":271,"wins":218}},"model_slug":"gpt-4-1","overall":{"max":54.37710879884957,"mean":39.175380343627474,"min":17.324048509285905},"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":22,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":49,"wins":59},"GB2-02":{"draws":72,"losses":12,"wins":2},"GB2-03":{"draws":28,"losses":31,"wins":25},"GB2-04":{"draws":66,"losses":14,"wins":4},"GB2-05":{"draws":0,"losses":66,"wins":28},"GB2-06":{"draws":10,"losses":35,"wins":47},"GB2-07":{"draws":0,"losses":48,"wins":40},"GB2-08":{"draws":79,"losses":16,"wins":13}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":5,"losses":49,"wins":59},"GB2-02":{"draws":72,"losses":12,"wins":2},"GB2-03":{"draws":28,"losses":31,"wins":25},"GB2-04":{"draws":66,"losses":14,"wins":4},"GB2-05":{"draws":0,"losses":66,"wins":28},"GB2-06":{"draws":10,"losses":35,"wins":47},"GB2-07":{"draws":0,"losses":48,"wins":40},"GB2-08":{"draws":79,"losses":16,"wins":13}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1572.9878368669815,"GB2-02":1460.2386314581393,"GB2-03":1521.331600253054,"GB2-04":1457.7387499700872,"GB2-05":1135.4295707705774,"GB2-06":1555.174459690298,"GB2-07":1530.801634444942,"GB2-08":1418.4565971654238}},"per_game_tracks":{"none":{"GB2-01":54.37710879884957,"GB2-02":18.7319500025143,"GB2-03":48.831744011327004,"GB2-04":36.31202602070684,"GB2-05":17.324048509285905,"GB2-06":54.318655446755876,"GB2-07":49.29223370785008,"GB2-08":34.21527625173018}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":39.175380343627474},"reasoning_agg":{"none":{"max":54.37710879884957,"mean":39.175380343627474,"min":17.324048509285905}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.37710879884957},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":54.37710879884957,"expected_score":46.11557158310743,"reliability_score":92.13276789594286,"uncertainty_avg":7.867232104057134,"uncertainty_penalty":6.940191239479958}}},{"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":0.8354799999999999},"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":0.8354799999999999},"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":0.9576840000000001},"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":4.659586}},"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":6.452749999999998},"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":39.20443030695615,"highest":43.31650489789861,"medium":39.30149945456943,"none":34.240469798169755},"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":134,"losses":115,"wins":162},"match_totals_tracks":{"highest":{"draws":36,"losses":29,"wins":64},"medium":{"draws":44,"losses":41,"wins":59},"none":{"draws":54,"losses":45,"wins":39}},"model_slug":"qwen-qwen3-8-max","overall":{"max":65.34857672458816,"mean":38.169396763757256,"min":7.491362721335916},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":23,"overall_ranking_status":"partial","per_game":{"GB2-02":20.442652389870492,"GB2-03":41.72942915084835,"GB2-04":50.427853739274326,"GB2-05":46.48436747017905,"GB2-06":46.45237289235433,"GB2-07":65.34857672458816,"GB2-08":32.3302819181756},"per_game_all":{"GB2-02":13.24053763491604,"GB2-03":36.87474790857869,"GB2-04":37.2038253783334,"GB2-05":52.86920329947693,"GB2-06":43.222886130811055,"GB2-07":50.03775473490094,"GB2-08":40.98205706167599},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":17,"wins":9},"GB2-02":{"draws":45,"losses":6,"wins":3},"GB2-03":{"draws":14,"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":7,"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":1484.8333409923919,"GB2-03":1487.2732800771744,"GB2-04":1509.435511948029,"GB2-05":1610.7639127614282,"GB2-06":1480.1621129700764,"GB2-07":1585.8222225945508,"GB2-08":1540.5886994724067},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1519.2581453563312,"GB2-03":1520.0917022516862,"GB2-04":1594.1909851365033,"GB2-05":1528.9563415565945,"GB2-06":1522.7378338885317,"GB2-07":1746.3008626110957,"GB2-08":1453.2655519062441},"medium":{"GB2-01":1500.3453591301432,"GB2-02":1473.6963543985923,"GB2-03":1501.4910334028175,"GB2-04":1475.637623633983,"GB2-05":1577.631160970109,"GB2-06":1596.932346317202,"GB2-07":1452.2408415859013,"GB2-08":1632.9497775865889},"none":{"GB2-01":1364.0547383269693,"GB2-02":1461.545523222252,"GB2-03":1440.2371045770194,"GB2-04":1458.4779270736012,"GB2-05":1725.7042357575813,"GB2-06":1320.8161587044958,"GB2-07":1558.924963586655,"GB2-08":1535.5507689243868}},"per_game_tracks":{"highest":{"GB2-02":20.442652389870492,"GB2-03":41.72942915084835,"GB2-04":50.427853739274326,"GB2-05":46.48436747017905,"GB2-06":46.45237289235433,"GB2-07":65.34857672458816,"GB2-08":32.3302819181756},"medium":{"GB2-01":41.01649081370751,"GB2-02":11.78759779354171,"GB2-03":38.823095003355,"GB2-04":30.86262516391439,"GB2-05":50.2040113856351,"GB2-06":53.968299220992186,"GB2-07":37.2529709637503,"GB2-08":50.496905291659246},"none":{"GB2-01":27.24176104741712,"GB2-02":7.491362721335916,"GB2-03":30.071719571532732,"GB2-04":30.32099723181149,"GB2-05":61.919231042616644,"GB2-06":29.24798627908666,"GB2-07":47.51171651636437,"GB2-08":40.11898397519311}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.96622103853259,"medium":39.301499454569424,"none":34.240469798169755},"reasoning_agg":{"highest":{"max":65.34857672458816,"mean":40.96622103853259,"min":20.442652389870492},"medium":{"max":53.968299220992186,"mean":39.301499454569424,"min":11.78759779354171},"none":{"max":61.919231042616644,"mean":34.240469798169755,"min":7.491362721335916}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":65.34857672458816,"expected_score":43.15624658724112,"reasoning_variance":6.725751240362833,"reliability_score":28.680385228972114,"uncertainty_avg":71.31961477102789,"uncertainty_penalty":4.986849823483865},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.34857672458816,"expected_score":35.862227373022584,"reliability_score":29.766396486381936,"uncertainty_avg":70.23360351361806,"uncertainty_penalty":-5.1039936655100036},"medium":{"ceiling_score":53.968299220992186,"expected_score":44.35428790926808,"reliability_score":28.681749152618764,"uncertainty_avg":71.31825084738124,"uncertainty_penalty":5.052788454698657},"none":{"ceiling_score":61.919231042616644,"expected_score":47.28684178437102,"reliability_score":26.179212018307226,"uncertainty_avg":73.82078798169277,"uncertainty_penalty":13.046371986201265}}},{"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":2.0151682500000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.14705250000000003}},"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":0.1470525},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":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":5.1688104},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":46.84330020788532,"none":29.208084954343278},"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":595,"losses":518,"wins":442},"match_totals_tracks":{"medium":{"draws":251,"losses":251,"wins":315},"none":{"draws":344,"losses":267,"wins":127}},"model_slug":"gpt-5-4-mini","overall":{"max":59.73623054906832,"mean":38.0256925811143,"min":7.8623797518037435},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":24,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":85,"wins":77},"GB2-02":{"draws":168,"losses":5,"wins":3},"GB2-03":{"draws":128,"losses":25,"wins":16},"GB2-04":{"draws":119,"losses":25,"wins":36},"GB2-05":{"draws":0,"losses":116,"wins":102},"GB2-06":{"draws":18,"losses":89,"wins":99},"GB2-07":{"draws":0,"losses":122,"wins":74},"GB2-08":{"draws":118,"losses":51,"wins":35}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":39,"wins":55},"GB2-02":{"draws":84,"losses":3,"wins":3},"GB2-03":{"draws":49,"losses":21,"wins":15},"GB2-04":{"draws":61,"losses":9,"wins":20},"GB2-05":{"draws":0,"losses":50,"wins":74},"GB2-06":{"draws":12,"losses":43,"wins":53},"GB2-07":{"draws":0,"losses":48,"wins":60},"GB2-08":{"draws":41,"losses":38,"wins":35}},"none":{"GB2-01":{"draws":40,"losses":46,"wins":22},"GB2-02":{"draws":84,"losses":2,"wins":0},"GB2-03":{"draws":79,"losses":4,"wins":1},"GB2-04":{"draws":58,"losses":16,"wins":16},"GB2-05":{"draws":0,"losses":66,"wins":28},"GB2-06":{"draws":6,"losses":46,"wins":46},"GB2-07":{"draws":0,"losses":74,"wins":14},"GB2-08":{"draws":77,"losses":13,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1628.750407707507,"GB2-02":1472.1832965878284,"GB2-03":1480.1394784776523,"GB2-04":1559.7577793037303,"GB2-05":1576.1336146218378,"GB2-06":1559.2793243998406,"GB2-07":1562.733366371016,"GB2-08":1435.5819424274005},"none":{"GB2-01":1351.113886438586,"GB2-02":1463.998408715422,"GB2-03":1474.8658260094098,"GB2-04":1460.0297776195794,"GB2-05":1258.1950094624974,"GB2-06":1335.615860264783,"GB2-07":1090.5750082161858,"GB2-08":1400.3144399361822}},"per_game_tracks":{"medium":{"GB2-01":59.73623054906832,"GB2-02":21.626339283900553,"GB2-03":43.25460249709266,"GB2-04":52.09375303448146,"GB2-05":54.357048515026754,"GB2-06":54.94736966606298,"GB2-07":52.68195407315516,"GB2-08":36.04910404429471},"none":{"GB2-01":31.866704468526944,"GB2-02":19.57568162564367,"GB2-03":42.50170870197985,"GB2-04":36.883321001904825,"GB2-05":27.518483895121314,"GB2-06":35.44117680027425,"GB2-07":7.8623797518037435,"GB2-08":32.01522338949161}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.84330020788533,"none":29.208084954343278},"reasoning_agg":{"medium":{"max":59.73623054906832,"mean":46.84330020788533,"min":21.626339283900553},"none":{"max":42.50170870197985,"mean":29.208084954343278,"min":7.8623797518037435}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":59.73623054906832,"reasoning_variance":17.63521525354205},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.73623054906832,"expected_score":46.705124259212205,"reliability_score":94.23425130987522,"uncertainty_avg":5.765748690124784,"uncertainty_penalty":-0.13817594867312266},"none":{"ceiling_score":42.50170870197985,"expected_score":33.25058992251807,"reliability_score":91.86140731283257,"uncertainty_avg":8.138592687167439,"uncertainty_penalty":4.042504968174789}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:0ccf02fcc67f023e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":18},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.51553995,"mean":0.34562851249999993,"median":0.32314493749999995,"min":0.21152055,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18},"run_count":17,"token_priced_attempt_count":18,"total":6.0079747999999995},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":18},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.009729675,"mean":0.006791625,"median":0.006426525,"min":0.00488805,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18},"run_count":17,"token_priced_attempt_count":18,"total":0.11355404999999999},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":17},"evidence_basis":"Standard list-price estimate","max":0.006186499999999999,"mean":0.0044960124999999995,"median":0.004244175,"min":0.0036738749999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":16,"token_priced_attempt_count":17,"total":0.0719362}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.0093148,"mean":0.007231125,"median":0.0070676,"min":0.0051605999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":9,"token_priced_attempt_count":9,"total":0.0630096},"historical-provider-setting-baseline-variant-1":{"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-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.007763,"mean":0.0043935499999999995,"median":0.0039395,"min":0.0032303999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.035148399999999996},"historical-provider-setting-intensive-variant-1":{"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},"historical-provider-setting-intensive-variant-2":{"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":0.9975713999999999,"mean":0.6329139249999999,"median":0.6142170999999998,"min":0.3971226,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":9,"token_priced_attempt_count":10,"total":5.761308199999999}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":53},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.51553995,"mean":0.11897204999999998,"median":0.006426525,"min":0.0036738749999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":53},"run_count":50,"token_priced_attempt_count":53,"total":6.1934650499999995},"codegen_latency_ms":{"attempt_count":28,"max_ms":220389,"mean_ms":65068.846153846156,"min_ms":7259,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":220389,"mean_ms":159594.88888888888,"min_ms":125171,"run_count":9},"medium":{"attempt_count":9,"max_ms":22604,"mean_ms":17903.777777777777,"min_ms":13783,"run_count":9},"none":{"attempt_count":9,"max_ms":28315,"mean_ms":11787.75,"min_ms":7259,"run_count":8}},"codegen_output_tokens":{"attempt_count":53,"output_max":830024,"output_mean":101695.54,"output_min":1487,"run_count":50},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":830024,"output_mean":292963.4117647059,"output_min":19109,"run_count":17},"medium":{"attempt_count":18,"output_max":6580,"output_mean":4044.823529411765,"output_min":2113,"run_count":17},"none":{"attempt_count":17,"output_max":4181,"output_mean":2227.3125,"output_min":1487,"run_count":16}},"display_name":"GPT-5.6 Luna","economics":{"all":38.82782919168082,"highest":52.9953155064623,"medium":42.737047775268074,"none":20.751124293312085},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["stop"],"indexed_attempts":77,"output_token_observations":53,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":5084777,"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":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"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,"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":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"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}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-08-23T12:40:55Z","match_totals_all":{"draws":1384,"losses":1667,"wins":1250},"match_totals_tracks":{"highest":{"draws":363,"losses":414,"wins":632},"medium":{"draws":522,"losses":502,"wins":454},"none":{"draws":499,"losses":751,"wins":164}},"model_slug":"gpt-5-6-luna","overall":{"max":80.44715581991792,"mean":37.901891204021624,"min":10.864694550855324},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.44715581991792,"GB2-02":23.37892449322698,"GB2-03":34.722469385399606,"GB2-04":35.835204403454306,"GB2-05":56.6666251213187,"GB2-06":78.29991891467037,"GB2-07":73.71875066727475,"GB2-08":40.89347524643575},"per_game_all":{"GB2-01":52.79001685756692,"GB2-02":21.71930061838494,"GB2-03":35.80409354618032,"GB2-04":37.344411330057355,"GB2-05":41.579437892912345,"GB2-06":51.70285972140976,"GB2-07":40.95954481494346,"GB2-08":28.72296875199146},"per_game_match_totals_all":{"GB2-01":{"draws":66,"losses":243,"wins":250},"GB2-02":{"draws":404,"losses":29,"wins":9},"GB2-03":{"draws":226,"losses":183,"wins":88},"GB2-04":{"draws":353,"losses":92,"wins":61},"GB2-05":{"draws":0,"losses":338,"wins":251},"GB2-06":{"draws":32,"losses":252,"wins":272},"GB2-07":{"draws":0,"losses":322,"wins":246},"GB2-08":{"draws":303,"losses":208,"wins":73}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":52,"wins":136},"GB2-02":{"draws":133,"losses":13,"wins":8},"GB2-03":{"draws":66,"losses":63,"wins":29},"GB2-04":{"draws":88,"losses":48,"wins":28},"GB2-05":{"draws":0,"losses":92,"wins":110},"GB2-06":{"draws":18,"losses":31,"wins":126},"GB2-07":{"draws":0,"losses":49,"wins":137},"GB2-08":{"draws":58,"losses":66,"wins":58}},"medium":{"GB2-01":{"draws":22,"losses":68,"wins":91},"GB2-02":{"draws":129,"losses":8,"wins":1},"GB2-03":{"draws":71,"losses":61,"wins":35},"GB2-04":{"draws":145,"losses":16,"wins":15},"GB2-05":{"draws":0,"losses":108,"wins":101},"GB2-06":{"draws":11,"losses":66,"wins":122},"GB2-07":{"draws":0,"losses":125,"wins":79},"GB2-08":{"draws":144,"losses":50,"wins":10}},"none":{"GB2-01":{"draws":44,"losses":123,"wins":23},"GB2-02":{"draws":142,"losses":8,"wins":0},"GB2-03":{"draws":89,"losses":59,"wins":24},"GB2-04":{"draws":120,"losses":28,"wins":18},"GB2-05":{"draws":0,"losses":138,"wins":40},"GB2-06":{"draws":3,"losses":155,"wins":24},"GB2-07":{"draws":0,"losses":148,"wins":30},"GB2-08":{"draws":101,"losses":92,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1561.0663307318252,"GB2-02":1477.2412049829945,"GB2-03":1426.2446076604194,"GB2-04":1464.5376268141983,"GB2-05":1426.8087360270563,"GB2-06":1524.8619687382516,"GB2-07":1440.883207855196,"GB2-08":1366.305537069317},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1834.5344217203296,"GB2-02":1483.6954959964735,"GB2-03":1419.4189111847174,"GB2-04":1455.1703609820988,"GB2-05":1607.8454582553452,"GB2-06":1833.5180772796284,"GB2-07":1789.226380256292,"GB2-08":1487.916458011123},"medium":{"GB2-01":1617.5393757778043,"GB2-02":1491.457570126053,"GB2-03":1451.8197120792142,"GB2-04":1470.374112829179,"GB2-05":1536.8552682209965,"GB2-06":1655.3643700867465,"GB2-07":1411.1647760575288,"GB2-08":1367.5105476995527},"none":{"GB2-01":1231.1251946973412,"GB2-02":1456.570548826457,"GB2-03":1407.4951997173266,"GB2-04":1468.0684066313174,"GB2-05":1135.7254816048269,"GB2-06":1085.7034588483796,"GB2-07":1122.2584672517671,"GB2-08":1243.4896054972753}},"per_game_tracks":{"highest":{"GB2-01":80.44715581991792,"GB2-02":23.37892449322698,"GB2-03":34.722469385399606,"GB2-04":35.835204403454306,"GB2-05":56.6666251213187,"GB2-06":78.29991891467037,"GB2-07":73.71875066727475,"GB2-08":40.89347524643575},"medium":{"GB2-01":58.43985564617407,"GB2-02":24.62525327826603,"GB2-03":39.31631498921994,"GB2-04":38.358671625552,"GB2-05":50.81791174484506,"GB2-06":63.11042159913285,"GB2-07":38.295189226700316,"GB2-08":28.932764092254317},"none":{"GB2-01":19.48303910660878,"GB2-02":17.153724083661814,"GB2-03":33.3734962639214,"GB2-04":37.83935796116576,"GB2-05":17.25377681257326,"GB2-06":13.698238650426038,"GB2-07":10.864694550855324,"GB2-08":16.34266691728431}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.45757923484194,"medium":41.496970083910846,"none":20.751124293312085},"reasoning_agg":{"highest":{"max":80.44715581991792,"mean":51.45757923484194,"min":23.37892449322698},"medium":{"max":63.11042159913285,"mean":41.496970083910846,"min":24.62525327826603},"none":{"max":37.83935796116576,"mean":20.751124293312085,"min":10.864694550855324}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":80.44715581991792,"expected_score":34.88646079981259,"reasoning_variance":30.706454941529852,"reliability_score":90.87318189796665,"uncertainty_avg":9.126818102033349,"uncertainty_penalty":-3.0154304042090345},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.44715581991792,"expected_score":41.631559049801254,"reliability_score":90.48757581757943,"uncertainty_avg":9.512424182420574,"uncertainty_penalty":-9.826020185040683},"medium":{"ceiling_score":63.11042159913285,"expected_score":41.02664283665477,"reliability_score":91.50903268097886,"uncertainty_avg":8.490967319021133,"uncertainty_penalty":-0.47032724725607267},"none":{"ceiling_score":37.83935796116576,"expected_score":22.001180512981737,"reliability_score":90.62293719534166,"uncertainty_avg":9.377062804658342,"uncertainty_penalty":1.250056219669652}}},{"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":0.48528459999999995}},"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":0.48528460000000007}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528459999999995},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":37.88184486713599},"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":318,"losses":294,"wins":222},"match_totals_tracks":{"medium":{"draws":318,"losses":294,"wins":222}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":63.41974151718129,"mean":37.88184486713599,"min":21.669541208427077},"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":26,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":43,"wins":42},"GB2-02":{"draws":86,"losses":3,"wins":3},"GB2-03":{"draws":32,"losses":20,"wins":18},"GB2-04":{"draws":84,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":60,"wins":64},"GB2-06":{"draws":0,"losses":73,"wins":51},"GB2-07":{"draws":0,"losses":73,"wins":33},"GB2-08":{"draws":93,"losses":15,"wins":6}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":23,"losses":43,"wins":42},"GB2-02":{"draws":86,"losses":3,"wins":3},"GB2-03":{"draws":32,"losses":20,"wins":18},"GB2-04":{"draws":84,"losses":7,"wins":5},"GB2-05":{"draws":0,"losses":60,"wins":64},"GB2-06":{"draws":0,"losses":73,"wins":51},"GB2-07":{"draws":0,"losses":73,"wins":33},"GB2-08":{"draws":93,"losses":15,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1483.761287066289,"GB2-02":1471.922484272434,"GB2-03":1411.5993597267618,"GB2-04":1480.7467967975713,"GB2-05":1685.2701621628198,"GB2-06":1419.0192370849595,"GB2-07":1249.6710367295523,"GB2-08":1404.4257773948275}},"per_game_tracks":{"medium":{"GB2-01":45.273218336317015,"GB2-02":21.669541208427077,"GB2-03":33.32639046166839,"GB2-04":40.244014723647986,"GB2-05":63.41974151718129,"GB2-06":43.0367051388074,"GB2-07":23.186026838702013,"GB2-08":32.89912071233677}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.88184486713599},"reasoning_agg":{"medium":{"max":63.41974151718129,"mean":37.88184486713599,"min":21.669541208427077}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":63.41974151718129},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.41974151718129,"expected_score":33.70553955221047,"reliability_score":94.46874073396964,"uncertainty_avg":5.5312592660303626,"uncertainty_penalty":-4.176305314925521}}},{"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":0.14744575000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":0.14744575000000004},"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":1.0821379},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":41.34035496936002,"none":37.47825265467622},"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":565,"losses":928,"wins":807},"match_totals_tracks":{"medium":{"draws":225,"losses":495,"wins":450},"none":{"draws":340,"losses":433,"wins":357}},"model_slug":"gpt-5-4-nano","overall":{"max":61.40570645858217,"mean":36.67448962129495,"min":13.75796311182292},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":27,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":80,"losses":191,"wins":113},"GB2-02":{"draws":233,"losses":17,"wins":4},"GB2-03":{"draws":34,"losses":28,"wins":28},"GB2-04":{"draws":64,"losses":9,"wins":25},"GB2-05":{"draws":0,"losses":232,"wins":154},"GB2-06":{"draws":7,"losses":172,"wins":231},"GB2-07":{"draws":0,"losses":175,"wins":119},"GB2-08":{"draws":147,"losses":104,"wins":133}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":26,"losses":129,"wins":33},"GB2-02":{"draws":77,"losses":3,"wins":0},"GB2-04":{"draws":64,"losses":9,"wins":25},"GB2-05":{"draws":0,"losses":96,"wins":112},"GB2-06":{"draws":6,"losses":86,"wins":122},"GB2-07":{"draws":0,"losses":113,"wins":81},"GB2-08":{"draws":52,"losses":59,"wins":77}},"none":{"GB2-01":{"draws":54,"losses":62,"wins":80},"GB2-02":{"draws":156,"losses":14,"wins":4},"GB2-03":{"draws":34,"losses":28,"wins":28},"GB2-05":{"draws":0,"losses":136,"wins":42},"GB2-06":{"draws":1,"losses":86,"wins":109},"GB2-07":{"draws":0,"losses":62,"wins":38},"GB2-08":{"draws":95,"losses":45,"wins":56}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1175.0071677189458,"GB2-02":1475.7131921870432,"GB2-04":1562.2888242629197,"GB2-05":1536.204965591142,"GB2-06":1634.145784366343,"GB2-07":1403.2063184617587,"GB2-08":1591.1098460751618},"none":{"GB2-01":1569.9906928986984,"GB2-02":1461.5162308159042,"GB2-03":1503.4667049734755,"GB2-05":1169.1766725591847,"GB2-06":1501.2372841051183,"GB2-07":1303.316043587365,"GB2-08":1526.837067851132}},"per_game_tracks":{"medium":{"GB2-01":13.75796311182292,"GB2-02":21.854529388279282,"GB2-04":52.743625903198904,"GB2-05":50.75472568681504,"GB2-06":61.40570645858217,"GB2-07":37.47050308707877,"GB2-08":51.39543114974306},"none":{"GB2-01":53.78745945851931,"GB2-02":19.073029071771302,"GB2-03":46.59618183026941,"GB2-05":20.032859834975213,"GB2-06":49.76392479065197,"GB2-07":28.128038323977535,"GB2-08":44.966275272568765}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.47153521149206,"none":34.877444031097845},"reasoning_agg":{"medium":{"max":61.40570645858217,"mean":38.47153521149206,"min":13.75796311182292},"none":{"max":53.78745945851931,"mean":34.877444031097845,"min":19.073029071771302}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":61.40570645858217,"reasoning_variance":3.5940911803942157},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":61.40570645858217,"expected_score":43.6046264493071,"reliability_score":92.81886576424333,"uncertainty_avg":7.181134235756666,"uncertainty_penalty":5.133091237815037},"none":{"ceiling_score":53.78745945851931,"expected_score":40.477500174816306,"reliability_score":92.42762131508947,"uncertainty_avg":7.572378684910538,"uncertainty_penalty":5.6000561437184615}}},{"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":0.07737849999999999,"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":0.07737849999999999,"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":0.0865375,"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":41.926016269347905,"highest":47.39906310459903,"medium":47.41858747665342,"none":26.898169851595892},"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":632,"losses":1867,"wins":1719},"match_totals_tracks":{"highest":{"draws":289,"losses":1289,"wins":1341},"medium":{"draws":158,"losses":225,"wins":253},"none":{"draws":185,"losses":353,"wins":125}},"model_slug":"o3","overall":{"max":59.630586714276724,"mean":36.11798355657051,"min":7.743053185185025},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":28,"overall_ranking_status":"partial","per_game":{"GB2-01":56.64546823346215,"GB2-03":38.84780628544275,"GB2-05":50.49609918819178,"GB2-06":49.13258160734104,"GB2-07":45.16236630356082,"GB2-08":44.110057009595636},"per_game_all":{"GB2-01":35.98226229830299,"GB2-06":42.661847068449624,"GB2-07":52.1249198259064,"GB2-08":36.93503588473259},"per_game_match_totals_all":{"GB2-01":{"draws":97,"losses":318,"wins":295},"GB2-03":{"draws":49,"losses":55,"wins":30},"GB2-04":{"draws":67,"losses":12,"wins":9},"GB2-05":{"draws":0,"losses":342,"wins":406},"GB2-06":{"draws":54,"losses":444,"wins":367},"GB2-07":{"draws":0,"losses":472,"wins":436},"GB2-08":{"draws":365,"losses":224,"wins":176}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":161,"wins":253},"GB2-03":{"draws":49,"losses":55,"wins":30},"GB2-05":{"draws":0,"losses":292,"wins":342},"GB2-06":{"draws":17,"losses":286,"wins":288},"GB2-07":{"draws":0,"losses":350,"wins":286},"GB2-08":{"draws":191,"losses":145,"wins":142}},"medium":{"GB2-01":{"draws":17,"losses":46,"wins":35},"GB2-04":{"draws":67,"losses":12,"wins":9},"GB2-05":{"draws":0,"losses":50,"wins":64},"GB2-06":{"draws":11,"losses":43,"wins":52},"GB2-07":{"draws":0,"losses":42,"wins":64},"GB2-08":{"draws":63,"losses":32,"wins":29}},"none":{"GB2-01":{"draws":48,"losses":111,"wins":7},"GB2-06":{"draws":26,"losses":115,"wins":27},"GB2-07":{"draws":0,"losses":80,"wins":86},"GB2-08":{"draws":111,"losses":47,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1388.1674406470186,"GB2-06":1412.9876489713808,"GB2-07":1552.2509161677906,"GB2-08":1439.9182894123785},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1590.752419913073,"GB2-03":1439.0846957731926,"GB2-05":1525.5655874239144,"GB2-06":1486.5307015706844,"GB2-07":1476.1447162410047,"GB2-08":1509.6216092291434},"medium":{"GB2-01":1468.681575830985,"GB2-04":1452.4224780953568,"GB2-05":1505.8097339730377,"GB2-06":1597.6476744413671,"GB2-07":1636.9247706055485,"GB2-08":1463.6955904890767},"none":{"GB2-01":1105.068326196998,"GB2-06":1154.7845709020912,"GB2-07":1543.6832616568183,"GB2-08":1346.4376685189152}},"per_game_tracks":{"highest":{"GB2-01":56.64546823346215,"GB2-03":38.84780628544275,"GB2-05":50.49609918819178,"GB2-06":49.13258160734104,"GB2-07":45.16236630356082,"GB2-08":44.110057009595636},"medium":{"GB2-01":43.55826547626181,"GB2-04":35.65160344774605,"GB2-05":48.39087874034282,"GB2-06":58.234720321902785,"GB2-07":59.630586714276724,"GB2-08":39.04547015939034},"none":{"GB2-01":7.743053185185025,"GB2-06":20.618239276105058,"GB2-07":51.58180645988167,"GB2-08":27.649580485211807}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.60740814708737,"medium":44.12796791753164,"none":22.61857460509252},"reasoning_agg":{"highest":{"max":56.64546823346215,"mean":41.60740814708737,"min":38.84780628544275},"medium":{"max":59.630586714276724,"mean":44.12796791753164,"min":35.65160344774605},"none":{"max":51.58180645988167,"mean":22.61857460509252,"min":7.743053185185025}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":59.630586714276724,"expected_score":35.807370890214244,"reasoning_variance":21.509393312439123,"reliability_score":98.61275839853977,"uncertainty_avg":1.3872416014602296,"uncertainty_penalty":-0.3106126663562634},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.64546823346215,"expected_score":31.98621228173859,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.621195865348778},"medium":{"ceiling_score":59.630586714276724,"expected_score":49.15156162139942,"reliability_score":95.20466106169059,"uncertainty_avg":4.795338938309407,"uncertainty_penalty":5.023593703867782},"none":{"ceiling_score":51.58180645988167,"expected_score":21.000153603840076,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6184210012524431}}},{"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":36.29047969706517,"highest":43.599988212612146,"medium":34.60521774334546,"none":30.66623313523792},"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":50.86244134919709,"mean":35.710303680479946,"min":3.872072017351666},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.48137058261478,"GB2-02":35.45001529607838,"GB2-03":37.63978744841054,"GB2-04":41.756439517176496,"GB2-05":48.8825630594869,"GB2-06":50.86244134919709,"GB2-07":46.70643609553631,"GB2-08":43.02085235239664},"per_game_all":{"GB2-01":40.68997316671346,"GB2-02":16.473596799145593,"GB2-03":36.36433105115082,"GB2-04":34.57835458403216,"GB2-05":42.949786626720446,"GB2-06":43.2677070715557,"GB2-07":41.25371236206305,"GB2-08":34.74637591514017},"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":44.48137058261478,"GB2-02":35.45001529607838,"GB2-03":37.63978744841054,"GB2-04":41.756439517176496,"GB2-05":48.8825630594869,"GB2-06":50.86244134919709,"GB2-07":46.70643609553631,"GB2-08":43.02085235239664},"medium":{"GB2-01":43.42288793742722,"GB2-02":10.098703084006734,"GB2-03":41.818965805599504,"GB2-04":35.0666411169392,"GB2-05":36.866899596586855,"GB2-06":35.79067812355425,"GB2-07":38.14606416585189,"GB2-08":35.63090211679806},"none":{"GB2-01":34.16566098009839,"GB2-02":3.872072017351666,"GB2-03":29.634239899442424,"GB2-04":26.9119831179808,"GB2-05":43.09989722408759,"GB2-06":43.15000174191575,"GB2-07":38.908636824800936,"GB2-08":25.587373276225822}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.59998821261214,"medium":33.38909206008818,"none":30.141830768739514},"reasoning_agg":{"highest":{"max":50.86244134919709,"mean":43.59998821261214,"min":35.45001529607838},"medium":{"max":43.42288793742722,"mean":33.38909206008818,"min":10.098703084006734},"none":{"max":43.15000174191575,"mean":30.141830768739514,"min":3.872072017351666}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":50.86244134919709,"expected_score":40.99140409744046,"reasoning_variance":13.458157443872626,"reliability_score":16.214253162425095,"uncertainty_avg":83.7857468375749,"uncertainty_penalty":5.281100416960513},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.86244134919709,"expected_score":38.65232258301897,"reliability_score":16.179010447538346,"uncertainty_avg":83.82098955246165,"uncertainty_penalty":-4.947665629593168},"medium":{"ceiling_score":43.42288793742722,"expected_score":40.33048745714392,"reliability_score":16.390466736858897,"uncertainty_avg":83.6095332631411,"uncertainty_penalty":6.941395397055736},"none":{"ceiling_score":43.15000174191575,"expected_score":43.99140225215848,"reliability_score":16.073282302878084,"uncertainty_avg":83.92671769712192,"uncertainty_penalty":13.849571483418966}}},{"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":0.010139173999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725613},"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":36.12658500680016,"none":39.18764503209153},"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":405,"losses":445,"wins":348},"match_totals_tracks":{"highest":{"draws":157,"losses":295,"wins":196},"none":{"draws":248,"losses":150,"wins":152}},"model_slug":"tencent-hy3-preview","overall":{"max":71.07282896064237,"mean":35.19742419481098,"min":13.758406271721789},"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":58.41330958645064,"GB2-02":13.758406271721789,"GB2-04":31.89937377831447,"GB2-05":58.289597890358415,"GB2-06":26.752823304656847,"GB2-07":25.647698335291103,"GB2-08":38.12488588080784},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":58,"wins":108},"GB2-02":{"draws":119,"losses":18,"wins":1},"GB2-03":{"draws":30,"losses":28,"wins":30},"GB2-04":{"draws":104,"losses":32,"wins":22},"GB2-05":{"draws":0,"losses":111,"wins":89},"GB2-06":{"draws":0,"losses":65,"wins":25},"GB2-07":{"draws":0,"losses":67,"wins":37},"GB2-08":{"draws":116,"losses":66,"wins":36}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":39,"wins":45},"GB2-02":{"draws":53,"losses":12,"wins":1},"GB2-04":{"draws":60,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":48,"wins":48},"GB2-06":{"draws":0,"losses":65,"wins":25},"GB2-07":{"draws":0,"losses":67,"wins":37},"GB2-08":{"draws":26,"losses":45,"wins":33}},"none":{"GB2-01":{"draws":18,"losses":19,"wins":63},"GB2-02":{"draws":66,"losses":6,"wins":0},"GB2-03":{"draws":30,"losses":28,"wins":30},"GB2-04":{"draws":44,"losses":13,"wins":15},"GB2-05":{"draws":0,"losses":63,"wins":41},"GB2-08":{"draws":90,"losses":21,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1614.8727554112447,"GB2-02":1444.0591535680944,"GB2-04":1428.305372108474,"GB2-05":1628.3276946126373,"GB2-06":1236.8815002319625,"GB2-07":1276.1948853703204,"GB2-08":1457.8491002180717},"none":{"GB2-01":1740.5175222083988,"GB2-02":1444.8163020312015,"GB2-03":1444.882558264278,"GB2-04":1506.6569734340017,"GB2-05":1329.3883779909766,"GB2-08":1417.9497965630508}},"per_game_tracks":{"highest":{"GB2-01":58.41330958645064,"GB2-02":13.758406271721789,"GB2-04":31.89937377831447,"GB2-05":58.289597890358415,"GB2-06":26.752823304656847,"GB2-07":25.647698335291103,"GB2-08":38.12488588080784},"none":{"GB2-01":71.07282896064237,"GB2-02":14.388654431203785,"GB2-03":38.551433143204484,"GB2-04":43.249796081077825,"GB2-05":33.59671726886273,"GB2-08":34.26644030755798}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.92663550598933,"none":36.46821288363263},"reasoning_agg":{"highest":{"max":58.41330958645064,"mean":33.92663550598933,"min":13.758406271721789},"none":{"max":71.07282896064237,"mean":36.46821288363263,"min":14.388654431203785}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":71.07282896064237,"reasoning_variance":2.5415773776433},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.41330958645064,"expected_score":21.212568104934906,"reliability_score":91.64594711201612,"uncertainty_avg":8.354052887983887,"uncertainty_penalty":-12.714067401054425},"none":{"ceiling_score":71.07282896064237,"expected_score":47.359571476857724,"reliability_score":91.21447587226827,"uncertainty_avg":8.785524127731733,"uncertainty_penalty":10.891358593225092}}},{"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":0.27157109999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995},"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":1.8519748999999996},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":34.29119703241208,"highest":35.62010828184078,"medium":27.137514209400695,"none":40.11596860599476},"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":1942,"losses":2725,"wins":1615},"match_totals_tracks":{"highest":{"draws":456,"losses":844,"wins":555},"medium":{"draws":713,"losses":1023,"wins":380},"none":{"draws":773,"losses":858,"wins":680}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":69.37028762269674,"mean":33.39036111727063,"min":9.276903456466506},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.072445927965525,"GB2-02":26.879776376230204,"GB2-03":53.05834174786712,"GB2-04":36.183653647643865,"GB2-05":24.21600641424555,"GB2-06":44.75966543731385,"GB2-07":44.78344638910896,"GB2-08":26.007530314351136},"per_game_all":{"GB2-01":35.24876416477925,"GB2-02":22.92772971791763,"GB2-03":47.79308783378854,"GB2-04":40.0127949040699,"GB2-05":16.663377328279047,"GB2-06":41.73079500447877,"GB2-07":43.14339864367571,"GB2-08":26.809628662307777},"per_game_match_totals_all":{"GB2-01":{"draws":184,"losses":393,"wins":283},"GB2-02":{"draws":420,"losses":30,"wins":13},"GB2-03":{"draws":232,"losses":255,"wins":234},"GB2-04":{"draws":529,"losses":142,"wins":103},"GB2-05":{"draws":0,"losses":758,"wins":192},"GB2-06":{"draws":21,"losses":528,"wins":363},"GB2-07":{"draws":0,"losses":376,"wins":393},"GB2-08":{"draws":556,"losses":243,"wins":34}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":28,"losses":78,"wins":34},"GB2-02":{"draws":81,"losses":8,"wins":11},"GB2-03":{"draws":61,"losses":95,"wins":108},"GB2-04":{"draws":171,"losses":66,"wins":35},"GB2-05":{"draws":0,"losses":222,"wins":78},"GB2-06":{"draws":13,"losses":152,"wins":129},"GB2-07":{"draws":0,"losses":162,"wins":153},"GB2-08":{"draws":102,"losses":61,"wins":7}},"medium":{"GB2-01":{"draws":73,"losses":155,"wins":138},"GB2-02":{"draws":105,"losses":2,"wins":0},"GB2-03":{"draws":119,"losses":109,"wins":53},"GB2-04":{"draws":195,"losses":31,"wins":18},"GB2-05":{"draws":0,"losses":259,"wins":67},"GB2-06":{"draws":4,"losses":260,"wins":52},"GB2-07":{"draws":0,"losses":117,"wins":39},"GB2-08":{"draws":217,"losses":90,"wins":13}},"none":{"GB2-01":{"draws":83,"losses":160,"wins":111},"GB2-02":{"draws":234,"losses":20,"wins":2},"GB2-03":{"draws":52,"losses":51,"wins":73},"GB2-04":{"draws":163,"losses":45,"wins":50},"GB2-05":{"draws":0,"losses":277,"wins":47},"GB2-06":{"draws":4,"losses":116,"wins":182},"GB2-07":{"draws":0,"losses":97,"wins":201},"GB2-08":{"draws":237,"losses":92,"wins":14}}},"per_game_raw_elo_all":{"GB2-01":1377.4870413230612,"GB2-02":1473.888639531993,"GB2-03":1503.1292580460147,"GB2-04":1473.761277799119,"GB2-05":1118.1406764150752,"GB2-06":1400.4923687074242,"GB2-07":1455.1853758524169,"GB2-08":1337.7537235331965},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1318.8398191425192,"GB2-02":1493.463385992254,"GB2-03":1543.7025318084882,"GB2-04":1447.685284464945,"GB2-05":1209.9376686322128,"GB2-06":1436.0497650366196,"GB2-07":1472.2642846072872,"GB2-08":1329.5503292837363},"medium":{"GB2-01":1425.2662451167348,"GB2-02":1472.044979547752,"GB2-03":1432.9985313839934,"GB2-04":1465.3565254548685,"GB2-05":1115.6686528221212,"GB2-06":1145.0239194216756,"GB2-07":1158.879352478688,"GB2-08":1334.025892170579},"none":{"GB2-01":1388.3550597099304,"GB2-02":1456.157553055973,"GB2-03":1532.6867109455625,"GB2-04":1508.2420234775436,"GB2-05":1028.8157077908918,"GB2-06":1620.4034216639773,"GB2-07":1734.4124904712762,"GB2-08":1349.6849491452738}},"per_game_tracks":{"highest":{"GB2-01":29.072445927965525,"GB2-02":26.879776376230204,"GB2-03":53.05834174786712,"GB2-04":36.183653647643865,"GB2-05":24.21600641424555,"GB2-06":44.75966543731385,"GB2-07":44.78344638910896,"GB2-08":26.007530314351136},"medium":{"GB2-01":40.20117378359939,"GB2-02":22.367578645782174,"GB2-03":38.12765176299469,"GB2-04":38.573622197421955,"GB2-05":16.497222114125087,"GB2-06":19.691715205934457,"GB2-07":15.276461919221447,"GB2-08":26.364688046126368},"none":{"GB2-01":36.47267278277283,"GB2-02":19.535834131740515,"GB2-03":52.19326999050381,"GB2-04":45.281108867143885,"GB2-05":9.276903456466506,"GB2-06":60.74100437018801,"GB2-07":69.37028762269674,"GB2-08":28.056667626445826}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.45063637172133,"medium":26.246541045387577,"none":39.473905934702984},"reasoning_agg":{"highest":{"max":53.05834174786712,"mean":34.45063637172133,"min":24.21600641424555},"medium":{"max":40.20117378359939,"mean":26.246541045387577,"min":15.276461919221447},"none":{"max":69.37028762269674,"mean":39.473905934702984,"min":9.276903456466506}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":69.37028762269674,"expected_score":27.693469478471847,"reasoning_variance":13.227364889315407,"reliability_score":99.45654055522557,"uncertainty_avg":0.5434594447744298,"uncertainty_penalty":-5.696891638798782},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.05834174786712,"expected_score":17.7899537370125,"reliability_score":99.18905758931282,"uncertainty_avg":0.8109424106871699,"uncertainty_penalty":-16.66068263470883},"medium":{"ceiling_score":40.20117378359939,"expected_score":18.915829232458766,"reliability_score":99.23621225055682,"uncertainty_avg":0.7637877494431888,"uncertainty_penalty":-7.330711812928811},"none":{"ceiling_score":69.37028762269674,"expected_score":46.37462546594428,"reliability_score":99.94435182580708,"uncertainty_avg":0.055648174192930444,"uncertainty_penalty":6.900719531241293}}},{"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":0.08145696000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"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":45.846013941307554,"none":26.44462943801277},"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":378,"losses":473,"wins":338},"match_totals_tracks":{"medium":{"draws":198,"losses":218,"wins":222},"none":{"draws":180,"losses":255,"wins":116}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":70.50103787240695,"mean":33.27997174457582,"min":4.247286587507169},"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":44,"losses":97,"wins":59},"GB2-02":{"draws":172,"losses":5,"wins":1},"GB2-04":{"draws":61,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":118,"wins":108},"GB2-06":{"draws":7,"losses":102,"wins":90},"GB2-07":{"draws":0,"losses":123,"wins":75},"GB2-08":{"draws":94,"losses":20,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":18,"losses":42,"wins":40},"GB2-02":{"draws":81,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":64,"wins":60},"GB2-06":{"draws":5,"losses":31,"wins":64},"GB2-07":{"draws":0,"losses":57,"wins":57},"GB2-08":{"draws":94,"losses":20,"wins":0}},"none":{"GB2-01":{"draws":26,"losses":55,"wins":19},"GB2-02":{"draws":91,"losses":1,"wins":0},"GB2-04":{"draws":61,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":54,"wins":48},"GB2-06":{"draws":2,"losses":71,"wins":26},"GB2-07":{"draws":0,"losses":66,"wins":18}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1513.515357215152,"GB2-02":1480.3725891120614,"GB2-05":1607.3794802947366,"GB2-06":1740.616275075024,"GB2-07":1450.7149866418183,"GB2-08":1415.39305533373},"none":{"GB2-01":1300.7914998768108,"GB2-02":1453.658322014426,"GB2-04":1469.91418843072,"GB2-05":1476.341736666781,"GB2-06":1234.4468531079099,"GB2-07":1053.14781558953}},"per_game_tracks":{"medium":{"GB2-01":48.12999209690405,"GB2-02":23.250211486876427,"GB2-05":56.95170350971318,"GB2-06":70.50103787240695,"GB2-07":42.23519271244378,"GB2-08":34.007945969500966},"none":{"GB2-01":26.630246682212057,"GB2-02":17.570880513249598,"GB2-04":37.7416657545222,"GB2-05":45.76839619365652,"GB2-06":26.709300896929104,"GB2-07":4.247286587507169}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":42.664523344243406,"none":23.89542014490823},"reasoning_agg":{"medium":{"max":70.50103787240695,"mean":42.664523344243406,"min":23.250211486876427},"none":{"max":45.76839619365652,"mean":23.89542014490823,"min":4.247286587507169}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":70.50103787240695,"reasoning_variance":18.769103199335177},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":70.50103787240695,"expected_score":47.74019423427945,"reliability_score":95.23646897718069,"uncertainty_avg":4.763531022819305,"uncertainty_penalty":5.075670890036044},"none":{"ceiling_score":45.76839619365652,"expected_score":27.898273333975904,"reliability_score":91.611075078523,"uncertainty_avg":8.388924921476999,"uncertainty_penalty":4.002853189067675}}},{"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":0.06253070000000001},"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":41.52733113500447,"none":31.150644590364877},"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":266,"losses":452,"wins":332},"match_totals_tracks":{"medium":{"draws":76,"losses":197,"wins":169},"none":{"draws":190,"losses":255,"wins":163}},"model_slug":"google-gemma-4-31b-it","overall":{"max":55.00038838965367,"mean":33.03930197291725,"min":17.377509992236185},"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":33,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":40,"wins":55},"GB2-04":{"draws":144,"losses":15,"wins":19},"GB2-05":{"draws":0,"losses":125,"wins":93},"GB2-06":{"draws":3,"losses":135,"wins":82},"GB2-07":{"draws":0,"losses":116,"wins":80},"GB2-08":{"draws":94,"losses":21,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":75,"losses":6,"wins":9},"GB2-05":{"draws":0,"losses":58,"wins":66},"GB2-06":{"draws":1,"losses":76,"wins":41},"GB2-07":{"draws":0,"losses":57,"wins":53}},"none":{"GB2-01":{"draws":25,"losses":40,"wins":55},"GB2-04":{"draws":69,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":67,"wins":27},"GB2-06":{"draws":2,"losses":59,"wins":41},"GB2-07":{"draws":0,"losses":59,"wins":27},"GB2-08":{"draws":94,"losses":21,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1463.0389711785886,"GB2-05":1583.880968834933,"GB2-06":1333.1575713568993,"GB2-07":1408.849027987095},"none":{"GB2-01":1453.704251657997,"GB2-04":1478.369156952384,"GB2-05":1136.0733751755404,"GB2-06":1313.9232512674864,"GB2-07":1217.1234130773007,"GB2-08":1415.9221194161503}},"per_game_tracks":{"medium":{"GB2-04":37.342280705591044,"GB2-05":55.00038838965367,"GB2-06":35.53416954938754,"GB2-07":38.232485895385615},"none":{"GB2-01":42.432414819587265,"GB2-04":39.60896936866197,"GB2-05":17.377509992236185,"GB2-06":33.633332893697606,"GB2-07":19.726281854437815,"GB2-08":34.12535861356842}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.10559520111506,"none":29.973008744719447},"reasoning_agg":{"medium":{"max":55.00038838965367,"mean":36.10559520111506,"min":35.53416954938754},"none":{"max":42.432414819587265,"mean":29.973008744719447,"min":17.377509992236185}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.00038838965367,"reasoning_variance":6.132586456395611},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":55.00038838965367,"expected_score":42.81507183928192,"reliability_score":96.14289349371819,"uncertainty_avg":3.857106506281809,"uncertainty_penalty":6.709476638166862},"none":{"ceiling_score":42.432414819587265,"expected_score":33.243034031814055,"reliability_score":94.0066045732273,"uncertainty_avg":5.99339542677269,"uncertainty_penalty":3.270025287094608}}},{"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":0.38761485}},"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":0.5373186000000001},"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":33.51122596610653,"highest":36.52576900215633,"medium":32.1140712541683,"none":32.34497402709219},"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":54.116030920939295,"mean":32.377537246167044,"min":11.574430248545012},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":34,"overall_ranking_status":"partial","per_game":{"GB2-02":11.574430248545012,"GB2-03":45.53778410260007,"GB2-04":44.49159171005959,"GB2-05":43.47012582547535,"GB2-06":54.116030920939295,"GB2-07":22.881993246353847,"GB2-08":33.608426961121125},"per_game_all":{"GB2-02":13.584938181894444,"GB2-03":42.31912666838272,"GB2-04":37.94109020594699,"GB2-05":33.27041065799279,"GB2-06":41.11074718938405,"GB2-07":34.050691727918,"GB2-08":32.30157713122671},"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":1486.4409461299583,"GB2-03":1524.4933026068854,"GB2-04":1518.8897239376074,"GB2-05":1380.776677209483,"GB2-06":1451.5512034692485,"GB2-07":1417.6957118195394,"GB2-08":1460.4021622463351},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1482.473546162997,"GB2-03":1545.532411443232,"GB2-04":1562.2633173996858,"GB2-05":1503.5327853795927,"GB2-06":1608.3676756467582,"GB2-07":1304.7852176135736,"GB2-08":1468.4221652498795},"medium":{"GB2-01":1346.7122318417303,"GB2-02":1484.2472717904682,"GB2-03":1509.8258524700977,"GB2-04":1469.3700914144779,"GB2-05":1363.5335221414252,"GB2-06":1377.382181449011,"GB2-07":1542.484591986778,"GB2-08":1460.0832035786366},"none":{"GB2-01":1494.0445342877708,"GB2-02":1492.6020204364095,"GB2-03":1518.121643907326,"GB2-04":1525.0357629986581,"GB2-05":1275.2637241074317,"GB2-06":1368.9037533119765,"GB2-07":1405.8173258582663,"GB2-08":1452.7011179104888}},"per_game_tracks":{"highest":{"GB2-02":11.574430248545012,"GB2-03":45.53778410260007,"GB2-04":44.49159171005959,"GB2-05":43.47012582547535,"GB2-06":54.116030920939295,"GB2-07":22.881993246353847,"GB2-08":33.608426961121125},"medium":{"GB2-01":26.47208042284504,"GB2-02":14.155329190210882,"GB2-03":40.330911797900164,"GB2-04":31.39027464270986,"GB2-05":31.61761768988316,"GB2-06":34.79473339617072,"GB2-07":45.96450843356181,"GB2-08":32.187114460064755},"none":{"GB2-01":41.144919554096006,"GB2-02":15.025055106927441,"GB2-03":41.08868410464794,"GB2-04":37.941404265071526,"GB2-05":24.72348845861986,"GB2-06":34.421477251042134,"GB2-07":33.305573503838346,"GB2-08":31.109189972494256}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.543939546177654,"medium":31.182234699842784,"none":31.4064374924807},"reasoning_agg":{"highest":{"max":54.116030920939295,"mean":34.543939546177654,"min":11.574430248545012},"medium":{"max":45.96450843356181,"mean":31.182234699842784,"min":14.155329190210882},"none":{"max":41.144919554096006,"mean":31.4064374924807,"min":15.025055106927441}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":54.116030920939295,"expected_score":37.00260271851942,"reasoning_variance":3.36170484633487,"reliability_score":26.678541888425713,"uncertainty_avg":73.32145811157429,"uncertainty_penalty":4.625065472352375},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.116030920939295,"expected_score":28.50894052103188,"reliability_score":24.883614988135136,"uncertainty_avg":75.11638501186486,"uncertainty_penalty":-6.034999025145773},"medium":{"ceiling_score":45.96450843356181,"expected_score":34.45239227839326,"reliability_score":29.3684280225135,"uncertainty_avg":70.6315719774865,"uncertainty_penalty":3.270157578550478},"none":{"ceiling_score":41.144919554096006,"expected_score":46.88726767741367,"reliability_score":27.213038320862537,"uncertainty_avg":72.78696167913746,"uncertainty_penalty":15.48083018493297}}},{"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":0.05097333066},"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":0.05097333066},"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":0.14908945064},"codegen_latency_ms":{"attempt_count":25,"max_ms":1394682,"mean_ms":281124.875,"min_ms":22331,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1394682,"mean_ms":494109.375,"min_ms":61403,"run_count":8},"none":{"attempt_count":11,"max_ms":129944,"mean_ms":68140.375,"min_ms":22331,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":82048,"output_mean":17675.4375,"output_min":1698,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":82048,"output_mean":31903.25,"output_min":4091,"run_count":8},"none":{"attempt_count":11,"output_max":6315,"output_mean":3447.625,"output_min":1698,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":32.6405739762851,"highest":39.93877346153044,"medium":32.39306411364516,"none":28.29631741105212},"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":777,"losses":919,"wins":552},"match_totals_tracks":{"highest":{"draws":155,"losses":231,"wins":174},"medium":{"draws":369,"losses":431,"wins":242},"none":{"draws":253,"losses":257,"wins":136}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":72.03816050961174,"mean":31.954685717749697,"min":16.918306920549412},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":35,"overall_ranking_status":"partial","per_game":{"GB2-01":31.797564014719292,"GB2-02":22.300174477766653,"GB2-05":51.803795837193945,"GB2-06":29.52707950589016,"GB2-07":72.03816050961174,"GB2-08":32.16586642400081},"per_game_all":{"GB2-02":19.46399875998714,"GB2-05":40.41147506097852,"GB2-06":24.539755224605873,"GB2-07":46.72914241876557,"GB2-08":32.05849841708838},"per_game_match_totals_all":{"GB2-01":{"draws":57,"losses":133,"wins":56},"GB2-02":{"draws":253,"losses":34,"wins":7},"GB2-03":{"draws":58,"losses":49,"wins":35},"GB2-04":{"draws":97,"losses":35,"wins":8},"GB2-05":{"draws":0,"losses":205,"wins":169},"GB2-06":{"draws":3,"losses":232,"wins":101},"GB2-07":{"draws":0,"losses":168,"wins":164},"GB2-08":{"draws":309,"losses":63,"wins":12}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":51,"wins":25},"GB2-02":{"draws":59,"losses":11,"wins":4},"GB2-05":{"draws":0,"losses":48,"wins":54},"GB2-06":{"draws":1,"losses":61,"wins":24},"GB2-07":{"draws":0,"losses":31,"wins":65},"GB2-08":{"draws":77,"losses":29,"wins":2}},"medium":{"GB2-01":{"draws":39,"losses":82,"wins":31},"GB2-02":{"draws":114,"losses":20,"wins":2},"GB2-03":{"draws":18,"losses":21,"wins":15},"GB2-04":{"draws":53,"losses":9,"wins":4},"GB2-05":{"draws":0,"losses":93,"wins":65},"GB2-06":{"draws":1,"losses":101,"wins":58},"GB2-07":{"draws":0,"losses":89,"wins":63},"GB2-08":{"draws":144,"losses":16,"wins":4}},"none":{"GB2-02":{"draws":80,"losses":3,"wins":1},"GB2-03":{"draws":40,"losses":28,"wins":20},"GB2-04":{"draws":44,"losses":26,"wins":4},"GB2-05":{"draws":0,"losses":64,"wins":50},"GB2-06":{"draws":1,"losses":70,"wins":19},"GB2-07":{"draws":0,"losses":48,"wins":36},"GB2-08":{"draws":88,"losses":18,"wins":6}}},"per_game_raw_elo_all":{"GB2-02":1466.530779069996,"GB2-05":1412.8975088211334,"GB2-06":1212.446974149287,"GB2-07":1504.36146730321,"GB2-08":1398.7634600837148},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1353.1558761739786,"GB2-02":1479.442621444907,"GB2-05":1549.0224155741603,"GB2-06":1269.9135910657938,"GB2-07":1770.709939839599,"GB2-08":1398.1860928220167},"medium":{"GB2-01":1360.8578517467413,"GB2-02":1457.4662368310856,"GB2-03":1523.0961019109775,"GB2-04":1470.9778216962018,"GB2-05":1284.9171506996952,"GB2-06":1244.2632602994895,"GB2-07":1405.3669338787731,"GB2-08":1394.044883352306},"none":{"GB2-02":1462.6834789339953,"GB2-03":1430.6399776232663,"GB2-04":1363.997401760583,"GB2-05":1404.752960189545,"GB2-06":1123.1640710825773,"GB2-07":1337.0075281912582,"GB2-08":1404.0594040768221}},"per_game_tracks":{"highest":{"GB2-01":31.797564014719292,"GB2-02":22.300174477766653,"GB2-05":51.803795837193945,"GB2-06":29.52707950589016,"GB2-07":72.03816050961174,"GB2-08":32.16586642400081},"medium":{"GB2-01":32.116626000567756,"GB2-02":16.923785423162606,"GB2-03":47.63490899953319,"GB2-04":37.49517602497302,"GB2-05":29.431499631947965,"GB2-06":27.173879247378046,"GB2-07":37.187861256738046,"GB2-08":31.180776324860656},"none":{"GB2-02":19.168036379032152,"GB2-03":36.61116549844097,"GB2-04":21.587325373198095,"GB2-05":39.99912971379366,"GB2-06":16.918306920549412,"GB2-07":30.9614054899469,"GB2-08":32.82885250240368}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.167216649878206,"medium":31.329541839544742,"none":27.36729866382614},"reasoning_agg":{"highest":{"max":72.03816050961174,"mean":37.167216649878206,"min":22.300174477766653},"medium":{"max":47.63490899953319,"mean":31.329541839544742,"min":16.923785423162606},"none":{"max":39.99912971379366,"mean":27.36729866382614,"min":16.918306920549412}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.03816050961174,"expected_score":25.540282662132316,"reasoning_variance":9.799917986052066,"reliability_score":90.59311324674931,"uncertainty_avg":9.406886753250692,"uncertainty_penalty":-6.414403055617381},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.03816050961174,"expected_score":27.621763074063193,"reliability_score":91.98922371815614,"uncertainty_avg":8.010776281843865,"uncertainty_penalty":-9.545453575815014},"medium":{"ceiling_score":47.63490899953319,"expected_score":27.77241784382211,"reliability_score":85.1210245887961,"uncertainty_avg":14.878975411203893,"uncertainty_penalty":-3.5571239957226304},"none":{"ceiling_score":39.99912971379366,"expected_score":31.303666579296777,"reliability_score":91.56776064344284,"uncertainty_avg":8.432239356557162,"uncertainty_penalty":3.936367915470637}}},{"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":0.04917796},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":28.928846631529616,"none":37.83510598141368},"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":1183,"losses":1184,"wins":725},"match_totals_tracks":{"medium":{"draws":722,"losses":724,"wins":313},"none":{"draws":461,"losses":460,"wins":412}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":54.815141934474596,"mean":31.820507612172108,"min":18.971051988167996},"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":36,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":82,"losses":182,"wins":136},"GB2-02":{"draws":324,"losses":13,"wins":3},"GB2-03":{"draws":242,"losses":200,"wins":127},"GB2-04":{"draws":94,"losses":46,"wins":12},"GB2-05":{"draws":0,"losses":323,"wins":248},"GB2-06":{"draws":11,"losses":183,"wins":90},"GB2-07":{"draws":0,"losses":113,"wins":89},"GB2-08":{"draws":430,"losses":124,"wins":20}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":28,"losses":74,"wins":58},"GB2-02":{"draws":225,"losses":9,"wins":0},"GB2-03":{"draws":133,"losses":123,"wins":62},"GB2-04":{"draws":94,"losses":46,"wins":12},"GB2-05":{"draws":0,"losses":252,"wins":123},"GB2-06":{"draws":7,"losses":125,"wins":44},"GB2-08":{"draws":235,"losses":95,"wins":14}},"none":{"GB2-01":{"draws":54,"losses":108,"wins":78},"GB2-02":{"draws":99,"losses":4,"wins":3},"GB2-03":{"draws":109,"losses":77,"wins":65},"GB2-05":{"draws":0,"losses":71,"wins":125},"GB2-06":{"draws":4,"losses":58,"wins":46},"GB2-07":{"draws":0,"losses":113,"wins":89},"GB2-08":{"draws":195,"losses":29,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1415.0856930075604,"GB2-02":1465.1384095012668,"GB2-03":1406.9195777629861,"GB2-04":1380.6694525948496,"GB2-05":1299.0500309172046,"GB2-06":1156.182973847154,"GB2-08":1354.0937791457006},"none":{"GB2-01":1477.0026155738424,"GB2-02":1457.0890590046167,"GB2-03":1449.4006292034796,"GB2-05":1586.099222433189,"GB2-06":1210.0954507274137,"GB2-07":1544.010143590685,"GB2-08":1383.4836426691504}},"per_game_tracks":{"medium":{"GB2-01":39.01837754189059,"GB2-02":21.191551614417335,"GB2-03":34.84632546230651,"GB2-04":26.24251380391939,"GB2-05":31.896275052743633,"GB2-06":20.800006608149722,"GB2-08":28.50687633728013},"none":{"GB2-01":44.7867759390862,"GB2-02":18.971051988167996,"GB2-03":39.927445639857304,"GB2-05":54.815141934474596,"GB2-06":24.749232472982165,"GB2-07":50.79810134192654,"GB2-08":30.797992553400974}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.236248088672685,"none":36.40476713567153},"reasoning_agg":{"medium":{"max":39.01837754189059,"mean":27.236248088672685,"min":20.800006608149722},"none":{"max":54.815141934474596,"mean":36.40476713567153,"min":18.971051988167996}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":54.815141934474596,"reasoning_variance":9.168519046998842},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":39.01837754189059,"expected_score":17.423131955883946,"reliability_score":99.67428991403479,"uncertainty_avg":0.32571008596521367,"uncertainty_penalty":-9.813116132788739},"none":{"ceiling_score":54.815141934474596,"expected_score":39.711811673081286,"reliability_score":95.7101043066367,"uncertainty_avg":4.289895693363306,"uncertainty_penalty":3.307044537409759}}},{"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":0.00169122,"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":0.21411433159999999},"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":0.19736108439999997}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":16,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.00169122,"recorded_attempt_count":108,"run_count":56,"total":0.7524538072},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":33.724249612802154,"highest":34.32762282883395,"medium":34.100059033206605,"none":36.67030236955936},"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":1220,"losses":1264,"wins":906},"match_totals_tracks":{"highest":{"draws":231,"losses":85,"wins":48},"medium":{"draws":569,"losses":590,"wins":369},"none":{"draws":420,"losses":589,"wins":489}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":55.77389183234963,"mean":31.575394430852445,"min":17.065325253973946},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":37,"overall_ranking_status":"partial","per_game":{"GB2-01":17.065325253973946,"GB2-02":27.437307852969795,"GB2-04":40.63045169882911,"GB2-06":55.77389183234963,"GB2-08":30.7311375060473},"per_game_all":{"GB2-01":31.487883078791185,"GB2-02":23.089088483752388,"GB2-04":39.350563835168025,"GB2-06":45.45129260064409,"GB2-08":29.24242006565505},"per_game_match_totals_all":{"GB2-01":{"draws":123,"losses":279,"wins":196},"GB2-02":{"draws":353,"losses":33,"wins":12},"GB2-03":{"draws":41,"losses":26,"wins":21},"GB2-04":{"draws":384,"losses":77,"wins":43},"GB2-05":{"draws":0,"losses":273,"wins":227},"GB2-06":{"draws":16,"losses":243,"wins":205},"GB2-07":{"draws":0,"losses":202,"wins":172},"GB2-08":{"draws":303,"losses":131,"wins":30}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":41,"losses":29,"wins":2},"GB2-02":{"draws":60,"losses":11,"wins":3},"GB2-04":{"draws":52,"losses":10,"wins":6},"GB2-06":{"draws":7,"losses":30,"wins":35},"GB2-08":{"draws":71,"losses":5,"wins":2}},"medium":{"GB2-01":{"draws":19,"losses":116,"wins":77},"GB2-02":{"draws":228,"losses":21,"wins":9},"GB2-04":{"draws":219,"losses":57,"wins":16},"GB2-05":{"draws":0,"losses":140,"wins":104},"GB2-06":{"draws":5,"losses":77,"wins":42},"GB2-07":{"draws":0,"losses":103,"wins":97},"GB2-08":{"draws":98,"losses":76,"wins":24}},"none":{"GB2-01":{"draws":63,"losses":134,"wins":117},"GB2-02":{"draws":65,"losses":1,"wins":0},"GB2-03":{"draws":41,"losses":26,"wins":21},"GB2-04":{"draws":113,"losses":10,"wins":21},"GB2-05":{"draws":0,"losses":133,"wins":123},"GB2-06":{"draws":4,"losses":136,"wins":128},"GB2-07":{"draws":0,"losses":99,"wins":75},"GB2-08":{"draws":134,"losses":50,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1350.5774449304097,"GB2-02":1482.7637862123702,"GB2-04":1479.4046205599461,"GB2-06":1452.7591750524134,"GB2-08":1372.9865444773925},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1213.1687467409479,"GB2-02":1502.3343523013145,"GB2-04":1490.8209858823616,"GB2-06":1577.339884678403,"GB2-08":1390.6857995210323},"medium":{"GB2-01":1343.1444354252926,"GB2-02":1476.0985457153822,"GB2-04":1464.8146522742954,"GB2-05":1415.8281286887423,"GB2-06":1340.4538958273813,"GB2-07":1430.6955545265241,"GB2-08":1380.240453455008},"none":{"GB2-01":1495.4191526249888,"GB2-02":1469.8584606204145,"GB2-03":1494.2810908524089,"GB2-04":1482.5782235231818,"GB2-05":1438.1145701397409,"GB2-06":1440.4837446514557,"GB2-07":1316.8492403373612,"GB2-08":1348.0333804561371}},"per_game_tracks":{"highest":{"GB2-01":17.065325253973946,"GB2-02":27.437307852969795,"GB2-04":40.63045169882911,"GB2-06":55.77389183234963,"GB2-08":30.7311375060473},"medium":{"GB2-01":31.023169583821865,"GB2-02":22.281928770414922,"GB2-04":37.845925647546906,"GB2-05":41.01646733124801,"GB2-06":36.242213374439,"GB2-07":40.113554926110965,"GB2-08":30.177153598864578},"none":{"GB2-01":46.37515439857774,"GB2-02":19.548028827872443,"GB2-03":45.280998303857686,"GB2-04":39.57531415912807,"GB2-05":42.291871269429016,"GB2-06":44.33777259514364,"GB2-07":29.134310310413017,"GB2-08":26.81896909205326}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.522052436048757,"medium":30.812881665619475,"none":33.391249190889106},"reasoning_agg":{"highest":{"max":55.77389183234963,"mean":30.522052436048757,"min":17.065325253973946},"medium":{"max":41.01646733124801,"mean":30.812881665619475,"min":22.281928770414922},"none":{"max":46.37515439857774,"mean":33.391249190889106,"min":19.548028827872443}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.77389183234963,"expected_score":28.1084985212213,"reasoning_variance":2.869196754840349,"reliability_score":89.68149625100176,"uncertainty_avg":10.31850374899824,"uncertainty_penalty":-3.4668959096311447},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.77389183234963,"expected_score":20.846772028352,"reliability_score":85.50530085914421,"uncertainty_avg":14.49469914085579,"uncertainty_penalty":-9.675280407696757},"medium":{"ceiling_score":41.01646733124801,"expected_score":32.138091200993294,"reliability_score":94.85543331035772,"uncertainty_avg":5.144566689642278,"uncertainty_penalty":1.3252095353738191},"none":{"ceiling_score":46.37515439857774,"expected_score":43.57505299401501,"reliability_score":89.67148164014624,"uncertainty_avg":10.328518359853756,"uncertainty_penalty":10.183803803125905}}},{"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":0.31772779999999995},"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":40.69387486702664,"highest":34.73276605228333,"medium":34.21970648915008,"none":36.179124442808664},"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":706,"losses":705,"wins":418},"match_totals_tracks":{"highest":{"draws":342,"losses":319,"wins":158},"medium":{"draws":186,"losses":177,"wins":123},"none":{"draws":178,"losses":209,"wins":137}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":60.46921496514469,"mean":31.19955846631954,"min":10.757672736091521},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":38,"overall_ranking_status":"partial","per_game":{"GB2-01":36.82037411124304,"GB2-02":19.283288670132,"GB2-04":37.17290928698389,"GB2-05":42.912176221849236,"GB2-06":40.27021537575938,"GB2-08":31.93763264773245},"per_game_all":{"GB2-01":46.44477138668932,"GB2-06":42.640056037580145,"GB2-08":32.996797176810475},"per_game_match_totals_all":{"GB2-01":{"draws":54,"losses":132,"wins":90},"GB2-02":{"draws":202,"losses":23,"wins":3},"GB2-03":{"draws":38,"losses":9,"wins":3},"GB2-04":{"draws":113,"losses":26,"wins":13},"GB2-05":{"draws":0,"losses":155,"wins":143},"GB2-06":{"draws":15,"losses":145,"wins":109},"GB2-07":{"draws":0,"losses":134,"wins":32},"GB2-08":{"draws":284,"losses":81,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":52,"wins":22},"GB2-02":{"draws":118,"losses":18,"wins":2},"GB2-04":{"draws":65,"losses":19,"wins":6},"GB2-05":{"draws":0,"losses":122,"wins":88},"GB2-06":{"draws":7,"losses":59,"wins":25},"GB2-08":{"draws":132,"losses":49,"wins":15}},"medium":{"GB2-01":{"draws":20,"losses":36,"wins":40},"GB2-02":{"draws":84,"losses":5,"wins":1},"GB2-06":{"draws":8,"losses":37,"wins":53},"GB2-07":{"draws":0,"losses":72,"wins":20},"GB2-08":{"draws":74,"losses":27,"wins":9}},"none":{"GB2-01":{"draws":14,"losses":44,"wins":28},"GB2-03":{"draws":38,"losses":9,"wins":3},"GB2-04":{"draws":48,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":33,"wins":55},"GB2-06":{"draws":0,"losses":49,"wins":31},"GB2-07":{"draws":0,"losses":62,"wins":12},"GB2-08":{"draws":78,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1498.552368522661,"GB2-06":1420.7719388903897,"GB2-08":1408.6281752985008},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1402.8528152679808,"GB2-02":1467.6237702694034,"GB2-04":1461.9284785190819,"GB2-05":1441.4480042293753,"GB2-06":1392.9558533954528,"GB2-08":1397.872639678978},"medium":{"GB2-01":1528.1057891742366,"GB2-02":1453.1606606288503,"GB2-06":1625.0173972189637,"GB2-07":1120.4180547333053,"GB2-08":1406.0071008564112},"none":{"GB2-01":1564.6985011257657,"GB2-03":1393.790497688098,"GB2-04":1498.4721260722356,"GB2-05":1593.0579629263639,"GB2-06":1244.3425660567527,"GB2-07":1144.8702182648058,"GB2-08":1422.0047853601131}},"per_game_tracks":{"highest":{"GB2-01":36.82037411124304,"GB2-02":19.283288670132,"GB2-04":37.17290928698389,"GB2-05":42.912176221849236,"GB2-06":40.27021537575938,"GB2-08":31.93763264773245},"medium":{"GB2-01":49.52252542484147,"GB2-02":17.357469503708607,"GB2-06":60.46921496514469,"GB2-07":10.757672736091521,"GB2-08":32.99164981596408},"none":{"GB2-01":52.991414623983445,"GB2-03":29.736891928612994,"GB2-04":41.455613711503254,"GB2-05":55.212486240190024,"GB2-06":27.180737771836384,"GB2-07":12.615617756799654,"GB2-08":34.06110906673491}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.079457744979113,"medium":29.54324213163337,"none":33.97597552234614},"reasoning_agg":{"highest":{"max":42.912176221849236,"mean":30.079457744979113,"min":19.283288670132},"medium":{"max":60.46921496514469,"mean":29.54324213163337,"min":10.757672736091521},"none":{"max":55.212486240190024,"mean":33.97597552234614,"min":12.615617756799654}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.46921496514469,"expected_score":33.32069084191583,"reasoning_variance":4.4327333907127695,"reliability_score":92.01447657001376,"uncertainty_avg":7.985523429986245,"uncertainty_penalty":2.121132375596286},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.912176221849236,"expected_score":20.27115755605925,"reliability_score":91.3211618393408,"uncertainty_avg":8.678838160659192,"uncertainty_penalty":-9.808300188919862},"medium":{"ceiling_score":60.46921496514469,"expected_score":31.56461961715065,"reliability_score":93.20221492402327,"uncertainty_avg":6.797785075976736,"uncertainty_penalty":2.021377485517281},"none":{"ceiling_score":55.212486240190024,"expected_score":44.1995561258312,"reliability_score":85.58759989890548,"uncertainty_avg":14.412400101094516,"uncertainty_penalty":10.223580603485061}}},{"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":0.20304798000000002}},"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":0.20304798000000002}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.7875583200000001},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":27.72984940569012,"none":38.2144104593529},"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":378,"losses":577,"wins":373},"match_totals_tracks":{"medium":{"draws":244,"losses":350,"wins":148},"none":{"draws":134,"losses":227,"wins":225}},"model_slug":"minimax-minimax-m3","overall":{"max":49.061655826617994,"mean":31.190972439089,"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":39,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":31,"losses":108,"wins":87},"GB2-02":{"draws":140,"losses":17,"wins":1},"GB2-03":{"draws":34,"losses":26,"wins":32},"GB2-04":{"draws":76,"losses":9,"wins":7},"GB2-05":{"draws":0,"losses":161,"wins":59},"GB2-06":{"draws":0,"losses":79,"wins":41},"GB2-07":{"draws":0,"losses":109,"wins":99},"GB2-08":{"draws":97,"losses":68,"wins":47}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":68,"wins":27},"GB2-02":{"draws":71,"losses":14,"wins":1},"GB2-04":{"draws":76,"losses":9,"wins":7},"GB2-05":{"draws":0,"losses":103,"wins":3},"GB2-06":{"draws":0,"losses":79,"wins":41},"GB2-07":{"draws":0,"losses":58,"wins":62},"GB2-08":{"draws":90,"losses":19,"wins":7}},"none":{"GB2-01":{"draws":24,"losses":40,"wins":60},"GB2-02":{"draws":69,"losses":3,"wins":0},"GB2-03":{"draws":34,"losses":26,"wins":32},"GB2-05":{"draws":0,"losses":58,"wins":56},"GB2-07":{"draws":0,"losses":51,"wins":37},"GB2-08":{"draws":7,"losses":49,"wins":40}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1293.2880278495784,"GB2-02":1429.2739821056432,"GB2-04":1483.269501274785,"GB2-05":924.4368254590598,"GB2-06":1342.8613766220567,"GB2-07":1487.907737533893,"GB2-08":1411.9719926684977},"none":{"GB2-01":1518.7090711594628,"GB2-02":1455.210402384003,"GB2-03":1464.257046359489,"GB2-05":1467.3464738181478,"GB2-07":1367.2693290956158,"GB2-08":1508.5181338037046}},"per_game_tracks":{"medium":{"GB2-01":25.911126435305174,"GB2-02":11.783172968660383,"GB2-04":40.496965218840195,"GB2-05":0.0,"GB2-06":36.399691312701414,"GB2-07":45.82355270808264,"GB2-08":33.69443719624106},"none":{"GB2-01":49.061655826617994,"GB2-02":16.721194515766282,"GB2-03":41.31640418901639,"GB2-05":45.19689169842294,"GB2-07":33.90216158577543,"GB2-08":43.08815494051834}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.819428816982093,"none":35.5625160611959},"reasoning_agg":{"medium":{"max":45.82355270808264,"mean":26.819428816982093,"min":0.0},"none":{"max":49.061655826617994,"mean":35.5625160611959,"min":16.721194515766282}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.061655826617994,"reasoning_variance":8.743087244213807},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.82355270808264,"expected_score":23.896819454178853,"reliability_score":95.15134184284254,"uncertainty_avg":4.848658157157453,"uncertainty_penalty":-2.9226093628032395},"none":{"ceiling_score":49.061655826617994,"expected_score":42.43925936795156,"reliability_score":92.83633990773383,"uncertainty_avg":7.163660092266164,"uncertainty_penalty":6.876743306755657}}},{"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":31.996121085079185,"none":33.67094708059916},"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":962,"losses":1435,"wins":876},"match_totals_tracks":{"medium":{"draws":436,"losses":894,"wins":501},"none":{"draws":526,"losses":541,"wins":375}},"model_slug":"meituan-longcat-2-0","overall":{"max":56.21511165223179,"mean":31.170607687823995,"min":14.601235431191899},"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":40,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":82,"losses":95,"wins":65},"GB2-02":{"draws":195,"losses":8,"wins":3},"GB2-03":{"draws":136,"losses":93,"wins":79},"GB2-04":{"draws":209,"losses":114,"wins":41},"GB2-05":{"draws":0,"losses":320,"wins":200},"GB2-06":{"draws":43,"losses":335,"wins":184},"GB2-07":{"draws":0,"losses":294,"wins":236},"GB2-08":{"draws":297,"losses":176,"wins":68}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":101,"losses":3,"wins":2},"GB2-03":{"draws":62,"losses":39,"wins":41},"GB2-04":{"draws":153,"losses":90,"wins":19},"GB2-05":{"draws":0,"losses":190,"wins":152},"GB2-06":{"draws":23,"losses":227,"wins":96},"GB2-07":{"draws":0,"losses":191,"wins":131},"GB2-08":{"draws":97,"losses":154,"wins":60}},"none":{"GB2-01":{"draws":82,"losses":95,"wins":65},"GB2-02":{"draws":94,"losses":5,"wins":1},"GB2-03":{"draws":74,"losses":54,"wins":38},"GB2-04":{"draws":56,"losses":24,"wins":22},"GB2-05":{"draws":0,"losses":130,"wins":48},"GB2-06":{"draws":20,"losses":108,"wins":88},"GB2-07":{"draws":0,"losses":103,"wins":105},"GB2-08":{"draws":200,"losses":22,"wins":8}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1476.8316916886058,"GB2-03":1476.9131306078064,"GB2-04":1336.8963911626097,"GB2-05":1416.4395331894639,"GB2-06":1266.7108166706953,"GB2-07":1372.8877030640774,"GB2-08":1369.8300630344902},"none":{"GB2-01":1358.3905602002214,"GB2-02":1457.7390320719044,"GB2-03":1380.8913638836275,"GB2-04":1584.2614626043232,"GB2-05":1103.7825250791311,"GB2-06":1458.432472937302,"GB2-07":1427.1612694805494,"GB2-08":1386.927401056984}},"per_game_tracks":{"medium":{"GB2-02":23.401496235109175,"GB2-03":44.134251044046394,"GB2-04":19.174525876824212,"GB2-05":41.53426134564661,"GB2-06":30.33372549288365,"GB2-07":35.46251830880079,"GB2-08":29.932069292243508},"none":{"GB2-01":32.811959377744365,"GB2-02":18.862874029135362,"GB2-03":29.66163798427531,"GB2-04":56.21511165223179,"GB2-05":14.601235431191899,"GB2-06":46.215404534608886,"GB2-07":39.853186603425755,"GB2-08":31.146167032179893}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":29.775745754193835,"none":32.565469621454156},"reasoning_agg":{"medium":{"max":44.134251044046394,"mean":29.775745754193835,"min":19.174525876824212},"none":{"max":56.21511165223179,"mean":32.565469621454156,"min":14.601235431191899}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":56.21511165223179,"reasoning_variance":2.789723867260321},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":44.134251044046394,"expected_score":23.173187821840056,"reliability_score":99.2229861172063,"uncertainty_avg":0.7770138827937011,"uncertainty_penalty":-6.602557932353779},"none":{"ceiling_score":56.21511165223179,"expected_score":38.80441753207652,"reliability_score":94.38599196336007,"uncertainty_avg":5.614008036639936,"uncertainty_penalty":6.238947910622365}}},{"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":0.48605810000000005},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.31476170000000003},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924717999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.3147617},"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":0.19924717999999997},"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":0.4860581}},"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":40.56250296731213,"highest":31.867344410388103,"medium":36.456734403728596,"none":35.208732986034015},"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":346,"losses":759,"wins":448},"match_totals_tracks":{"highest":{"draws":78,"losses":265,"wins":146},"medium":{"draws":153,"losses":164,"wins":97},"none":{"draws":115,"losses":330,"wins":205}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":50.91082045936282,"mean":29.532585278113142,"min":12.522239497043625},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":41,"overall_ranking_status":"partial","per_game":{"GB2-01":12.522239497043625,"GB2-05":41.604671181441674,"GB2-06":42.18034696924738,"GB2-07":32.46189477313855,"GB2-08":30.56756963106926},"per_game_all":{"GB2-05":40.17085113496656,"GB2-06":40.95415479965769},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":62,"wins":14},"GB2-02":{"draws":76,"losses":9,"wins":1},"GB2-04":{"draws":76,"losses":11,"wins":11},"GB2-05":{"draws":0,"losses":217,"wins":159},"GB2-06":{"draws":14,"losses":210,"wins":158},"GB2-07":{"draws":0,"losses":175,"wins":104},"GB2-08":{"draws":174,"losses":75,"wins":1}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":62,"wins":14},"GB2-05":{"draws":0,"losses":52,"wins":56},"GB2-06":{"draws":2,"losses":64,"wins":40},"GB2-07":{"draws":0,"losses":66,"wins":35},"GB2-08":{"draws":70,"losses":21,"wins":1}},"medium":{"GB2-02":{"draws":76,"losses":9,"wins":1},"GB2-04":{"draws":76,"losses":11,"wins":11},"GB2-05":{"draws":0,"losses":66,"wins":52},"GB2-06":{"draws":1,"losses":78,"wins":33}},"none":{"GB2-05":{"draws":0,"losses":99,"wins":51},"GB2-06":{"draws":11,"losses":68,"wins":85},"GB2-07":{"draws":0,"losses":109,"wins":69},"GB2-08":{"draws":104,"losses":54,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1405.3648819438924,"GB2-06":1394.9741765473884},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1165.3075653397077,"GB2-05":1425.1003871142666,"GB2-06":1412.0094597124114,"GB2-07":1349.1712838775788,"GB2-08":1385.5425180436987},"medium":{"GB2-02":1478.1857236712685,"GB2-04":1518.32655258939,"GB2-05":1491.530653934251,"GB2-06":1267.48183370103},"none":{"GB2-05":1299.4636047831602,"GB2-06":1505.431236228724,"GB2-07":1378.7192000023038,"GB2-08":1292.208218512245}},"per_game_tracks":{"highest":{"GB2-01":12.522239497043625,"GB2-05":41.604671181441674,"GB2-06":42.18034696924738,"GB2-07":32.46189477313855,"GB2-08":30.56756963106926},"medium":{"GB2-02":22.759457008176497,"GB2-04":46.03853672066733,"GB2-05":47.2576469157077,"GB2-06":29.77129697036285},"none":{"GB2-05":31.650235307750318,"GB2-06":50.91082045936282,"GB2-07":36.156327157500364,"GB2-08":22.117549019522556}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.33452120880606,"medium":30.656337271952143,"none":29.606897353581214},"reasoning_agg":{"highest":{"max":42.18034696924738,"mean":28.33452120880606,"min":12.522239497043625},"medium":{"max":47.2576469157077,"mean":30.656337271952143,"min":22.759457008176497},"none":{"max":50.91082045936282,"mean":29.606897353581214,"min":22.117549019522556}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":50.91082045936282,"expected_score":33.9072191025562,"reasoning_variance":2.321816063146084,"reliability_score":97.65014883601147,"uncertainty_avg":2.3498511639885296,"uncertainty_penalty":4.374633824443055},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.18034696924738,"expected_score":17.018714326284375,"reliability_score":93.25695388129182,"uncertainty_avg":6.743046118708181,"uncertainty_penalty":-11.315806882521684},"medium":{"ceiling_score":47.2576469157077,"expected_score":36.567037295655396,"reliability_score":94.5678785561398,"uncertainty_avg":5.432121443860191,"uncertainty_penalty":5.910700023703253},"none":{"ceiling_score":50.91082045936282,"expected_score":31.333083738930704,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7261863853494894}}},{"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":1.2552692800000003},"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":0.5884539500000001}},"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":32.21684629862723,"highest":31.03355701713752,"medium":30.876311405534093,"none":35.47310379880186},"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":1046,"losses":1571,"wins":784},"match_totals_tracks":{"highest":{"draws":409,"losses":674,"wins":267},"medium":{"draws":250,"losses":401,"wins":178},"none":{"draws":387,"losses":496,"wins":339}},"model_slug":"thinkingmachines-inkling","overall":{"max":67.94308497290339,"mean":28.016436981467752,"min":8.04764389452622},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":17.155695255029734,"GB2-02":19.990967262210003,"GB2-03":40.92223596271898,"GB2-04":40.504702920191605,"GB2-05":18.48372816664021,"GB2-06":58.54870417164183,"GB2-07":25.73846555139435,"GB2-08":26.923956847273455},"per_game_all":{"GB2-01":20.963308952047075,"GB2-03":47.846228494379865,"GB2-04":37.683629039475576,"GB2-05":25.395810387260372,"GB2-07":21.18751341748148,"GB2-08":40.224587501119025},"per_game_match_totals_all":{"GB2-01":{"draws":172,"losses":283,"wins":55},"GB2-02":{"draws":201,"losses":19,"wins":4},"GB2-03":{"draws":156,"losses":115,"wins":155},"GB2-04":{"draws":302,"losses":73,"wins":57},"GB2-05":{"draws":0,"losses":472,"wins":186},"GB2-06":{"draws":9,"losses":127,"wins":132},"GB2-07":{"draws":0,"losses":324,"wins":110},"GB2-08":{"draws":206,"losses":158,"wins":85}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":53,"losses":83,"wins":6},"GB2-02":{"draws":111,"losses":9,"wins":2},"GB2-03":{"draws":50,"losses":41,"wins":33},"GB2-04":{"draws":84,"losses":22,"wins":28},"GB2-05":{"draws":0,"losses":250,"wins":70},"GB2-06":{"draws":8,"losses":69,"wins":79},"GB2-07":{"draws":0,"losses":129,"wins":45},"GB2-08":{"draws":103,"losses":71,"wins":4}},"medium":{"GB2-01":{"draws":35,"losses":76,"wins":27},"GB2-03":{"draws":25,"losses":37,"wins":72},"GB2-04":{"draws":94,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":80,"wins":44},"GB2-07":{"draws":0,"losses":139,"wins":17},"GB2-08":{"draws":96,"losses":50,"wins":11}},"none":{"GB2-01":{"draws":84,"losses":124,"wins":22},"GB2-02":{"draws":90,"losses":10,"wins":2},"GB2-03":{"draws":81,"losses":37,"wins":50},"GB2-04":{"draws":124,"losses":32,"wins":22},"GB2-05":{"draws":0,"losses":142,"wins":72},"GB2-06":{"draws":1,"losses":58,"wins":53},"GB2-07":{"draws":0,"losses":56,"wins":48},"GB2-08":{"draws":7,"losses":37,"wins":70}}},"per_game_raw_elo_all":{"GB2-01":1239.7590267282778,"GB2-03":1508.5865707069988,"GB2-04":1461.0027926346954,"GB2-05":1226.866831588522,"GB2-07":1223.49792336108,"GB2-08":1472.5876617888453},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1200.6961116510595,"GB2-02":1459.031259226249,"GB2-03":1455.6626650012568,"GB2-04":1476.2686847664681,"GB2-05":1139.8966108091176,"GB2-06":1594.5323147640372,"GB2-07":1268.3605173911951,"GB2-08":1337.923250186877},"medium":{"GB2-01":1359.3433979275337,"GB2-03":1556.1129209687915,"GB2-04":1454.3921381611772,"GB2-05":1241.8551704733636,"GB2-07":1082.0671538643896,"GB2-08":1328.7976684792145},"none":{"GB2-01":1159.2375706062403,"GB2-02":1484.3681592549508,"GB2-03":1513.9841261509482,"GB2-04":1452.3475549764407,"GB2-05":1298.8487134830848,"GB2-06":1315.7125886364151,"GB2-07":1320.0660988276552,"GB2-08":1751.0420667004444}},"per_game_tracks":{"highest":{"GB2-01":17.155695255029734,"GB2-02":19.990967262210003,"GB2-03":40.92223596271898,"GB2-04":40.504702920191605,"GB2-05":18.48372816664021,"GB2-06":58.54870417164183,"GB2-07":25.73846555139435,"GB2-08":26.923956847273455},"medium":{"GB2-01":33.14168798272348,"GB2-03":54.7905686677935,"GB2-04":36.872662603409985,"GB2-05":26.598584601571144,"GB2-07":8.04764389452622,"GB2-08":25.806720683180234},"none":{"GB2-01":12.59254361838801,"GB2-02":24.925858625367727,"GB2-03":47.82588085262712,"GB2-04":35.67352159482515,"GB2-05":31.105118393569768,"GB2-06":33.94239152620984,"GB2-07":29.776430806523866,"GB2-08":67.94308497290339}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.875848746633917,"medium":24.162019435171192,"none":33.01144276259816},"reasoning_agg":{"highest":{"max":58.54870417164183,"mean":26.875848746633917,"min":17.155695255029734},"medium":{"max":54.7905686677935,"mean":24.162019435171192,"min":8.04764389452622},"none":{"max":67.94308497290339,"mean":33.01144276259816,"min":12.59254361838801}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":67.94308497290339,"expected_score":26.769232253192268,"reasoning_variance":8.849423327426965,"reliability_score":97.88203226496074,"uncertainty_avg":2.1179677350392523,"uncertainty_penalty":-1.2472047282754843},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.54870417164183,"expected_score":12.275254061091003,"reliability_score":99.71189483957907,"uncertainty_avg":0.28810516042092615,"uncertainty_penalty":-14.600594685542914},"medium":{"ceiling_score":54.7905686677935,"expected_score":25.346439588887407,"reliability_score":99.55401583257645,"uncertainty_avg":0.44598416742354247,"uncertainty_penalty":1.1844201537162142},"none":{"ceiling_score":67.94308497290339,"expected_score":41.603460152182635,"reliability_score":94.5901672495545,"uncertainty_avg":5.409832750445501,"uncertainty_penalty":8.592017389584477}}},{"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":0.07056469400000001},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.019725259999999998},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468000000001},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.008820586750000001,"median":0.007023681,"min":0.00271606,"recorded_attempt_count":19,"run_count":8,"total":0.070564694}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.01660212,"mean":0.00430918425,"median":0.0025298300000000003,"min":0.00045831,"recorded_attempt_count":48,"run_count":24,"total":0.10342042200000001},"codegen_latency_ms":{"attempt_count":48,"max_ms":622759,"mean_ms":232922.5,"min_ms":19833,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":622759,"mean_ms":483202.0,"min_ms":329312,"run_count":8},"medium":{"attempt_count":16,"max_ms":213246,"mean_ms":118332.0,"min_ms":41554,"run_count":8},"none":{"attempt_count":13,"max_ms":226636,"mean_ms":97233.5,"min_ms":19833,"run_count":8}},"codegen_output_tokens":{"attempt_count":48,"output_max":43929,"output_mean":12519.625,"output_min":1331,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":43929,"output_mean":28964.5,"output_min":18493,"run_count":8},"medium":{"attempt_count":16,"output_max":8961,"output_mean":5674.0,"output_min":2048,"run_count":8},"none":{"attempt_count":13,"output_max":5763,"output_mean":2920.375,"output_min":1331,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":32.11422092546289,"highest":38.58212869949016,"medium":34.95147835537315,"none":14.781157625670273},"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":733,"losses":1135,"wins":407},"match_totals_tracks":{"highest":{"draws":175,"losses":157,"wins":100},"medium":{"draws":314,"losses":240,"wins":143},"none":{"draws":244,"losses":738,"wins":164}},"model_slug":"openai-gpt-oss-120b","overall":{"max":67.82204727657161,"mean":27.468242352636967,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-02":13.91305101107773,"GB2-04":39.431761090888465,"GB2-06":67.82204727657161,"GB2-07":39.64119866533117,"GB2-08":32.10258545358184},"per_game_all":{"GB2-04":25.132721852518596,"GB2-06":42.304232544722105,"GB2-08":28.905708379147956},"per_game_match_totals_all":{"GB2-01":{"draws":59,"losses":156,"wins":55},"GB2-02":{"draws":136,"losses":20,"wins":4},"GB2-03":{"draws":106,"losses":91,"wins":21},"GB2-04":{"draws":178,"losses":105,"wins":25},"GB2-05":{"draws":0,"losses":220,"wins":85},"GB2-06":{"draws":7,"losses":231,"wins":142},"GB2-07":{"draws":0,"losses":207,"wins":57},"GB2-08":{"draws":247,"losses":105,"wins":18}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":59,"losses":15,"wins":0},"GB2-04":{"draws":43,"losses":23,"wins":14},"GB2-06":{"draws":6,"losses":32,"wins":50},"GB2-07":{"draws":0,"losses":65,"wins":31},"GB2-08":{"draws":67,"losses":22,"wins":5}},"medium":{"GB2-01":{"draws":24,"losses":43,"wins":27},"GB2-02":{"draws":77,"losses":5,"wins":4},"GB2-03":{"draws":43,"losses":13,"wins":10},"GB2-04":{"draws":83,"losses":11,"wins":2},"GB2-05":{"draws":0,"losses":67,"wins":49},"GB2-06":{"draws":1,"losses":78,"wins":42},"GB2-08":{"draws":86,"losses":23,"wins":9}},"none":{"GB2-01":{"draws":35,"losses":113,"wins":28},"GB2-03":{"draws":63,"losses":78,"wins":11},"GB2-04":{"draws":52,"losses":71,"wins":9},"GB2-05":{"draws":0,"losses":153,"wins":36},"GB2-06":{"draws":0,"losses":121,"wins":50},"GB2-07":{"draws":0,"losses":142,"wins":26},"GB2-08":{"draws":94,"losses":60,"wins":4}}},"per_game_raw_elo_all":{"GB2-04":1380.9691896044399,"GB2-06":1411.1438098291135,"GB2-08":1364.103528622483},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1442.0685143240635,"GB2-04":1479.2518107556666,"GB2-06":1712.237284828002,"GB2-07":1426.4652985743849,"GB2-08":1400.2862698488254},"medium":{"GB2-01":1422.8019145344933,"GB2-02":1473.9362990217546,"GB2-03":1409.558557661116,"GB2-04":1452.7004190221962,"GB2-05":1456.517503684909,"GB2-06":1340.0030877685297,"GB2-08":1421.642551452285},"none":{"GB2-01":1217.332032382236,"GB2-03":1273.1146500874393,"GB2-04":1210.9553390354572,"GB2-05":1087.1904502695809,"GB2-06":1181.1910568908093,"GB2-07":1108.1862556209687,"GB2-08":1270.3817645663387}},"per_game_tracks":{"highest":{"GB2-02":13.91305101107773,"GB2-04":39.431761090888465,"GB2-06":67.82204727657161,"GB2-07":39.64119866533117,"GB2-08":32.10258545358184},"medium":{"GB2-01":38.83660567477785,"GB2-02":21.805843612607568,"GB2-03":32.858125032877226,"GB2-04":35.96640446666731,"GB2-05":44.324242271963605,"GB2-06":36.16541568514887,"GB2-08":34.70371174356963},"none":{"GB2-01":19.17906841539228,"GB2-03":16.522204329731178,"GB2-04":0.0,"GB2-05":14.31642168470547,"GB2-06":22.92523467244584,"GB2-07":10.614346337124728,"GB2-08":19.910827940292407}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.30490253088758,"medium":33.803958762497714,"none":14.2958657645256},"reasoning_agg":{"highest":{"max":67.82204727657161,"mean":34.30490253088758,"min":13.91305101107773},"medium":{"max":44.324242271963605,"mean":33.803958762497714,"min":21.805843612607568},"none":{"max":22.92523467244584,"mean":14.2958657645256,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":67.82204727657161,"expected_score":22.196755319053267,"reasoning_variance":20.00903676636198,"reliability_score":95.64172519005754,"uncertainty_avg":4.358274809942451,"uncertainty_penalty":-5.2714870335837},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.82204727657161,"expected_score":24.74684582907314,"reliability_score":90.07865953284504,"uncertainty_avg":9.921340467154959,"uncertainty_penalty":-9.55805670181444},"medium":{"ceiling_score":44.324242271963605,"expected_score":28.084708617165635,"reliability_score":93.16651585632096,"uncertainty_avg":6.833484143679037,"uncertainty_penalty":-5.719250145332079},"none":{"ceiling_score":22.92523467244584,"expected_score":10.741073613266911,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.554792151258688}}},{"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":2.586028}},"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":2.586028}},"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":28.182587082918836,"none":36.33161686261811},"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":353,"losses":504,"wins":287},"match_totals_tracks":{"medium":{"draws":58,"losses":307,"wins":127},"none":{"draws":295,"losses":197,"wins":160}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":60.50605278337446,"mean":27.303167692125538,"min":11.297346143143717},"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":44,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-02":{"draws":71,"losses":11,"wins":2},"GB2-03":{"draws":78,"losses":42,"wins":24},"GB2-04":{"draws":83,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":127,"wins":85},"GB2-06":{"draws":12,"losses":143,"wins":43},"GB2-07":{"draws":0,"losses":88,"wins":120},"GB2-08":{"draws":109,"losses":85,"wins":8}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":35,"losses":27,"wins":14},"GB2-05":{"draws":0,"losses":74,"wins":32},"GB2-06":{"draws":10,"losses":76,"wins":20},"GB2-07":{"draws":0,"losses":59,"wins":53},"GB2-08":{"draws":13,"losses":71,"wins":8}},"none":{"GB2-02":{"draws":71,"losses":11,"wins":2},"GB2-03":{"draws":43,"losses":15,"wins":10},"GB2-04":{"draws":83,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":53,"wins":53},"GB2-06":{"draws":2,"losses":67,"wins":23},"GB2-07":{"draws":0,"losses":29,"wins":67},"GB2-08":{"draws":96,"losses":14,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1414.8192171011551,"GB2-05":1281.5487586993647,"GB2-06":1195.0146527344775,"GB2-07":1454.1203052409805,"GB2-08":1194.9426957801345},"none":{"GB2-02":1451.0500885064464,"GB2-03":1447.1051582810692,"GB2-04":1464.340110846728,"GB2-05":1463.6103813613147,"GB2-06":1204.3990254582595,"GB2-07":1648.1717121399788,"GB2-08":1403.0243582764076}},"per_game_tracks":{"medium":{"GB2-03":34.022102828158765,"GB2-05":29.654555612064655,"GB2-06":23.41419124049507,"GB2-07":42.524739590732,"GB2-08":11.297346143143717},"none":{"GB2-02":16.55738720588751,"GB2-03":38.07029226565205,"GB2-04":37.74168060162787,"GB2-05":44.77294290610812,"GB2-06":23.982876833913124,"GB2-07":60.50605278337446,"GB2-08":32.69008544176368}},"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":25.058257165591744,"none":29.54807821865933},"reasoning_agg":{"medium":{"max":42.524739590732,"mean":25.058257165591744,"min":11.297346143143717},"none":{"max":60.50605278337446,"mean":29.54807821865933,"min":16.55738720588751}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.50605278337446,"reasoning_variance":4.489821053067587},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":42.524739590732,"expected_score":18.63838749355879,"reliability_score":93.24248694198272,"uncertainty_avg":6.757513058017288,"uncertainty_penalty":-6.419869672032956},"none":{"ceiling_score":60.50605278337446,"expected_score":42.33556847228325,"reliability_score":91.80679050180858,"uncertainty_avg":8.193209498191418,"uncertainty_penalty":12.787490253623918}}},{"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":34.324135825057176,"none":26.841171478481243},"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":384,"losses":521,"wins":273},"match_totals_tracks":{"medium":{"draws":190,"losses":266,"wins":186},"none":{"draws":194,"losses":255,"wins":87}},"model_slug":"cohere-north-mini-code","overall":{"max":47.666905146048265,"mean":26.00533205586351,"min":20.068456528448355},"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":98,"losses":105,"wins":23},"GB2-03":{"draws":28,"losses":24,"wins":10},"GB2-04":{"draws":81,"losses":18,"wins":7},"GB2-05":{"draws":0,"losses":56,"wins":72},"GB2-06":{"draws":1,"losses":79,"wins":34},"GB2-07":{"draws":0,"losses":197,"wins":123},"GB2-08":{"draws":176,"losses":42,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":28,"losses":24,"wins":10},"GB2-04":{"draws":81,"losses":18,"wins":7},"GB2-05":{"draws":0,"losses":56,"wins":72},"GB2-06":{"draws":1,"losses":79,"wins":34},"GB2-07":{"draws":0,"losses":67,"wins":63},"GB2-08":{"draws":80,"losses":22,"wins":0}},"none":{"GB2-01":{"draws":98,"losses":105,"wins":23},"GB2-07":{"draws":0,"losses":130,"wins":60},"GB2-08":{"draws":96,"losses":20,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1416.0627821631542,"GB2-04":1451.3736279368563,"GB2-05":1510.9170144593968,"GB2-06":1268.3538600217935,"GB2-07":1422.0867753907792,"GB2-08":1368.1606981960256},"none":{"GB2-01":1263.538009086365,"GB2-07":1267.58485647528,"GB2-08":1402.3296396091612}},"per_game_tracks":{"medium":{"GB2-03":30.765006071781528,"GB2-04":33.52310753913016,"GB2-05":47.666905146048265,"GB2-06":28.469827580005035,"GB2-07":38.36837714419139,"GB2-08":27.151591469186677},"none":{"GB2-01":23.07648794314826,"GB2-07":24.665143039430337,"GB2-08":32.78188345286514}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.942207583278662,"none":20.068456528448355},"reasoning_agg":{"medium":{"max":47.666905146048265,"mean":31.942207583278662,"min":27.151591469186677},"none":{"max":32.78188345286514,"mean":20.068456528448355,"min":23.07648794314826}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":47.666905146048265,"reasoning_variance":11.873751054830308},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.666905146048265,"expected_score":30.0688539719236,"reliability_score":73.25782784604162,"uncertainty_avg":26.742172153958375,"uncertainty_penalty":-1.8733536113550642},"none":{"ceiling_score":32.78188345286514,"expected_score":23.65548308056688,"reliability_score":95.85839527751199,"uncertainty_avg":4.141604722488015,"uncertainty_penalty":3.5870265521185267}}},{"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":0.08108399999999999},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.34809300000000004},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":23.820802992712277,"highest":33.03984697397667,"medium":30.637348965354164,"none":17.4455680741114},"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":382,"losses":794,"wins":329},"match_totals_tracks":{"highest":{"draws":136,"losses":254,"wins":95},"medium":{"draws":161,"losses":328,"wins":161},"none":{"draws":85,"losses":212,"wins":73}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":44.84292897073299,"mean":24.46661762026912,"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":40.94245051776638,"GB2-05":19.73749709047673,"GB2-06":29.280934011909366,"GB2-07":44.84292897073299,"GB2-08":30.395424278997872},"per_game_all":{"GB2-05":19.764438241825975,"GB2-06":36.5668289911193,"GB2-07":15.131141745191561},"per_game_match_totals_all":{"GB2-01":{"draws":69,"losses":83,"wins":28},"GB2-02":{"draws":59,"losses":2,"wins":1},"GB2-04":{"draws":141,"losses":25,"wins":14},"GB2-05":{"draws":0,"losses":199,"wins":65},"GB2-06":{"draws":1,"losses":184,"wins":122},"GB2-07":{"draws":0,"losses":222,"wins":52},"GB2-08":{"draws":112,"losses":79,"wins":47}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":64,"losses":20,"wins":6},"GB2-05":{"draws":0,"losses":70,"wins":18},"GB2-06":{"draws":0,"losses":66,"wins":29},"GB2-07":{"draws":0,"losses":70,"wins":36},"GB2-08":{"draws":72,"losses":28,"wins":6}},"medium":{"GB2-01":{"draws":44,"losses":38,"wins":22},"GB2-04":{"draws":77,"losses":5,"wins":8},"GB2-05":{"draws":0,"losses":70,"wins":28},"GB2-06":{"draws":0,"losses":82,"wins":50},"GB2-07":{"draws":0,"losses":82,"wins":12},"GB2-08":{"draws":40,"losses":51,"wins":41}},"none":{"GB2-01":{"draws":25,"losses":45,"wins":6},"GB2-02":{"draws":59,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":59,"wins":19},"GB2-06":{"draws":1,"losses":36,"wins":43},"GB2-07":{"draws":0,"losses":70,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1166.3135601036993,"GB2-06":1348.414926228723,"GB2-07":1167.3772678842406},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1486.643674866353,"GB2-05":1165.8540579796686,"GB2-06":1265.0077154404437,"GB2-07":1479.7936186306395,"GB2-08":1381.0312376325182},"medium":{"GB2-01":1442.0722052107417,"GB2-04":1494.6174746882057,"GB2-05":1196.77816581129,"GB2-06":1399.0006395624505,"GB2-07":1011.5193889215823,"GB2-08":1434.8578660442124},"none":{"GB2-01":1144.1569784358514,"GB2-02":1477.5240632772964,"GB2-05":1136.308456520139,"GB2-06":1381.2364236832755,"GB2-07":1010.8187961005}},"per_game_tracks":{"highest":{"GB2-04":40.94245051776638,"GB2-05":19.73749709047673,"GB2-06":29.280934011909366,"GB2-07":44.84292897073299,"GB2-08":30.395424278997872},"medium":{"GB2-01":40.98668493442913,"GB2-04":42.15860784753806,"GB2-05":22.487988563537684,"GB2-06":41.39995376105174,"GB2-07":0.5504962648416883,"GB2-08":36.2403624207267},"none":{"GB2-01":10.214928346057336,"GB2-02":20.925483752639348,"GB2-05":17.067829071463514,"GB2-06":39.0195992003968,"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":29.37703979232976,"medium":28.511265817165267,"none":15.511547251312342},"reasoning_agg":{"highest":{"max":44.84292897073299,"mean":29.37703979232976,"min":19.73749709047673},"medium":{"max":42.15860784753806,"mean":28.511265817165267,"min":0.5504962648416883},"none":{"max":39.0195992003968,"mean":15.511547251312342,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":44.84292897073299,"expected_score":15.635869382487918,"reasoning_variance":13.865492541017419,"reliability_score":91.83738437237537,"uncertainty_avg":8.162615627624634,"uncertainty_penalty":-8.8307482377812},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":44.84292897073299,"expected_score":13.480531437364641,"reliability_score":93.12623579020737,"uncertainty_avg":6.873764209792633,"uncertainty_penalty":-15.89650835496512},"medium":{"ceiling_score":42.15860784753806,"expected_score":29.360690772014504,"reliability_score":95.37332435820986,"uncertainty_avg":4.62667564179015,"uncertainty_penalty":0.849424954849237},"none":{"ceiling_score":39.0195992003968,"expected_score":13.00246743830186,"reliability_score":85.8461310828981,"uncertainty_avg":14.1538689171019,"uncertainty_penalty":-2.509079813010482}}},{"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":0.34395749999999997}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.042994687499999996,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.34395749999999997},"historical-provider-setting-intensive":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.3927285,"mean":0.1902770625,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":14,"run_count":9,"total":1.914945}},"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":21.11214296718544,"none":34.34821004798081},"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":"2026-08-05T05:02:41Z","match_totals_all":{"draws":128,"losses":435,"wins":208},"match_totals_tracks":{"highest":{"draws":19,"losses":265,"wins":82},"none":{"draws":109,"losses":170,"wins":126}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":39.8933469399602,"mean":23.060639624246463,"min":11.379446013072632},"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":11.379446013072632,"GB2-05":25.241466318726623,"GB2-06":28.20923732650551,"GB2-07":19.618422210437004},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":112,"wins":51},"GB2-05":{"draws":0,"losses":117,"wins":71},"GB2-06":{"draws":8,"losses":109,"wins":63},"GB2-07":{"draws":0,"losses":75,"wins":21},"GB2-08":{"draws":92,"losses":22,"wins":2}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":63,"wins":8},"GB2-05":{"draws":0,"losses":65,"wins":25},"GB2-06":{"draws":0,"losses":62,"wins":28},"GB2-07":{"draws":0,"losses":75,"wins":21}},"none":{"GB2-01":{"draws":9,"losses":49,"wins":43},"GB2-05":{"draws":0,"losses":52,"wins":46},"GB2-06":{"draws":8,"losses":47,"wins":35},"GB2-08":{"draws":92,"losses":22,"wins":2}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1152.0261703164747,"GB2-05":1231.6665190864155,"GB2-06":1253.7221512485582,"GB2-07":1213.7066599409454},"none":{"GB2-01":1431.8243444955588,"GB2-05":1351.468176625996,"GB2-06":1323.4952044044514,"GB2-08":1354.8843322134849}},"per_game_tracks":{"highest":{"GB2-01":11.379446013072632,"GB2-05":25.241466318726623,"GB2-06":28.20923732650551,"GB2-07":19.618422210437004},"none":{"GB2-01":39.8933469399602,"GB2-05":35.33343869093166,"GB2-06":34.24335399238109,"GB2-08":27.922700568650274}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.23799254876425,"none":28.88328669972868},"reasoning_agg":{"highest":{"max":28.20923732650551,"mean":17.23799254876425,"min":11.379446013072632},"none":{"max":39.8933469399602,"mean":28.88328669972868,"min":27.922700568650274}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":39.8933469399602,"reasoning_variance":11.645294150964428},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":28.20923732650551,"expected_score":3.170094537573378,"reliability_score":91.74749155875783,"uncertainty_avg":8.252508441242176,"uncertainty_penalty":-14.067898011190872},"none":{"ceiling_score":39.8933469399602,"expected_score":29.147213731535018,"reliability_score":94.15036847500184,"uncertainty_avg":5.849631524998166,"uncertainty_penalty":0.2639270318063396}}},{"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":26.540316595936496,"none":27.734523333650188},"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":939,"losses":949,"wins":436},"match_totals_tracks":{"medium":{"draws":263,"losses":509,"wins":232},"none":{"draws":676,"losses":440,"wins":204}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":41.40501950685979,"mean":22.88330140834788,"min":12.133934164094017},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":135,"losses":227,"wins":100},"GB2-02":{"draws":208,"losses":29,"wins":3},"GB2-03":{"draws":87,"losses":77,"wins":36},"GB2-04":{"draws":231,"losses":34,"wins":21},"GB2-06":{"draws":6,"losses":329,"wins":107},"GB2-07":{"draws":0,"losses":216,"wins":164},"GB2-08":{"draws":272,"losses":37,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":34,"losses":107,"wins":7},"GB2-02":{"draws":98,"losses":22,"wins":2},"GB2-04":{"draws":129,"losses":27,"wins":14},"GB2-06":{"draws":2,"losses":137,"wins":45},"GB2-07":{"draws":0,"losses":216,"wins":164}},"none":{"GB2-01":{"draws":101,"losses":120,"wins":93},"GB2-02":{"draws":110,"losses":7,"wins":1},"GB2-03":{"draws":87,"losses":77,"wins":36},"GB2-04":{"draws":102,"losses":7,"wins":7},"GB2-06":{"draws":4,"losses":192,"wins":62},"GB2-08":{"draws":272,"losses":37,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1249.214707380887,"GB2-02":1449.556144588857,"GB2-04":1434.6985624189183,"GB2-06":1240.7179893577259,"GB2-07":1449.0297347788198},"none":{"GB2-01":1385.0409369204554,"GB2-02":1445.7308308182332,"GB2-03":1361.644886820065,"GB2-04":1476.192389292363,"GB2-06":1103.1532899366941,"GB2-08":1371.6131397638803}},"per_game_tracks":{"medium":{"GB2-01":19.956639805537932,"GB2-02":12.133934164094017,"GB2-04":32.370699474354865,"GB2-06":26.835290028835875,"GB2-07":41.40501950685979},"none":{"GB2-01":35.951635842394275,"GB2-02":16.871313010451086,"GB2-03":27.56514642169852,"GB2-04":40.10360954415184,"GB2-06":15.779988068257042,"GB2-08":30.13544711494835}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":21.106736920958664,"none":24.659865895737095},"reasoning_agg":{"medium":{"max":41.40501950685979,"mean":21.106736920958664,"min":12.133934164094017},"none":{"max":40.10360954415184,"mean":24.659865895737095,"min":15.779988068257042}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":41.40501950685979,"reasoning_variance":3.5531289747784314},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":41.40501950685979,"expected_score":21.58322566928635,"reliability_score":80.75242439915301,"uncertainty_avg":19.24757560084699,"uncertainty_penalty":0.47648874832768584},"none":{"ceiling_score":40.10360954415184,"expected_score":29.27825937218962,"reliability_score":98.21576813379313,"uncertainty_avg":1.78423186620687,"uncertainty_penalty":4.618393476452525}}}],"public_release_id":"gb2-20260823-7d5648862dc8","results_cut_id":"gb2-20260823-7d5648862dc8","schema_version":2,"snapshot_id":"20260823_205116","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-08-23 20:51 UTC","versus_totals_all":{"claude-fable-5":{"claude-fable-5":{"draws":4,"losses":12,"wins":12},"claude-opus-4-5":{"draws":7,"losses":8,"wins":45},"claude-opus-4-8":{"draws":6,"losses":26,"wins":28},"claude-opus-5":{"draws":25,"losses":58,"wins":57},"claude-sonnet-5":{"draws":11,"losses":1,"wins":34},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":22},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":28},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":8},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":34},"gpt-5.4":{"draws":8,"losses":28,"wins":30},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":13},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":37},"gpt-5.5":{"draws":8,"losses":22,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":33},"gpt-5.6-sol":{"draws":13,"losses":20,"wins":41},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":48},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":27},"o3":{"draws":1,"losses":2,"wins":31},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":19},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":19},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":20},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":30},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":21}},"claude-opus-4-5":{"claude-fable-5":{"draws":5,"losses":29,"wins":6},"claude-opus-4-5":{"draws":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":70,"losses":50,"wins":66},"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":39,"losses":73,"wins":34},"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":51,"losses":39,"wins":60},"gpt-5.6-sol":{"draws":31,"losses":97,"wins":30},"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},"claude-sonnet-5":{"draws":17,"losses":18,"wins":37},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":18,"wins":11},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":19,"losses":27,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":11},"gpt-5":{"draws":11,"losses":13,"wins":26},"gpt-5.4":{"draws":15,"losses":32,"wins":23},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":36},"gpt-5.5":{"draws":19,"losses":35,"wins":22},"gpt-5.6-luna":{"draws":17,"losses":19,"wins":26},"gpt-5.6-sol":{"draws":15,"losses":40,"wins":23},"gpt-5.6-terra":{"draws":22,"losses":17,"wins":27},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":17},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":31},"o3":{"draws":4,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":23},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":17},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":15,"losses":20,"wins":19},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":12,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":25}},"claude-opus-5":{"claude-fable-5":{"draws":25,"losses":57,"wins":58},"claude-opus-4-5":{"draws":35,"losses":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":39,"losses":20,"wins":121},"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":23,"losses":48,"wins":89},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":32},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":54},"gpt-5.5":{"draws":21,"losses":33,"wins":94},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":74},"gpt-5.6-sol":{"draws":29,"losses":35,"wins":128},"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-fable-5":{"draws":11,"losses":34,"wins":1},"claude-opus-4-5":{"draws":90,"losses":83,"wins":69},"claude-opus-4-8":{"draws":17,"losses":37,"wins":18},"claude-opus-5":{"draws":39,"losses":121,"wins":20},"claude-sonnet-5":{"draws":70,"losses":65,"wins":65},"cohere/north-mini-code":{"draws":12,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":28,"losses":9,"wins":37},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":15,"wins":16},"google/gemini-3.5-flash-lite":{"draws":118,"losses":77,"wins":153},"google/gemini-3.6-flash":{"draws":92,"losses":139,"wins":101},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":9},"gpt-4.1":{"draws":9,"losses":12,"wins":15},"gpt-4.1-nano":{"draws":4,"losses":3,"wins":5},"gpt-5":{"draws":24,"losses":20,"wins":18},"gpt-5.4":{"draws":76,"losses":118,"wins":40},"gpt-5.4-mini":{"draws":22,"losses":15,"wins":13},"gpt-5.4-nano":{"draws":20,"losses":17,"wins":19},"gpt-5.5":{"draws":29,"losses":23,"wins":18},"gpt-5.6-luna":{"draws":88,"losses":68,"wins":81},"gpt-5.6-sol":{"draws":46,"losses":180,"wins":46},"gpt-5.6-terra":{"draws":28,"losses":26,"wins":30},"inclusionai/ling-3.0-flash":{"draws":35,"losses":7,"wins":44},"meituan/longcat-2.0":{"draws":44,"losses":19,"wins":79},"meta/muse-spark-1.2":{"draws":35,"losses":41,"wins":38},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":8},"moonshotai/kimi-k3":{"draws":68,"losses":65,"wins":41},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":15,"wins":25},"o3":{"draws":29,"losses":96,"wins":95},"openai/gpt-oss-120b":{"draws":32,"losses":8,"wins":52},"poolside/laguna-s-2.1":{"draws":62,"losses":16,"wins":68},"qwen/qwen3.7-max":{"draws":23,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":16,"losses":14,"wins":34},"tencent/hy3-preview":{"draws":16,"losses":10,"wins":12},"thinkingmachines/inkling":{"draws":60,"losses":22,"wins":78},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":67,"losses":66,"wins":33},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":61,"losses":14,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":34,"losses":26,"wins":40}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":9,"losses":22,"wins":3},"claude-opus-4-8":{"draws":7,"losses":15,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"claude-sonnet-5":{"draws":12,"losses":15,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":13,"wins":13},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":1},"google/gemini-3.5-flash-lite":{"draws":19,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":17,"wins":4},"gpt-5.4":{"draws":8,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":27,"wins":11},"gpt-5.5":{"draws":14,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":10,"wins":6},"meituan/longcat-2.0":{"draws":22,"losses":18,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":15,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":13},"o3":{"draws":12,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":21,"losses":2,"wins":15},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":5,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":24,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":5}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":3,"losses":22,"wins":3},"claude-opus-4-5":{"draws":28,"losses":33,"wins":11},"claude-opus-4-8":{"draws":11,"losses":28,"wins":7},"claude-opus-5":{"draws":8,"losses":46,"wins":2},"claude-sonnet-5":{"draws":28,"losses":37,"wins":9},"cohere/north-mini-code":{"draws":15,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":38,"losses":25,"wins":25},"deepseek/deepseek-v4-pro":{"draws":18,"losses":28,"wins":10},"google/gemini-3.1-flash-lite":{"draws":13,"losses":27,"wins":32},"google/gemini-3.5-flash":{"draws":18,"losses":15,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":9},"google/gemini-3.6-flash":{"draws":16,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":14,"losses":19,"wins":15},"gpt-4.1":{"draws":13,"losses":9,"wins":8},"gpt-5":{"draws":13,"losses":17,"wins":4},"gpt-5.4":{"draws":23,"losses":31,"wins":12},"gpt-5.4-mini":{"draws":25,"losses":19,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":18,"wins":27},"gpt-5.5":{"draws":28,"losses":31,"wins":1},"gpt-5.6-luna":{"draws":32,"losses":21,"wins":25},"gpt-5.6-sol":{"draws":5,"losses":39,"wins":12},"gpt-5.6-terra":{"draws":22,"losses":37,"wins":7},"inclusionai/ling-3.0-flash":{"draws":26,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":13},"minimax/minimax-m3":{"draws":14,"losses":19,"wins":15},"mistralai/mistral-medium-3-5":{"draws":9,"losses":14,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":23,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":22,"wins":24},"o3":{"draws":11,"losses":15,"wins":20},"openai/gpt-oss-120b":{"draws":24,"losses":22,"wins":12},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":10},"qwen/qwen3.7-max":{"draws":18,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":18,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":18,"wins":20},"tencent/hy3-preview":{"draws":21,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":17,"wins":20},"x-ai/grok-4.5":{"draws":2,"losses":12,"wins":6},"x-ai/grok-build-0.1":{"draws":11,"losses":7,"wins":6},"xiaomi/mimo-v2.5":{"draws":48,"losses":49,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":32,"losses":34,"wins":12}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":19,"losses":19,"wins":12},"claude-opus-4-8":{"draws":11,"losses":23,"wins":12},"claude-opus-5":{"draws":6,"losses":55,"wins":3},"claude-sonnet-5":{"draws":15,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":28},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":14,"losses":6,"wins":14},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":10},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":4,"losses":6,"wins":14},"gpt-5.4":{"draws":9,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":12},"gpt-5.5":{"draws":15,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":10},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":12},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":14},"o3":{"draws":11,"losses":15,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":17,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":11,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":11,"wins":16}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":2,"losses":22,"wins":0},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":9,"losses":27,"wins":4},"claude-opus-5":{"draws":4,"losses":27,"wins":1},"claude-sonnet-5":{"draws":14,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":13,"losses":32,"wins":27},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":17,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":12},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":16,"wins":14},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-5":{"draws":14,"losses":18,"wins":2},"gpt-5.4":{"draws":6,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":21,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":29,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":25,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":11,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":24,"wins":13},"o3":{"draws":10,"losses":24,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":24,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.5":{"draws":35,"losses":42,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":21,"wins":8}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-opus-4-5":{"draws":18,"losses":16,"wins":22},"claude-opus-4-8":{"draws":13,"losses":11,"wins":18},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-sonnet-5":{"draws":21,"losses":16,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":14},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":8,"losses":8,"wins":18},"gpt-5.4":{"draws":15,"losses":17,"wins":10},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":17},"gpt-5.5":{"draws":11,"losses":21,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":20},"o3":{"draws":8,"losses":18,"wins":10},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":9,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":7,"losses":11,"wins":16}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":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":118,"losses":153,"wins":77},"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":87,"losses":179,"wins":36},"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":104,"losses":113,"wins":77},"gpt-5.6-sol":{"draws":43,"losses":214,"wins":27},"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":92,"losses":101,"wins":139},"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":77,"losses":146,"wins":87},"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":86,"losses":74,"wins":144},"gpt-5.6-sol":{"draws":46,"losses":174,"wins":84},"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},"claude-sonnet-5":{"draws":11,"losses":9,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":14,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":7,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":5,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":8,"wins":3},"gpt-5.4":{"draws":5,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":13},"gpt-5.5":{"draws":7,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":2},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":13},"o3":{"draws":8,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":4,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":1,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":13,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":26,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":3}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":5,"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},"claude-sonnet-5":{"draws":24,"losses":18,"wins":20},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":4,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":18,"wins":8},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":21,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":8},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":13},"gpt-5.5":{"draws":11,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":19,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":15},"o3":{"draws":6,"losses":16,"wins":20},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":8,"losses":18,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":31,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":19}},"gpt-5.4":{"claude-fable-5":{"draws":8,"losses":30,"wins":28},"claude-opus-4-5":{"draws":50,"losses":44,"wins":82},"claude-opus-4-8":{"draws":15,"losses":23,"wins":32},"claude-opus-5":{"draws":23,"losses":89,"wins":48},"claude-sonnet-5":{"draws":76,"losses":40,"wins":118},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":23,"losses":12,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":28},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":15,"losses":10,"wins":17},"google/gemini-3.5-flash-lite":{"draws":87,"losses":36,"wins":179},"google/gemini-3.6-flash":{"draws":77,"losses":87,"wins":146},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":13},"gpt-4.1":{"draws":8,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":7,"wins":28},"gpt-5.4":{"draws":54,"losses":73,"wins":73},"gpt-5.4-mini":{"draws":22,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":40},"gpt-5.5":{"draws":29,"losses":23,"wins":32},"gpt-5.6-luna":{"draws":86,"losses":32,"wins":133},"gpt-5.6-sol":{"draws":50,"losses":102,"wins":104},"gpt-5.6-terra":{"draws":30,"losses":19,"wins":43},"inclusionai/ling-3.0-flash":{"draws":25,"losses":11,"wins":34},"meituan/longcat-2.0":{"draws":31,"losses":22,"wins":54},"meta/muse-spark-1.2":{"draws":19,"losses":33,"wins":48},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":19},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":43,"losses":41,"wins":78},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":3,"wins":27},"o3":{"draws":18,"losses":36,"wins":134},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":63},"poolside/laguna-s-2.1":{"draws":40,"losses":6,"wins":54},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":26},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":19},"qwen/qwen3.8-max":{"draws":9,"losses":1,"wins":12},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":36},"tencent/hy3-preview":{"draws":17,"losses":4,"wins":23},"thinkingmachines/inkling":{"draws":35,"losses":22,"wins":65},"thinkingmachines/inkling-small":{"draws":9,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":35,"losses":47,"wins":76},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.5":{"draws":36,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":23},"z-ai/glm-5.2":{"draws":40,"losses":15,"wins":19}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-opus-4-5":{"draws":25,"losses":27,"wins":18},"claude-opus-4-8":{"draws":18,"losses":17,"wins":15},"claude-opus-5":{"draws":10,"losses":32,"wins":6},"claude-sonnet-5":{"draws":22,"losses":13,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":21},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":9},"google/gemini-3.5-flash-lite":{"draws":17,"losses":7,"wins":16},"google/gemini-3.6-flash":{"draws":13,"losses":23,"wins":9},"google/gemma-4-31b-it":{"draws":5,"losses":10,"wins":11},"gpt-4.1":{"draws":14,"losses":3,"wins":9},"gpt-5":{"draws":7,"losses":6,"wins":9},"gpt-5.4":{"draws":22,"losses":21,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":14,"losses":29,"wins":15},"gpt-5.5":{"draws":19,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":9,"wins":12},"gpt-5.6-sol":{"draws":15,"losses":18,"wins":5},"gpt-5.6-terra":{"draws":26,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":17},"minimax/minimax-m3":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":9},"o3":{"draws":3,"losses":4,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":12},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":27,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"z-ai/glm-5.2":{"draws":30,"losses":17,"wins":7}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":37,"wins":5},"claude-opus-4-5":{"draws":24,"losses":33,"wins":33},"claude-opus-4-8":{"draws":13,"losses":36,"wins":17},"claude-opus-5":{"draws":14,"losses":54,"wins":12},"claude-sonnet-5":{"draws":20,"losses":19,"wins":17},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":27},"deepseek/deepseek-v4-flash":{"draws":17,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":19,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":17,"wins":6},"google/gemini-3.5-flash-lite":{"draws":19,"losses":19,"wins":12},"google/gemini-3.6-flash":{"draws":18,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":3,"losses":13,"wins":22},"gpt-4.1":{"draws":5,"losses":9,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":8,"losses":13,"wins":15},"gpt-5.4":{"draws":13,"losses":40,"wins":13},"gpt-5.4-mini":{"draws":14,"losses":15,"wins":29},"gpt-5.4-nano":{"draws":12,"losses":30,"wins":30},"gpt-5.5":{"draws":16,"losses":28,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":26,"wins":30},"gpt-5.6-sol":{"draws":11,"losses":41,"wins":16},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":32},"inclusionai/ling-3.0-flash":{"draws":20,"losses":9,"wins":19},"meituan/longcat-2.0":{"draws":18,"losses":21,"wins":31},"minimax/minimax-m3":{"draws":14,"losses":18,"wins":30},"mistralai/mistral-medium-3-5":{"draws":5,"losses":13,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":16,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":15,"wins":17},"o3":{"draws":6,"losses":13,"wins":15},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":23},"poolside/laguna-s-2.1":{"draws":18,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":12,"losses":25,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":12,"losses":12,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":17,"wins":13},"x-ai/grok-4.5":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.5":{"draws":42,"losses":58,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":24,"wins":19},"z-ai/glm-5.2":{"draws":14,"losses":19,"wins":17}},"gpt-5.5":{"claude-fable-5":{"draws":8,"losses":24,"wins":22},"claude-opus-4-5":{"draws":31,"losses":24,"wins":33},"claude-opus-4-8":{"draws":19,"losses":22,"wins":35},"claude-opus-5":{"draws":21,"losses":94,"wins":33},"claude-sonnet-5":{"draws":29,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":14,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":28,"losses":1,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":3,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":6,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":26,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":10,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":29,"losses":32,"wins":23},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":18,"wins":28},"gpt-5.5":{"draws":16,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":17,"losses":31,"wins":36},"gpt-5.6-terra":{"draws":28,"losses":16,"wins":26},"inclusionai/ling-3.0-flash":{"draws":27,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":5,"wins":23},"o3":{"draws":12,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":21,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.7-max":{"draws":17,"losses":11,"wins":16},"qwen/qwen3.7-plus":{"draws":13,"losses":4,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":5,"wins":17},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":22},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":16},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":37,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":10},"z-ai/glm-5.2":{"draws":22,"losses":13,"wins":21}},"gpt-5.6-luna":{"claude-fable-5":{"draws":6,"losses":33,"wins":7},"claude-opus-4-5":{"draws":69,"losses":66,"wins":53},"claude-opus-4-8":{"draws":17,"losses":26,"wins":19},"claude-opus-5":{"draws":16,"losses":74,"wins":14},"claude-sonnet-5":{"draws":88,"losses":81,"wins":68},"cohere/north-mini-code":{"draws":5,"losses":16,"wins":7},"deepseek/deepseek-v4-flash":{"draws":32,"losses":25,"wins":21},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":15,"losses":15,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":104,"losses":77,"wins":113},"google/gemini-3.6-flash":{"draws":86,"losses":144,"wins":74},"google/gemma-4-31b-it":{"draws":8,"losses":12,"wins":8},"gpt-4.1":{"draws":12,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":19,"losses":17,"wins":16},"gpt-5.4":{"draws":86,"losses":133,"wins":32},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":30,"wins":26},"gpt-5.5":{"draws":17,"losses":29,"wins":18},"gpt-5.6-luna":{"draws":68,"losses":45,"wins":45},"gpt-5.6-sol":{"draws":37,"losses":145,"wins":44},"gpt-5.6-terra":{"draws":21,"losses":34,"wins":23},"inclusionai/ling-3.0-flash":{"draws":41,"losses":23,"wins":18},"meituan/longcat-2.0":{"draws":47,"losses":32,"wins":47},"meta/muse-spark-1.2":{"draws":29,"losses":54,"wins":31},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":57,"losses":76,"wins":43},"nex-agi/nex-n2-pro":{"draws":18,"losses":14,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":9,"wins":23},"o3":{"draws":25,"losses":80,"wins":85},"openai/gpt-oss-120b":{"draws":33,"losses":25,"wins":40},"poolside/laguna-s-2.1":{"draws":55,"losses":28,"wins":31},"qwen/qwen3.7-max":{"draws":22,"losses":11,"wins":15},"qwen/qwen3.7-plus":{"draws":11,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":7,"losses":12,"wins":5},"stepfun/step-3.7-flash":{"draws":15,"losses":19,"wins":26},"tencent/hy3-preview":{"draws":13,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":50,"losses":28,"wins":50},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":36,"losses":65,"wins":43},"x-ai/grok-build-0.1":{"draws":19,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":37,"losses":37,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":14,"wins":5},"z-ai/glm-5.2":{"draws":31,"losses":35,"wins":14}},"gpt-5.6-sol":{"claude-fable-5":{"draws":13,"losses":41,"wins":20},"claude-opus-4-5":{"draws":42,"losses":37,"wins":117},"claude-opus-4-8":{"draws":15,"losses":23,"wins":40},"claude-opus-5":{"draws":29,"losses":128,"wins":35},"claude-sonnet-5":{"draws":46,"losses":46,"wins":180},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":20},"deepseek/deepseek-v4-flash":{"draws":5,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":20},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":12,"losses":11,"wins":21},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":214},"google/gemini-3.6-flash":{"draws":46,"losses":84,"wins":174},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":10,"losses":11,"wins":31},"gpt-5.4":{"draws":50,"losses":104,"wins":102},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":41},"gpt-5.5":{"draws":17,"losses":36,"wins":31},"gpt-5.6-luna":{"draws":37,"losses":44,"wins":145},"gpt-5.6-sol":{"draws":22,"losses":71,"wins":71},"gpt-5.6-terra":{"draws":16,"losses":27,"wins":41},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":40},"meituan/longcat-2.0":{"draws":17,"losses":17,"wins":62},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":71},"minimax/minimax-m3":{"draws":11,"losses":2,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":11},"moonshotai/kimi-k3":{"draws":37,"losses":32,"wins":97},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":8,"wins":38},"o3":{"draws":9,"losses":34,"wins":141},"openai/gpt-oss-120b":{"draws":15,"losses":4,"wins":71},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":79},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":42},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":25},"thinkingmachines/inkling":{"draws":24,"losses":13,"wins":89},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":19,"losses":45,"wins":88},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":27,"losses":14,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":36}},"gpt-5.6-terra":{"claude-fable-5":{"draws":7,"losses":48,"wins":5},"claude-opus-4-5":{"draws":42,"losses":29,"wins":37},"claude-opus-4-8":{"draws":22,"losses":27,"wins":17},"claude-opus-5":{"draws":37,"losses":107,"wins":18},"claude-sonnet-5":{"draws":28,"losses":30,"wins":26},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":22,"losses":7,"wins":37},"deepseek/deepseek-v4-pro":{"draws":17,"losses":10,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":17},"google/gemini-3.6-flash":{"draws":21,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":21},"gpt-4.1":{"draws":10,"losses":7,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":30,"losses":43,"wins":19},"gpt-5.4-mini":{"draws":26,"losses":11,"wins":23},"gpt-5.4-nano":{"draws":17,"losses":32,"wins":23},"gpt-5.5":{"draws":28,"losses":26,"wins":16},"gpt-5.6-luna":{"draws":21,"losses":23,"wins":34},"gpt-5.6-sol":{"draws":16,"losses":41,"wins":27},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":13},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":8,"wins":27},"o3":{"draws":5,"losses":16,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":12},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":12,"wins":13},"x-ai/grok-4.5":{"draws":17,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":12,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":45,"losses":16,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":32,"losses":25,"wins":17}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":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":35,"losses":44,"wins":7},"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":25,"losses":34,"wins":11},"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":41,"losses":18,"wins":23},"gpt-5.6-sol":{"draws":11,"losses":40,"wins":5},"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":44,"losses":79,"wins":19},"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":31,"losses":54,"wins":22},"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":47,"losses":47,"wins":32},"gpt-5.6-sol":{"draws":17,"losses":62,"wins":17},"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":35,"losses":38,"wins":41},"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},"claude-sonnet-5":{"draws":11,"losses":16,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":9},"google/gemini-3.1-flash-lite":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":9,"losses":11,"wins":6},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":11,"wins":6},"gpt-5.4":{"draws":10,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":30,"wins":18},"gpt-5.5":{"draws":9,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":10},"gpt-5.6-sol":{"draws":11,"losses":23,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":18},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":9},"o3":{"draws":5,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.7-max":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":26,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":10,"wins":6}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":20,"wins":0},"claude-opus-4-8":{"draws":2,"losses":18,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":10,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":15,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":14,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":9,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":14,"wins":4},"gpt-5.4":{"draws":1,"losses":15,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":13},"gpt-5.5":{"draws":2,"losses":12,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":19,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":8},"o3":{"draws":3,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":22,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":6}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-sonnet-5":{"draws":6,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":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":68,"losses":41,"wins":65},"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":43,"losses":78,"wins":41},"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":57,"losses":43,"wins":76},"gpt-5.6-sol":{"draws":37,"losses":97,"wins":32},"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},"claude-sonnet-5":{"draws":8,"losses":19,"wins":7},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":8},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":4,"losses":10,"wins":2},"gpt-5.4":{"draws":10,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":16},"gpt-5.5":{"draws":8,"losses":15,"wins":3},"gpt-5.6-luna":{"draws":18,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":16,"wins":9},"o3":{"draws":2,"losses":11,"wins":3},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":7},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":29,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":14,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":4,"losses":27,"wins":1},"claude-opus-4-5":{"draws":35,"losses":29,"wins":16},"claude-opus-4-8":{"draws":14,"losses":31,"wins":11},"claude-opus-5":{"draws":11,"losses":43,"wins":0},"claude-sonnet-5":{"draws":38,"losses":25,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":36,"losses":24,"wins":22},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":13,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-5":{"draws":17,"losses":15,"wins":6},"gpt-5.4":{"draws":16,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":18,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":17,"wins":15},"gpt-5.5":{"draws":22,"losses":23,"wins":5},"gpt-5.6-luna":{"draws":32,"losses":23,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":8},"gpt-5.6-terra":{"draws":25,"losses":27,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":18},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":3},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":7},"o3":{"draws":18,"losses":30,"wins":10},"openai/gpt-oss-120b":{"draws":21,"losses":11,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":18,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":24},"x-ai/grok-4.5":{"draws":10,"losses":15,"wins":1},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":23,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":3},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":11}},"o3":{"claude-fable-5":{"draws":1,"losses":31,"wins":2},"claude-opus-4-5":{"draws":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":29,"losses":95,"wins":96},"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":18,"losses":134,"wins":36},"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":25,"losses":85,"wins":80},"gpt-5.6-sol":{"draws":9,"losses":141,"wins":34},"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":32,"losses":52,"wins":8},"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":18,"losses":63,"wins":5},"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":33,"losses":40,"wins":25},"gpt-5.6-sol":{"draws":15,"losses":71,"wins":4},"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":62,"losses":68,"wins":16},"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":40,"losses":54,"wins":6},"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":55,"losses":31,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":79,"wins":13},"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},"claude-sonnet-5":{"draws":23,"losses":10,"wins":11},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":11,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":9},"google/gemini-3.5-flash-lite":{"draws":7,"losses":7,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":14},"gpt-4.1":{"draws":7,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":10,"wins":4},"gpt-5.4":{"draws":9,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":17,"losses":15,"wins":22},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":18,"losses":4,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"o3":{"draws":10,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":9}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":23,"losses":18,"wins":11},"claude-opus-4-8":{"draws":12,"losses":20,"wins":6},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"claude-sonnet-5":{"draws":11,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":12,"losses":16,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":13,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":12,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":12,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":10,"losses":19,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":25},"gpt-5.5":{"draws":13,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":10,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":13},"o3":{"draws":3,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":8,"wins":13},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":25,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":6}},"qwen/qwen3.8-max":{"claude-opus-4-5":{"draws":5,"losses":2,"wins":4},"claude-sonnet-5":{"draws":2,"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":16,"losses":34,"wins":14},"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":8,"losses":36,"wins":6},"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":15,"losses":26,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":42,"wins":8},"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},"claude-sonnet-5":{"draws":16,"losses":12,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":11,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":3},"gpt-5":{"draws":5,"losses":9,"wins":8},"gpt-5.4":{"draws":17,"losses":23,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":12},"gpt-5.5":{"draws":24,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":13,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":13,"losses":25,"wins":10},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":11,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":14},"o3":{"draws":10,"losses":12,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":11,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":20,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":19,"losses":8,"wins":9}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":4,"losses":10,"wins":0},"claude-opus-4-5":{"draws":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":60,"losses":78,"wins":22},"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":35,"losses":65,"wins":22},"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":50,"losses":50,"wins":28},"gpt-5.6-sol":{"draws":24,"losses":89,"wins":13},"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":67,"losses":33,"wins":66},"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":35,"losses":76,"wins":47},"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":36,"losses":43,"wins":65},"gpt-5.6-sol":{"draws":19,"losses":88,"wins":45},"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},"claude-sonnet-5":{"draws":9,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":5,"losses":41,"wins":2},"claude-opus-4-5":{"draws":62,"losses":55,"wins":33},"claude-opus-4-8":{"draws":38,"losses":46,"wins":12},"claude-opus-5":{"draws":9,"losses":50,"wins":3},"claude-sonnet-5":{"draws":61,"losses":41,"wins":14},"cohere/north-mini-code":{"draws":27,"losses":15,"wins":24},"deepseek/deepseek-v4-flash":{"draws":48,"losses":31,"wins":49},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":11},"google/gemini-3.1-flash-lite":{"draws":35,"losses":25,"wins":42},"google/gemini-3.5-flash":{"draws":28,"losses":25,"wins":9},"google/gemini-3.5-flash-lite":{"draws":11,"losses":12,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":17,"losses":27,"wins":26},"gpt-4.1":{"draws":13,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":31,"losses":23,"wins":18},"gpt-5.4":{"draws":36,"losses":45,"wins":9},"gpt-5.4-mini":{"draws":39,"losses":28,"wins":27},"gpt-5.4-nano":{"draws":42,"losses":60,"wins":58},"gpt-5.5":{"draws":37,"losses":33,"wins":10},"gpt-5.6-luna":{"draws":37,"losses":30,"wins":37},"gpt-5.6-sol":{"draws":27,"losses":53,"wins":14},"gpt-5.6-terra":{"draws":45,"losses":35,"wins":16},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":24},"meituan/longcat-2.0":{"draws":23,"losses":32,"wins":29},"minimax/minimax-m3":{"draws":28,"losses":30,"wins":26},"mistralai/mistral-medium-3-5":{"draws":10,"losses":14,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":22,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":18,"losses":19,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":31,"wins":23},"o3":{"draws":12,"losses":24,"wins":4},"openai/gpt-oss-120b":{"draws":36,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":23,"losses":24,"wins":19},"qwen/qwen3.7-max":{"draws":28,"losses":31,"wins":19},"qwen/qwen3.7-plus":{"draws":23,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":28,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":42},"x-ai/grok-4.5":{"draws":16,"losses":23,"wins":5},"x-ai/grok-build-0.1":{"draws":24,"losses":18,"wins":10},"xiaomi/mimo-v2.5":{"draws":76,"losses":56,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":32,"losses":46,"wins":26}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":7,"losses":21,"wins":18},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":8,"losses":35,"wins":1},"claude-sonnet-5":{"draws":13,"losses":13,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":18},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":2,"losses":11,"wins":5},"gpt-5":{"draws":5,"losses":8,"wins":5},"gpt-5.4":{"draws":6,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":24},"gpt-5.5":{"draws":8,"losses":10,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":11},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":10},"o3":{"draws":4,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":16},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":30},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":10}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":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":34,"losses":40,"wins":26},"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":40,"losses":19,"wins":15},"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":31,"losses":14,"wins":35},"gpt-5.6-sol":{"draws":14,"losses":36,"wins":16},"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},"claude-sonnet-5":{"draws":8,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":19},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":19},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":21},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":7,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":21},"gpt-5.4":{"draws":3,"losses":14,"wins":19},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":16},"gpt-5.5":{"draws":5,"losses":11,"wins":14},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":11,"losses":8,"wins":25},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":16},"o3":{"draws":0,"losses":2,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":11},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":15},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":20},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":13}},"claude-opus-4-5":{"claude-fable-5":{"draws":0,"losses":15,"wins":1},"claude-opus-4-5":{"draws":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":37,"losses":18,"wins":27},"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":18,"losses":34,"wins":10},"gpt-5.5":{"draws":2,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":21,"losses":21,"wins":24},"gpt-5.6-sol":{"draws":9,"losses":44,"wins":15},"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},"claude-sonnet-5":{"draws":6,"losses":6,"wins":22},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":5,"wins":16},"gpt-5.4":{"draws":6,"losses":13,"wins":11},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":8},"gpt-5.5":{"draws":4,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":16,"wins":16},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":15},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":18},"o3":{"draws":0,"losses":5,"wins":25},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":6,"wins":11}},"claude-opus-5":{"claude-fable-5":{"draws":7,"losses":19,"wins":26},"claude-opus-4-5":{"draws":3,"losses":6,"wins":53},"claude-opus-4-8":{"draws":2,"losses":12,"wins":16},"claude-opus-5":{"draws":14,"losses":51,"wins":81},"claude-sonnet-5":{"draws":3,"losses":1,"wins":38},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":13},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":23},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":34},"google/gemini-3.6-flash":{"draws":4,"losses":8,"wins":34},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":0,"losses":2,"wins":16},"gpt-5.4":{"draws":0,"losses":9,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":3},"gpt-5.5":{"draws":0,"losses":7,"wins":23},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":15},"o3":{"draws":0,"losses":3,"wins":41},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":19},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":23},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"claude-sonnet-5":{"claude-fable-5":{"draws":7,"losses":16,"wins":1},"claude-opus-4-5":{"draws":38,"losses":27,"wins":33},"claude-opus-4-8":{"draws":5,"losses":21,"wins":6},"claude-opus-5":{"draws":18,"losses":65,"wins":11},"claude-sonnet-5":{"draws":20,"losses":19,"wins":35},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":21},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":8},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":11,"losses":6,"wins":9},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":63},"google/gemini-3.6-flash":{"draws":24,"losses":47,"wins":51},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":2,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":10,"wins":10},"gpt-5.4":{"draws":31,"losses":42,"wins":21},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":1},"gpt-5.5":{"draws":10,"losses":10,"wins":8},"gpt-5.6-luna":{"draws":24,"losses":28,"wins":32},"gpt-5.6-sol":{"draws":18,"losses":66,"wins":24},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":12,"losses":2,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":8,"wins":21},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":25,"losses":19,"wins":20},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":12},"o3":{"draws":7,"losses":39,"wins":44},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":19},"poolside/laguna-s-2.1":{"draws":16,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":14},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"x-ai/grok-4.5":{"draws":30,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":19}},"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},"claude-sonnet-5":{"draws":6,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":11,"wins":3},"gpt-5.4":{"draws":8,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":3},"gpt-5.5":{"draws":3,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":8},"o3":{"draws":5,"losses":11,"wins":18},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":6}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":2},"claude-opus-4-5":{"draws":9,"losses":12,"wins":3},"claude-opus-4-8":{"draws":5,"losses":13,"wins":6},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"claude-sonnet-5":{"draws":8,"losses":11,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":18},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":3,"losses":4,"wins":11},"gpt-5.4":{"draws":1,"losses":19,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":0},"gpt-5.5":{"draws":8,"losses":10,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":5},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":12},"o3":{"draws":7,"losses":13,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":7},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":8}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":6,"losses":14,"wins":2},"claude-opus-4-8":{"draws":3,"losses":13,"wins":2},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"claude-sonnet-5":{"draws":8,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":8,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":8,"wins":0},"gpt-5.4":{"draws":1,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":3},"gpt-5.5":{"draws":4,"losses":12,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":3},"o3":{"draws":4,"losses":16,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":3}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":2,"losses":16,"wins":4},"claude-opus-4-5":{"draws":8,"losses":5,"wins":11},"claude-opus-4-8":{"draws":1,"losses":6,"wins":7},"claude-opus-5":{"draws":4,"losses":32,"wins":0},"claude-sonnet-5":{"draws":9,"losses":5,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":5,"wins":7},"gpt-5.4":{"draws":3,"losses":7,"wins":6},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":8,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":9,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":12},"o3":{"draws":7,"losses":12,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":9}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":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":37,"losses":41,"wins":30},"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":18,"losses":62,"wins":16},"gpt-5.5":{"draws":6,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":29,"losses":35,"wins":30},"gpt-5.6-sol":{"draws":11,"losses":72,"wins":7},"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":12,"losses":26,"wins":66},"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":13,"losses":50,"wins":33},"gpt-5.5":{"draws":4,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":14,"losses":30,"wins":52},"gpt-5.6-sol":{"draws":9,"losses":52,"wins":39},"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},"claude-sonnet-5":{"draws":17,"losses":8,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":7,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":7},"gpt-5.5":{"draws":8,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":10},"o3":{"draws":3,"losses":12,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":5,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":11,"wins":13}},"gpt-5.4":{"claude-fable-5":{"draws":4,"losses":11,"wins":19},"claude-opus-4-5":{"draws":14,"losses":11,"wins":35},"claude-opus-4-8":{"draws":5,"losses":8,"wins":15},"claude-opus-5":{"draws":7,"losses":41,"wins":34},"claude-sonnet-5":{"draws":14,"losses":10,"wins":48},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":18},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":11},"google/gemini-3.5-flash-lite":{"draws":12,"losses":7,"wins":73},"google/gemini-3.6-flash":{"draws":15,"losses":15,"wins":70},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":3,"wins":15},"gpt-5.4":{"draws":13,"losses":4,"wins":44},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":9},"gpt-5.5":{"draws":12,"losses":6,"wins":14},"gpt-5.6-luna":{"draws":15,"losses":3,"wins":63},"gpt-5.6-sol":{"draws":18,"losses":21,"wins":49},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":21},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":22},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":22},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":34},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":17},"o3":{"draws":2,"losses":6,"wins":66},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":23},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":20},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":15},"thinkingmachines/inkling":{"draws":6,"losses":7,"wins":25},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":38},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":11}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":11,"wins":16},"claude-opus-4-5":{"draws":6,"losses":5,"wins":17},"claude-opus-4-8":{"draws":2,"losses":3,"wins":19},"claude-opus-5":{"draws":1,"losses":38,"wins":27},"claude-sonnet-5":{"draws":5,"losses":4,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":11},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":3,"wins":14},"gpt-5.4":{"draws":11,"losses":10,"wins":13},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":10},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":20},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":11},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":11},"o3":{"draws":1,"losses":2,"wins":27},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":12}},"gpt-5.6-luna":{"claude-fable-5":{"draws":4,"losses":19,"wins":5},"claude-opus-4-5":{"draws":18,"losses":14,"wins":30},"claude-opus-4-8":{"draws":3,"losses":10,"wins":13},"claude-opus-5":{"draws":10,"losses":47,"wins":9},"claude-sonnet-5":{"draws":24,"losses":19,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":8,"wins":13},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":10},"google/gemini-3.5-flash-lite":{"draws":35,"losses":14,"wins":51},"google/gemini-3.6-flash":{"draws":24,"losses":36,"wins":44},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":9,"wins":8},"gpt-5.4":{"draws":30,"losses":39,"wins":16},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":3},"gpt-5.5":{"draws":2,"losses":10,"wins":12},"gpt-5.6-luna":{"draws":18,"losses":6,"wins":23},"gpt-5.6-sol":{"draws":11,"losses":41,"wins":28},"gpt-5.6-terra":{"draws":5,"losses":15,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":13,"wins":18},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":20,"losses":14,"wins":24},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":16},"o3":{"draws":8,"losses":19,"wins":49},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":13,"losses":5,"wins":12},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":14},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":28},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":8,"wins":8}},"gpt-5.6-sol":{"claude-fable-5":{"draws":9,"losses":15,"wins":14},"claude-opus-4-5":{"draws":6,"losses":14,"wins":46},"claude-opus-4-8":{"draws":3,"losses":7,"wins":16},"claude-opus-5":{"draws":14,"losses":50,"wins":24},"claude-sonnet-5":{"draws":3,"losses":13,"wins":86},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":5,"wins":17},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":13},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":88},"google/gemini-3.6-flash":{"draws":8,"losses":20,"wins":76},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":5,"wins":18},"gpt-5.4":{"draws":9,"losses":31,"wins":46},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":7},"gpt-5.5":{"draws":3,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":3,"losses":13,"wins":58},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":11,"wins":16},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":23},"meta/muse-spark-1.2":{"draws":1,"losses":2,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":44},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":17},"o3":{"draws":1,"losses":14,"wins":59},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":20},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":19},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":13},"thinkingmachines/inkling":{"draws":5,"losses":3,"wins":32},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":7,"wins":47},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":3,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":19}},"gpt-5.6-terra":{"claude-fable-5":{"draws":4,"losses":30,"wins":4},"claude-opus-4-5":{"draws":11,"losses":8,"wins":17},"claude-opus-4-8":{"draws":1,"losses":16,"wins":5},"claude-opus-5":{"draws":12,"losses":52,"wins":10},"claude-sonnet-5":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":5,"wins":16},"gpt-5.4":{"draws":8,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":6},"gpt-5.5":{"draws":5,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":10,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":19},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":13},"o3":{"draws":1,"losses":9,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":11}},"meta/muse-spark-1.2":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":4},"claude-sonnet-5":{"draws":4,"losses":6,"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},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":15,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":12,"wins":0},"gpt-5.4":{"draws":0,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":7,"wins":7},"gpt-5.5":{"draws":0,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":9,"wins":5},"o3":{"draws":0,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":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":23,"losses":7,"wins":18},"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":12,"losses":11,"wins":13},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":23,"wins":7},"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},"claude-sonnet-5":{"draws":21,"losses":17,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":22,"losses":9,"wins":13},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":9,"wins":1},"gpt-5.4":{"draws":4,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":4},"gpt-5.5":{"draws":7,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":17,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":21},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":21,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":5,"losses":6,"wins":5}},"o3":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":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":14,"losses":65,"wins":85},"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":9,"losses":108,"wins":27},"gpt-5.5":{"draws":1,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":62,"wins":67},"gpt-5.6-sol":{"draws":5,"losses":101,"wins":28},"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},"claude-sonnet-5":{"draws":9,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":11,"losses":3,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":7,"losses":2,"wins":1},"gpt-5.4":{"draws":3,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":2},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":5},"o3":{"draws":4,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":3}},"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},"claude-sonnet-5":{"draws":4,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":4,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":6},"gpt-5.5":{"draws":0,"losses":10,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":9},"o3":{"draws":5,"losses":19,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":17},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":17,"wins":1},"claude-opus-4-5":{"draws":11,"losses":12,"wins":5},"claude-opus-4-8":{"draws":3,"losses":10,"wins":7},"claude-opus-5":{"draws":3,"losses":35,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":9,"wins":8},"gpt-5.4":{"draws":6,"losses":14,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":12,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":7},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":12},"o3":{"draws":5,"losses":12,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":8,"wins":8},"z-ai/glm-5.2":{"draws":7,"losses":3,"wins":6}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":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":24,"losses":42,"wins":12},"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":37,"wins":9},"gpt-5.5":{"draws":1,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":25,"losses":31,"wins":10},"gpt-5.6-sol":{"draws":13,"losses":47,"wins":6},"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":21,"losses":15,"wins":38},"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":15,"losses":25,"wins":28},"gpt-5.5":{"draws":3,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":20,"wins":34},"gpt-5.6-sol":{"draws":6,"losses":39,"wins":23},"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},"claude-sonnet-5":{"draws":12,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":3,"wins":2},"gpt-5.4":{"draws":5,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":3},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":2},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":4}},"z-ai/glm-5.2":{"claude-opus-4-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5":{"draws":3,"losses":11,"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},"claude-sonnet-5":{"draws":3,"losses":1,"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":{"draws":5,"losses":14,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":9},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":21},"gpt-5.5":{"draws":3,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":16},"gpt-5.6-sol":{"draws":2,"losses":12,"wins":16},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":11},"o3":{"draws":1,"losses":0,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":12},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":8}},"claude-opus-4-5":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":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":19,"losses":18,"wins":37},"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":14,"losses":31,"wins":13},"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":19,"losses":17,"wins":24},"gpt-5.6-sol":{"draws":13,"losses":41,"wins":12},"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},"claude-sonnet-5":{"draws":8,"losses":4,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":9},"gpt-5.4":{"draws":6,"losses":10,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":14},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":4,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":10}},"claude-opus-5":{"claude-fable-5":{"draws":10,"losses":21,"wins":17},"claude-opus-4-5":{"draws":15,"losses":6,"wins":73},"claude-opus-4-8":{"draws":8,"losses":9,"wins":25},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"claude-sonnet-5":{"draws":12,"losses":10,"wins":44},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":21},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":19},"google/gemini-3.6-flash":{"draws":3,"losses":11,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":19},"gpt-5":{"draws":3,"losses":2,"wins":17},"gpt-5.4":{"draws":4,"losses":18,"wins":34},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":19},"gpt-5.5":{"draws":7,"losses":16,"wins":35},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":48},"gpt-5.6-terra":{"draws":17,"losses":5,"wins":44},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":5,"losses":1,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":16},"o3":{"draws":0,"losses":0,"wins":14},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":31},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":24},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":13},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":32}},"claude-sonnet-5":{"claude-fable-5":{"draws":2,"losses":12,"wins":0},"claude-opus-4-5":{"draws":21,"losses":32,"wins":21},"claude-opus-4-8":{"draws":6,"losses":5,"wins":7},"claude-opus-5":{"draws":7,"losses":22,"wins":3},"claude-sonnet-5":{"draws":23,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":4},"google/gemini-3.5-flash-lite":{"draws":35,"losses":22,"wins":49},"google/gemini-3.6-flash":{"draws":29,"losses":46,"wins":21},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":6,"wins":3},"gpt-5.4":{"draws":20,"losses":35,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":11},"gpt-5.5":{"draws":4,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":24,"losses":18,"wins":26},"gpt-5.6-sol":{"draws":10,"losses":57,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":21},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":15,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":19,"losses":24,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":4},"o3":{"draws":10,"losses":22,"wins":26},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":14},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":22},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":18,"losses":4,"wins":22},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":13,"losses":23,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":7,"wins":11}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":4,"losses":11,"wins":3},"claude-opus-4-8":{"draws":5,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":13,"wins":2},"gpt-5.4":{"draws":4,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":5},"gpt-5.5":{"draws":7,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":2,"losses":7,"wins":1},"claude-opus-4-5":{"draws":9,"losses":6,"wins":3},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":21,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":13},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":19,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":8},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-5":{"draws":7,"losses":6,"wins":1},"gpt-5.4":{"draws":10,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":13},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":3,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":3},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":15,"wins":3},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":20,"wins":4}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":13,"wins":0},"claude-opus-4-5":{"draws":6,"losses":20,"wins":0},"claude-opus-4-8":{"draws":6,"losses":10,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":1},"claude-sonnet-5":{"draws":6,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":8,"wins":9},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":13,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":9},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":6,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":1},"xiaomi/mimo-v2.5":{"draws":17,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":4}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-5":{"draws":10,"losses":11,"wins":11},"claude-opus-4-8":{"draws":12,"losses":5,"wins":11},"claude-opus-5":{"draws":7,"losses":28,"wins":11},"claude-sonnet-5":{"draws":12,"losses":11,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":4,"losses":6,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4":{"draws":12,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":15},"gpt-5.5":{"draws":3,"losses":9,"wins":14},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":8},"o3":{"draws":1,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":7}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":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":39,"losses":62,"wins":13},"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":28,"losses":58,"wins":8},"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":33,"losses":46,"wins":13},"gpt-5.6-sol":{"draws":17,"losses":67,"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":27,"losses":25,"wins":46},"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":23,"losses":41,"wins":36},"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":20,"losses":14,"wins":52},"gpt-5.6-sol":{"draws":16,"losses":41,"wins":33},"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},"claude-sonnet-5":{"draws":3,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":6,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":5,"wins":2},"gpt-5.4":{"draws":1,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":10,"wins":5},"gpt-5.5":{"draws":2,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":4,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":6,"losses":12,"wins":10},"claude-opus-4-8":{"draws":7,"losses":11,"wins":8},"claude-opus-5":{"draws":7,"losses":14,"wins":3},"claude-sonnet-5":{"draws":7,"losses":10,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":4,"losses":14,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":6},"gpt-5.5":{"draws":3,"losses":9,"wins":6},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":5},"o3":{"draws":3,"losses":4,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":6}},"gpt-5.4":{"claude-fable-5":{"draws":3,"losses":12,"wins":5},"claude-opus-4-5":{"draws":19,"losses":13,"wins":30},"claude-opus-4-8":{"draws":7,"losses":9,"wins":10},"claude-opus-5":{"draws":6,"losses":26,"wins":6},"claude-sonnet-5":{"draws":34,"losses":17,"wins":37},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":30,"losses":15,"wins":53},"google/gemini-3.6-flash":{"draws":29,"losses":36,"wins":41},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-4.1":{"draws":3,"losses":1,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":4,"wins":7},"gpt-5.4":{"draws":22,"losses":20,"wins":23},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":14},"gpt-5.5":{"draws":9,"losses":9,"wins":8},"gpt-5.6-luna":{"draws":36,"losses":14,"wins":32},"gpt-5.6-sol":{"draws":14,"losses":44,"wins":26},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":7,"losses":9,"wins":14},"meituan/longcat-2.0":{"draws":12,"losses":11,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":7,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":14,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":6},"o3":{"draws":8,"losses":11,"wins":41},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":20},"poolside/laguna-s-2.1":{"draws":15,"losses":3,"wins":24},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":8},"qwen/qwen3.8-max":{"draws":6,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":13,"losses":10,"wins":21},"thinkingmachines/inkling-small":{"draws":7,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":17,"wins":19},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":15,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":9,"wins":5}},"gpt-5.4-mini":{"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-opus-4-5":{"draws":11,"losses":16,"wins":13},"claude-opus-4-8":{"draws":8,"losses":8,"wins":12},"claude-opus-5":{"draws":6,"losses":25,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":15},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":9},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":7,"losses":2,"wins":5},"gpt-5":{"draws":3,"losses":4,"wins":9},"gpt-5.4":{"draws":10,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":8,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":14},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":5},"o3":{"draws":2,"losses":3,"wins":7},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":9},"xiaomi/mimo-v2.5":{"draws":17,"losses":7,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":10,"wins":5}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":27,"wins":5},"claude-opus-4-5":{"draws":14,"losses":17,"wins":21},"claude-opus-4-8":{"draws":6,"losses":20,"wins":8},"claude-opus-5":{"draws":3,"losses":22,"wins":11},"claude-sonnet-5":{"draws":9,"losses":14,"wins":13},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":10,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":8,"wins":9},"gpt-4.1":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":4,"losses":10,"wins":14},"gpt-5.4":{"draws":5,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":18},"gpt-5.4-nano":{"draws":2,"losses":13,"wins":21},"gpt-5.5":{"draws":7,"losses":17,"wins":10},"gpt-5.6-luna":{"draws":7,"losses":18,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":19},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":8,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":9},"o3":{"draws":3,"losses":11,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":11},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.5":{"draws":24,"losses":27,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"z-ai/glm-5.2":{"draws":5,"losses":10,"wins":13}},"gpt-5.5":{"claude-fable-5":{"draws":5,"losses":13,"wins":6},"claude-opus-4-5":{"draws":11,"losses":9,"wins":10},"claude-opus-4-8":{"draws":8,"losses":10,"wins":12},"claude-opus-5":{"draws":10,"losses":28,"wins":6},"claude-sonnet-5":{"draws":12,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":7,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":6,"wins":7},"gpt-5.4":{"draws":8,"losses":15,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":5,"losses":7,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":10,"losses":9,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":4,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":14,"wins":2},"claude-opus-4-5":{"draws":25,"losses":23,"wins":20},"claude-opus-4-8":{"draws":7,"losses":7,"wins":4},"claude-opus-5":{"draws":2,"losses":20,"wins":4},"claude-sonnet-5":{"draws":37,"losses":29,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":3},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":37,"losses":20,"wins":37},"google/gemini-3.6-flash":{"draws":25,"losses":48,"wins":23},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":5,"wins":8},"gpt-5.4":{"draws":32,"losses":41,"wins":11},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":17},"gpt-5.5":{"draws":7,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":25,"losses":12,"wins":20},"gpt-5.6-sol":{"draws":18,"losses":50,"wins":12},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":23,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":17,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":26,"wins":14},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":6},"o3":{"draws":12,"losses":20,"wins":28},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":25,"losses":10,"wins":15},"qwen/qwen3.7-max":{"draws":13,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":1},"thinkingmachines/inkling":{"draws":16,"losses":7,"wins":13},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":23,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":6,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":3}},"gpt-5.6-sol":{"claude-fable-5":{"draws":3,"losses":19,"wins":6},"claude-opus-4-5":{"draws":16,"losses":7,"wins":37},"claude-opus-4-8":{"draws":3,"losses":8,"wins":17},"claude-opus-5":{"draws":8,"losses":38,"wins":10},"claude-sonnet-5":{"draws":18,"losses":15,"wins":57},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":11,"losses":11,"wins":68},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":51},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4":{"draws":13,"losses":37,"wins":36},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":21},"gpt-5.5":{"draws":6,"losses":13,"wins":9},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":50},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":3,"losses":7,"wins":24},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":17},"o3":{"draws":7,"losses":8,"wins":43},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":25},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":27},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":34},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":17,"wins":25},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":8},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":10}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":17,"losses":10,"wins":13},"claude-opus-4-8":{"draws":9,"losses":4,"wins":7},"claude-opus-5":{"draws":11,"losses":32,"wins":3},"claude-sonnet-5":{"draws":8,"losses":8,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":5,"losses":6,"wins":7},"gpt-5.4":{"draws":10,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":10},"gpt-5.5":{"draws":11,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":4,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":5,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":9,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":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":13,"losses":29,"wins":6},"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":9,"losses":29,"wins":10},"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":15,"losses":15,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":31,"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":23,"losses":52,"wins":11},"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":20,"losses":46,"wins":17},"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":27,"losses":37,"wins":24},"gpt-5.6-sol":{"draws":14,"losses":56,"wins":10},"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":14,"wins":20},"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},"claude-sonnet-5":{"draws":9,"losses":10,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":13,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":5,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":4},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":2},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":24,"wins":8},"gpt-5.5":{"draws":5,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":3},"o3":{"draws":4,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":17,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":1}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-sonnet-5":{"draws":6,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":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":23,"losses":19,"wins":24},"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":22,"losses":36,"wins":6},"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":22,"losses":18,"wins":22},"gpt-5.6-sol":{"draws":12,"losses":38,"wins":10},"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},"claude-sonnet-5":{"draws":2,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":1,"losses":7,"wins":14},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":12},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":1,"losses":6,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":7,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":10,"wins":2},"gpt-5.4":{"draws":0,"losses":12,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":0,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":14,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":12,"wins":4},"o3":{"draws":0,"losses":8,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":16,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":0}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":8,"losses":4,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":0},"claude-opus-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":8,"losses":2,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":4,"wins":4},"gpt-5.4":{"draws":5,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":8},"gpt-5.5":{"draws":3,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":3,"losses":5,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":1}},"o3":{"claude-fable-5":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":7,"losses":16,"wins":9},"claude-opus-4-8":{"draws":4,"losses":7,"wins":3},"claude-opus-5":{"draws":2,"losses":19,"wins":3},"claude-sonnet-5":{"draws":4,"losses":11,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":15},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":4,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":12},"gpt-5.5":{"draws":7,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":8}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":3,"losses":9,"wins":0},"claude-opus-4-5":{"draws":13,"losses":14,"wins":3},"claude-opus-4-8":{"draws":7,"losses":6,"wins":3},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":7,"losses":9,"wins":4},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.6-flash":{"draws":9,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":2},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":4,"wins":1},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":5},"gpt-5.5":{"draws":10,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":9},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":6},"o3":{"draws":4,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":12,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":3,"wins":6}},"poolside/laguna-s-2.1":{"claude-opus-4-5":{"draws":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":43,"losses":45,"wins":6},"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":29,"losses":42,"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":37,"losses":24,"wins":17},"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},"claude-sonnet-5":{"draws":11,"losses":8,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":11,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":7,"wins":3},"gpt-5.4":{"draws":3,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":11},"gpt-5.5":{"draws":7,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":11,"losses":1,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":7},"o3":{"draws":7,"losses":2,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":8,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":6}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":12,"wins":1},"claude-opus-4-5":{"draws":7,"losses":11,"wins":8},"claude-opus-4-8":{"draws":6,"losses":11,"wins":3},"claude-opus-5":{"draws":4,"losses":18,"wins":0},"claude-sonnet-5":{"draws":6,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":6,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":8,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":3}},"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},"claude-sonnet-5":{"draws":7,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":0},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":7,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":1},"o3":{"draws":2,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":1}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":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":20,"losses":26,"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":10,"losses":19,"wins":7},"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":12,"losses":16,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":33,"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},"claude-sonnet-5":{"draws":10,"losses":6,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":5,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4":{"draws":5,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":12},"gpt-5.5":{"draws":6,"losses":9,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":11,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":27},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":7},"o3":{"draws":2,"losses":5,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":5,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":4}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"claude-sonnet-5":{"draws":9,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":25,"wins":12},"claude-opus-4-8":{"draws":18,"losses":19,"wins":5},"claude-opus-5":{"draws":2,"losses":17,"wins":1},"claude-sonnet-5":{"draws":33,"losses":22,"wins":5},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":17},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":9},"gpt-4.1":{"draws":3,"losses":3,"wins":4},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":19,"losses":20,"wins":5},"gpt-5.4-mini":{"draws":19,"losses":20,"wins":5},"gpt-5.4-nano":{"draws":19,"losses":28,"wins":25},"gpt-5.5":{"draws":20,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":16,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":18,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":19,"losses":11,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":17,"wins":9},"o3":{"draws":8,"losses":20,"wins":0},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":7},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":22},"x-ai/grok-4.5":{"draws":11,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":14,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":6,"losses":20,"wins":8}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":2,"losses":12,"wins":8},"claude-opus-4-8":{"draws":3,"losses":12,"wins":1},"claude-opus-5":{"draws":5,"losses":9,"wins":0},"claude-sonnet-5":{"draws":7,"losses":8,"wins":3},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":7},"gpt-4.1":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4":{"draws":2,"losses":16,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":13},"gpt-5.5":{"draws":1,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":6},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":17},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":4,"losses":12,"wins":16},"claude-opus-4-8":{"draws":12,"losses":10,"wins":4},"claude-opus-5":{"draws":1,"losses":17,"wins":0},"claude-sonnet-5":{"draws":13,"losses":8,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":7,"losses":6,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":5},"gpt-5.4":{"draws":14,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":4},"gpt-5.5":{"draws":10,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":4},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":4}}},"none":{"claude-opus-4-5":{"claude-fable-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-5":{"draws":13,"losses":4,"wins":9},"claude-opus-4-8":{"draws":3,"losses":12,"wins":9},"claude-opus-5":{"draws":10,"losses":38,"wins":6},"claude-sonnet-5":{"draws":14,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":5,"losses":5,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":7,"losses":8,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":14,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":8},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":11,"wins":15}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":6,"wins":2},"claude-opus-4-5":{"draws":8,"losses":6,"wins":14},"claude-opus-4-8":{"draws":4,"losses":1,"wins":3},"claude-opus-5":{"draws":4,"losses":19,"wins":7},"claude-sonnet-5":{"draws":3,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":12},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":14},"gpt-5.5":{"draws":5,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":6},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":11,"losses":7,"wins":4}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":17,"wins":15},"claude-opus-4-5":{"draws":17,"losses":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":24,"losses":9,"wins":39},"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":19,"losses":21,"wins":26},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":32},"gpt-5.5":{"draws":14,"losses":10,"wins":36},"gpt-5.6-luna":{"draws":9,"losses":7,"wins":36},"gpt-5.6-sol":{"draws":16,"losses":8,"wins":52},"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-fable-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":31,"losses":24,"wins":15},"claude-opus-4-8":{"draws":6,"losses":11,"wins":5},"claude-opus-5":{"draws":14,"losses":34,"wins":6},"claude-sonnet-5":{"draws":27,"losses":24,"wins":21},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":55,"losses":28,"wins":41},"google/gemini-3.6-flash":{"draws":39,"losses":46,"wins":29},"google/gemma-4-31b-it":{"draws":8,"losses":0,"wins":2},"gpt-4.1":{"draws":3,"losses":8,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":7,"losses":4,"wins":5},"gpt-5.4":{"draws":25,"losses":41,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":7},"gpt-5.5":{"draws":15,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":40,"losses":22,"wins":23},"gpt-5.6-sol":{"draws":18,"losses":57,"wins":11},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":19,"losses":1,"wins":14},"meituan/longcat-2.0":{"draws":20,"losses":8,"wins":24},"meta/muse-spark-1.2":{"draws":15,"losses":18,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":22,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":4,"wins":9},"o3":{"draws":12,"losses":35,"wins":25},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":26,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":6,"wins":23},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":24,"losses":21,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":25,"losses":9,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":10}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":5,"losses":11,"wins":0},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":2},"claude-sonnet-5":{"draws":4,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":2},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":14,"wins":6},"gpt-5.5":{"draws":7,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":8,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":16,"wins":0},"claude-opus-4-8":{"draws":3,"losses":11,"wins":2},"claude-opus-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":8,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":3,"losses":8,"wins":3},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":5},"google/gemini-3.5-flash":{"draws":9,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":5},"gpt-4.1":{"draws":5,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":4},"gpt-5.5":{"draws":10,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":4},"o3":{"draws":3,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":13,"losses":13,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":9,"losses":5,"wins":2}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":10,"losses":7,"wins":9},"claude-opus-4-8":{"draws":6,"losses":10,"wins":6},"claude-opus-5":{"draws":3,"losses":23,"wins":2},"claude-sonnet-5":{"draws":7,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":9,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":3},"gpt-5.4":{"draws":8,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":12},"gpt-5.5":{"draws":7,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":12},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":1},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":8}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":0,"losses":5,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":16,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":7},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":10,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":21,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":12,"wins":1}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":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":42,"losses":50,"wins":34},"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":41,"losses":59,"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":42,"losses":32,"wins":34},"gpt-5.6-sol":{"draws":15,"losses":75,"wins":16},"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":53,"losses":50,"wins":27},"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":41,"losses":55,"wins":18},"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":52,"losses":30,"wins":40},"gpt-5.6-sol":{"draws":21,"losses":81,"wins":12},"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},"claude-sonnet-5":{"draws":8,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":3,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":5},"o3":{"draws":4,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":22,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":3}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":5,"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-fable-5":{"draws":1,"losses":7,"wins":4},"claude-opus-4-5":{"draws":17,"losses":20,"wins":17},"claude-opus-4-8":{"draws":3,"losses":6,"wins":7},"claude-opus-5":{"draws":10,"losses":22,"wins":8},"claude-sonnet-5":{"draws":28,"losses":13,"wins":33},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":5,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":45,"losses":14,"wins":53},"google/gemini-3.6-flash":{"draws":33,"losses":36,"wins":35},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":7},"gpt-4.1":{"draws":5,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":6},"gpt-5.4":{"draws":19,"losses":49,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":35,"losses":15,"wins":38},"gpt-5.6-sol":{"draws":18,"losses":37,"wins":29},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":10},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":14,"losses":11,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":20,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":20,"losses":20,"wins":20},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":4},"o3":{"draws":8,"losses":19,"wins":27},"openai/gpt-oss-120b":{"draws":9,"losses":3,"wins":20},"poolside/laguna-s-2.1":{"draws":21,"losses":2,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":9},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":5,"wins":19},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":19},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":8},"z-ai/glm-5.2":{"draws":21,"losses":2,"wins":3}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":14,"losses":11,"wins":5},"claude-opus-4-8":{"draws":10,"losses":9,"wins":3},"claude-opus-5":{"draws":4,"losses":7,"wins":1},"claude-sonnet-5":{"draws":16,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":11,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":8,"wins":3},"gpt-4.1":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":12,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":3},"gpt-5.5":{"draws":9,"losses":4,"wins":3},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":8,"wins":1},"gpt-5.6-terra":{"draws":11,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":4},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":7,"wins":2}},"gpt-5.4-nano":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":10,"losses":16,"wins":12},"claude-opus-4-8":{"draws":7,"losses":16,"wins":9},"claude-opus-5":{"draws":11,"losses":32,"wins":1},"claude-sonnet-5":{"draws":11,"losses":5,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":19,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":8},"google/gemini-3.6-flash":{"draws":16,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":8,"losses":16,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":9},"gpt-5.5":{"draws":9,"losses":11,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":18,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":14},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":12,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":3,"losses":2,"wins":7},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":31,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":4}},"gpt-5.5":{"claude-opus-4-5":{"draws":14,"losses":10,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":4},"claude-opus-5":{"draws":10,"losses":28,"wins":0},"claude-sonnet-5":{"draws":12,"losses":9,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":8},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":15,"losses":4,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":11,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":10,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":2,"wins":9},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":22,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":1},"o3":{"draws":7,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":19,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":7}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":26,"losses":29,"wins":3},"claude-opus-4-8":{"draws":7,"losses":9,"wins":2},"claude-opus-5":{"draws":4,"losses":7,"wins":1},"claude-sonnet-5":{"draws":27,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":15,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":4},"google/gemini-3.5-flash-lite":{"draws":32,"losses":43,"wins":25},"google/gemini-3.6-flash":{"draws":37,"losses":60,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":1},"gpt-4.1":{"draws":6,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":3,"wins":0},"gpt-5.4":{"draws":24,"losses":53,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":17,"wins":6},"gpt-5.5":{"draws":8,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":25,"losses":27,"wins":2},"gpt-5.6-sol":{"draws":8,"losses":54,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":13,"wins":0},"inclusionai/ling-3.0-flash":{"draws":22,"losses":14,"wins":4},"meituan/longcat-2.0":{"draws":14,"losses":18,"wins":12},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":21,"losses":36,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":1},"o3":{"draws":5,"losses":41,"wins":8},"openai/gpt-oss-120b":{"draws":15,"losses":17,"wins":4},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":17,"losses":17,"wins":10},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":13,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":31,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"gpt-5.6-sol":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":20,"losses":16,"wins":34},"claude-opus-4-8":{"draws":9,"losses":8,"wins":7},"claude-opus-5":{"draws":7,"losses":40,"wins":1},"claude-sonnet-5":{"draws":25,"losses":18,"wins":37},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":58},"google/gemini-3.6-flash":{"draws":22,"losses":31,"wins":47},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":8},"gpt-4.1":{"draws":3,"losses":2,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":3,"wins":2},"gpt-5.4":{"draws":28,"losses":36,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":13},"gpt-5.5":{"draws":8,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":23,"losses":16,"wins":37},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":16},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":15,"wins":26},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":4},"o3":{"draws":1,"losses":12,"wins":39},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":26},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":22},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":10},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":23},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":7}},"gpt-5.6-terra":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":14,"losses":11,"wins":7},"claude-opus-4-8":{"draws":12,"losses":7,"wins":5},"claude-opus-5":{"draws":14,"losses":23,"wins":5},"claude-sonnet-5":{"draws":13,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":15,"losses":5,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":1},"google/gemini-3.6-flash":{"draws":11,"losses":6,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":12,"losses":15,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":7},"gpt-5.5":{"draws":12,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":15},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":6},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":4,"wins":11},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":3}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":14,"losses":6,"wins":2},"claude-opus-4-8":{"draws":14,"losses":4,"wins":0},"claude-opus-5":{"draws":8,"losses":17,"wins":1},"claude-sonnet-5":{"draws":22,"losses":15,"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":{"draws":16,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":18,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":14,"wins":7},"gpt-5.5":{"draws":26,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":26,"losses":3,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":11},"meituan/longcat-2.0":{"draws":35,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":5,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":39,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":17,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":16},"x-ai/grok-4.5":{"draws":10,"losses":24,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":2,"wins":4}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":16,"losses":12,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":7,"losses":31,"wins":6},"claude-sonnet-5":{"draws":21,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":18,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":19,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":17},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":25,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":7,"losses":9,"wins":6},"gpt-5.4":{"draws":11,"losses":8,"wins":5},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":16,"losses":22,"wins":16},"gpt-5.5":{"draws":13,"losses":4,"wins":9},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":7},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":9},"inclusionai/ling-3.0-flash":{"draws":33,"losses":19,"wins":24},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":6},"o3":{"draws":7,"losses":4,"wins":13},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":12},"qwen/qwen3.7-max":{"draws":17,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":11,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":17},"x-ai/grok-4.5":{"draws":14,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":17,"wins":9}},"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":19,"losses":18,"wins":15},"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},"claude-sonnet-5":{"draws":2,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":8},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4":{"draws":4,"losses":9,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":10},"gpt-5.5":{"draws":4,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":9,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":1,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":9,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":5}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-8":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":1,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":3},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":5}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":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":22,"losses":15,"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":9,"losses":31,"wins":22},"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":20,"losses":12,"wins":40},"gpt-5.6-sol":{"draws":15,"losses":36,"wins":15},"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},"claude-sonnet-5":{"draws":6,"losses":4,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":9,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":12,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":15,"losses":8,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":10,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":8},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":5},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":2,"losses":7,"wins":3},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-sonnet-5":{"draws":9,"losses":6,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":14,"wins":8},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4":{"draws":7,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":3},"gpt-5.5":{"draws":12,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":12,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":5}},"o3":{"claude-opus-4-5":{"draws":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":11,"losses":19,"wins":4},"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":5,"losses":17,"wins":6},"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":6,"losses":16,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":27,"wins":4},"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":16,"losses":36,"wins":2},"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":9,"losses":44,"wins":3},"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":16,"losses":25,"wins":17},"gpt-5.6-sol":{"draws":3,"losses":54,"wins":1},"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":19,"losses":23,"wins":10},"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":11,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":16,"losses":10,"wins":14},"gpt-5.5":{"draws":13,"losses":9,"wins":12},"gpt-5.6-luna":{"draws":18,"losses":7,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":13},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":21},"meituan/longcat-2.0":{"draws":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},"claude-sonnet-5":{"draws":12,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":12,"losses":8,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":9},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":6,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":11},"gpt-5.5":{"draws":10,"losses":4,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":3},"o3":{"draws":3,"losses":4,"wins":1},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":8},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":11,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":3}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":16,"losses":7,"wins":3},"claude-opus-4-8":{"draws":6,"losses":9,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":5,"losses":3,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":10,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":9,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":6,"wins":6},"o3":{"draws":1,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":12,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":23,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"qwen/qwen3.8-max":{"claude-sonnet-5":{"draws":2,"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":5,"losses":14,"wins":11},"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":5,"losses":22,"wins":3},"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":9,"losses":11,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":23,"wins":6},"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},"claude-sonnet-5":{"draws":10,"losses":2,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":11,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":10},"gpt-5.5":{"draws":12,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":5,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":3}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":20,"losses":22,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":6,"losses":29,"wins":7},"claude-sonnet-5":{"draws":16,"losses":10,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":17,"wins":10},"google/gemini-3.6-flash":{"draws":25,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":6,"wins":0},"gpt-5.4":{"draws":13,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":12},"gpt-5.5":{"draws":11,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":11},"o3":{"draws":5,"losses":5,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":14,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":33,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":9,"losses":14,"wins":9}},"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":36,"losses":12,"wins":20},"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":15,"losses":34,"wins":13},"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":19,"losses":17,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":38,"wins":15},"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},"claude-sonnet-5":{"draws":16,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":14},"deepseek/deepseek-v4-flash":{"draws":19,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":11,"losses":20,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":15,"wins":17},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":5},"gpt-5.4":{"draws":12,"losses":25,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":30},"gpt-5.5":{"draws":16,"losses":15,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":25},"gpt-5.6-sol":{"draws":8,"losses":24,"wins":10},"gpt-5.6-terra":{"draws":19,"losses":17,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":12},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":16,"wins":17},"poolside/laguna-s-2.1":{"draws":6,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":9,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":21,"wins":14}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":5,"losses":9,"wins":10},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":3,"losses":26,"wins":1},"claude-sonnet-5":{"draws":6,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":8,"losses":7,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":10,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":11},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":7}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":31,"wins":20},"claude-opus-4-8":{"draws":11,"losses":15,"wins":12},"claude-opus-5":{"draws":12,"losses":43,"wins":9},"claude-sonnet-5":{"draws":18,"losses":21,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":10,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":11,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-5":{"draws":9,"losses":13,"wins":12},"gpt-5.4":{"draws":18,"losses":10,"wins":10},"gpt-5.4-mini":{"draws":18,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":15},"gpt-5.5":{"draws":12,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":19,"wins":11},"gpt-5.6-terra":{"draws":27,"losses":11,"wins":18},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":6},"z-ai/glm-5.2":{"draws":16,"losses":13,"wins":17}}}}}